diff --git a/backend/backend.proto b/backend/backend.proto
index c3d3180b69ef..f42c308a283a 100644
--- a/backend/backend.proto
+++ b/backend/backend.proto
@@ -1,5 +1,7 @@
 syntax = "proto3";
 
+import "google/protobuf/any.proto";
+
 option go_package = "github.com/go-skynet/LocalAI/pkg/grpc/proto";
 option java_multiple_files = true;
 option java_package = "io.skynet.localai.backend";
@@ -107,6 +109,8 @@ message PredictOptions {
   string NegativePrompt = 40;
   int32 NDraft = 41;
   repeated string Images = 42;
+  bool UseTokenizerTemplate = 43;
+  repeated Message Messages = 44;
 }
 
 // The response message containing the result
@@ -256,3 +260,8 @@ message StatusResponse {
   State state = 1;
   MemoryUsageData memory = 2;
 }
+
+message Message {
+  string Role = 1;
+  google.protobuf.Any Content = 2;
+}
\ No newline at end of file
diff --git a/backend/python/autogptq/backend_pb2.py b/backend/python/autogptq/backend_pb2.py
index 08b896c7cad5..8d366c16d63b 100644
--- a/backend/python/autogptq/backend_pb2.py
+++ b/backend/python/autogptq/backend_pb2.py
@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 # Generated by the protocol buffer compiler.  DO NOT EDIT!
 # source: backend.proto
+# Protobuf Python Version: 4.25.1
 """Generated protocol buffer code."""
 from google.protobuf import descriptor as _descriptor
 from google.protobuf import descriptor_pool as _descriptor_pool
@@ -11,51 +12,69 @@
 _sym_db = _symbol_database.Default()
 
 
+from google.protobuf import any_pb2 as google_dot_protobuf_dot_any__pb2
 
 
-DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\rbackend.proto\x12\x07\x62\x61\x63kend\"\x0f\n\rHealthMessage\"\xa6\x06\n\x0ePredictOptions\x12\x0e\n\x06Prompt\x18\x01 \x01(\t\x12\x0c\n\x04Seed\x18\x02 \x01(\x05\x12\x0f\n\x07Threads\x18\x03 \x01(\x05\x12\x0e\n\x06Tokens\x18\x04 \x01(\x05\x12\x0c\n\x04TopK\x18\x05 \x01(\x05\x12\x0e\n\x06Repeat\x18\x06 \x01(\x05\x12\r\n\x05\x42\x61tch\x18\x07 \x01(\x05\x12\r\n\x05NKeep\x18\x08 \x01(\x05\x12\x13\n\x0bTemperature\x18\t \x01(\x02\x12\x0f\n\x07Penalty\x18\n \x01(\x02\x12\r\n\x05\x46\x31\x36KV\x18\x0b \x01(\x08\x12\x11\n\tDebugMode\x18\x0c \x01(\x08\x12\x13\n\x0bStopPrompts\x18\r \x03(\t\x12\x11\n\tIgnoreEOS\x18\x0e \x01(\x08\x12\x19\n\x11TailFreeSamplingZ\x18\x0f \x01(\x02\x12\x10\n\x08TypicalP\x18\x10 \x01(\x02\x12\x18\n\x10\x46requencyPenalty\x18\x11 \x01(\x02\x12\x17\n\x0fPresencePenalty\x18\x12 \x01(\x02\x12\x10\n\x08Mirostat\x18\x13 \x01(\x05\x12\x13\n\x0bMirostatETA\x18\x14 \x01(\x02\x12\x13\n\x0bMirostatTAU\x18\x15 \x01(\x02\x12\x12\n\nPenalizeNL\x18\x16 \x01(\x08\x12\x11\n\tLogitBias\x18\x17 \x01(\t\x12\r\n\x05MLock\x18\x19 \x01(\x08\x12\x0c\n\x04MMap\x18\x1a \x01(\x08\x12\x16\n\x0ePromptCacheAll\x18\x1b \x01(\x08\x12\x15\n\rPromptCacheRO\x18\x1c \x01(\x08\x12\x0f\n\x07Grammar\x18\x1d \x01(\t\x12\x0f\n\x07MainGPU\x18\x1e \x01(\t\x12\x13\n\x0bTensorSplit\x18\x1f \x01(\t\x12\x0c\n\x04TopP\x18  \x01(\x02\x12\x17\n\x0fPromptCachePath\x18! \x01(\t\x12\r\n\x05\x44\x65\x62ug\x18\" \x01(\x08\x12\x17\n\x0f\x45mbeddingTokens\x18# \x03(\x05\x12\x12\n\nEmbeddings\x18$ \x01(\t\x12\x14\n\x0cRopeFreqBase\x18% \x01(\x02\x12\x15\n\rRopeFreqScale\x18& \x01(\x02\x12\x1b\n\x13NegativePromptScale\x18\' \x01(\x02\x12\x16\n\x0eNegativePrompt\x18( \x01(\t\x12\x0e\n\x06NDraft\x18) \x01(\x05\x12\x0e\n\x06Images\x18* \x03(\t\"\x18\n\x05Reply\x12\x0f\n\x07message\x18\x01 \x01(\x0c\"\xb0\x08\n\x0cModelOptions\x12\r\n\x05Model\x18\x01 \x01(\t\x12\x13\n\x0b\x43ontextSize\x18\x02 \x01(\x05\x12\x0c\n\x04Seed\x18\x03 \x01(\x05\x12\x0e\n\x06NBatch\x18\x04 \x01(\x05\x12\x11\n\tF16Memory\x18\x05 \x01(\x08\x12\r\n\x05MLock\x18\x06 \x01(\x08\x12\x0c\n\x04MMap\x18\x07 \x01(\x08\x12\x11\n\tVocabOnly\x18\x08 \x01(\x08\x12\x0f\n\x07LowVRAM\x18\t \x01(\x08\x12\x12\n\nEmbeddings\x18\n \x01(\x08\x12\x0c\n\x04NUMA\x18\x0b \x01(\x08\x12\x12\n\nNGPULayers\x18\x0c \x01(\x05\x12\x0f\n\x07MainGPU\x18\r \x01(\t\x12\x13\n\x0bTensorSplit\x18\x0e \x01(\t\x12\x0f\n\x07Threads\x18\x0f \x01(\x05\x12\x19\n\x11LibrarySearchPath\x18\x10 \x01(\t\x12\x14\n\x0cRopeFreqBase\x18\x11 \x01(\x02\x12\x15\n\rRopeFreqScale\x18\x12 \x01(\x02\x12\x12\n\nRMSNormEps\x18\x13 \x01(\x02\x12\x0c\n\x04NGQA\x18\x14 \x01(\x05\x12\x11\n\tModelFile\x18\x15 \x01(\t\x12\x0e\n\x06\x44\x65vice\x18\x16 \x01(\t\x12\x11\n\tUseTriton\x18\x17 \x01(\x08\x12\x15\n\rModelBaseName\x18\x18 \x01(\t\x12\x18\n\x10UseFastTokenizer\x18\x19 \x01(\x08\x12\x14\n\x0cPipelineType\x18\x1a \x01(\t\x12\x15\n\rSchedulerType\x18\x1b \x01(\t\x12\x0c\n\x04\x43UDA\x18\x1c \x01(\x08\x12\x10\n\x08\x43\x46GScale\x18\x1d \x01(\x02\x12\x0f\n\x07IMG2IMG\x18\x1e \x01(\x08\x12\x11\n\tCLIPModel\x18\x1f \x01(\t\x12\x15\n\rCLIPSubfolder\x18  \x01(\t\x12\x10\n\x08\x43LIPSkip\x18! \x01(\x05\x12\x12\n\nControlNet\x18\x30 \x01(\t\x12\x11\n\tTokenizer\x18\" \x01(\t\x12\x10\n\x08LoraBase\x18# \x01(\t\x12\x13\n\x0bLoraAdapter\x18$ \x01(\t\x12\x11\n\tLoraScale\x18* \x01(\x02\x12\x11\n\tNoMulMatQ\x18% \x01(\x08\x12\x12\n\nDraftModel\x18\' \x01(\t\x12\x11\n\tAudioPath\x18& \x01(\t\x12\x14\n\x0cQuantization\x18( \x01(\t\x12\x1c\n\x14GPUMemoryUtilization\x18\x32 \x01(\x02\x12\x17\n\x0fTrustRemoteCode\x18\x33 \x01(\x08\x12\x14\n\x0c\x45nforceEager\x18\x34 \x01(\x08\x12\x11\n\tSwapSpace\x18\x35 \x01(\x05\x12\x13\n\x0bMaxModelLen\x18\x36 \x01(\x05\x12\x0e\n\x06MMProj\x18) \x01(\t\x12\x13\n\x0bRopeScaling\x18+ \x01(\t\x12\x15\n\rYarnExtFactor\x18, \x01(\x02\x12\x16\n\x0eYarnAttnFactor\x18- \x01(\x02\x12\x14\n\x0cYarnBetaFast\x18. \x01(\x02\x12\x14\n\x0cYarnBetaSlow\x18/ \x01(\x02\x12\x0c\n\x04Type\x18\x31 \x01(\t\"*\n\x06Result\x12\x0f\n\x07message\x18\x01 \x01(\t\x12\x0f\n\x07success\x18\x02 \x01(\x08\"%\n\x0f\x45mbeddingResult\x12\x12\n\nembeddings\x18\x01 \x03(\x02\"C\n\x11TranscriptRequest\x12\x0b\n\x03\x64st\x18\x02 \x01(\t\x12\x10\n\x08language\x18\x03 \x01(\t\x12\x0f\n\x07threads\x18\x04 \x01(\r\"N\n\x10TranscriptResult\x12,\n\x08segments\x18\x01 \x03(\x0b\x32\x1a.backend.TranscriptSegment\x12\x0c\n\x04text\x18\x02 \x01(\t\"Y\n\x11TranscriptSegment\x12\n\n\x02id\x18\x01 \x01(\x05\x12\r\n\x05start\x18\x02 \x01(\x03\x12\x0b\n\x03\x65nd\x18\x03 \x01(\x03\x12\x0c\n\x04text\x18\x04 \x01(\t\x12\x0e\n\x06tokens\x18\x05 \x03(\x05\"\xd7\x01\n\x14GenerateImageRequest\x12\x0e\n\x06height\x18\x01 \x01(\x05\x12\r\n\x05width\x18\x02 \x01(\x05\x12\x0c\n\x04mode\x18\x03 \x01(\x05\x12\x0c\n\x04step\x18\x04 \x01(\x05\x12\x0c\n\x04seed\x18\x05 \x01(\x05\x12\x17\n\x0fpositive_prompt\x18\x06 \x01(\t\x12\x17\n\x0fnegative_prompt\x18\x07 \x01(\t\x12\x0b\n\x03\x64st\x18\x08 \x01(\t\x12\x0b\n\x03src\x18\t \x01(\t\x12\x18\n\x10\x45nableParameters\x18\n \x01(\t\x12\x10\n\x08\x43LIPSkip\x18\x0b \x01(\x05\"E\n\nTTSRequest\x12\x0c\n\x04text\x18\x01 \x01(\t\x12\r\n\x05model\x18\x02 \x01(\t\x12\x0b\n\x03\x64st\x18\x03 \x01(\t\x12\r\n\x05voice\x18\x04 \x01(\t\"6\n\x14TokenizationResponse\x12\x0e\n\x06length\x18\x01 \x01(\x05\x12\x0e\n\x06tokens\x18\x02 \x03(\x05\"\x8e\x01\n\x0fMemoryUsageData\x12\r\n\x05total\x18\x01 \x01(\x04\x12:\n\tbreakdown\x18\x02 \x03(\x0b\x32\'.backend.MemoryUsageData.BreakdownEntry\x1a\x30\n\x0e\x42reakdownEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\x04:\x02\x38\x01\"\xad\x01\n\x0eStatusResponse\x12,\n\x05state\x18\x01 \x01(\x0e\x32\x1d.backend.StatusResponse.State\x12(\n\x06memory\x18\x02 \x01(\x0b\x32\x18.backend.MemoryUsageData\"C\n\x05State\x12\x11\n\rUNINITIALIZED\x10\x00\x12\x08\n\x04\x42USY\x10\x01\x12\t\n\x05READY\x10\x02\x12\x12\n\x05\x45RROR\x10\xff\xff\xff\xff\xff\xff\xff\xff\xff\x01\x32\xf4\x04\n\x07\x42\x61\x63kend\x12\x32\n\x06Health\x12\x16.backend.HealthMessage\x1a\x0e.backend.Reply\"\x00\x12\x34\n\x07Predict\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x12\x35\n\tLoadModel\x12\x15.backend.ModelOptions\x1a\x0f.backend.Result\"\x00\x12<\n\rPredictStream\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x30\x01\x12@\n\tEmbedding\x12\x17.backend.PredictOptions\x1a\x18.backend.EmbeddingResult\"\x00\x12\x41\n\rGenerateImage\x12\x1d.backend.GenerateImageRequest\x1a\x0f.backend.Result\"\x00\x12M\n\x12\x41udioTranscription\x12\x1a.backend.TranscriptRequest\x1a\x19.backend.TranscriptResult\"\x00\x12-\n\x03TTS\x12\x13.backend.TTSRequest\x1a\x0f.backend.Result\"\x00\x12J\n\x0eTokenizeString\x12\x17.backend.PredictOptions\x1a\x1d.backend.TokenizationResponse\"\x00\x12;\n\x06Status\x12\x16.backend.HealthMessage\x1a\x17.backend.StatusResponse\"\x00\x42Z\n\x19io.skynet.localai.backendB\x0eLocalAIBackendP\x01Z+github.com/go-skynet/LocalAI/pkg/grpc/protob\x06proto3')
+DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\rbackend.proto\x12\x07\x62\x61\x63kend\x1a\x19google/protobuf/any.proto\"\x1b\n\tStoresKey\x12\x0e\n\x06\x46loats\x18\x01 \x03(\x02\"\x1c\n\x0bStoresValue\x12\r\n\x05\x42ytes\x18\x01 \x01(\x0c\"Z\n\x10StoresSetOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\"7\n\x13StoresDeleteOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\"4\n\x10StoresGetOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\"Y\n\x0fStoresGetResult\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\"B\n\x11StoresFindOptions\x12\x1f\n\x03Key\x18\x01 \x01(\x0b\x32\x12.backend.StoresKey\x12\x0c\n\x04TopK\x18\x02 \x01(\x05\"p\n\x10StoresFindResult\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\x12\x14\n\x0cSimilarities\x18\x03 \x03(\x02\"\x0f\n\rHealthMessage\"\xe8\x06\n\x0ePredictOptions\x12\x0e\n\x06Prompt\x18\x01 \x01(\t\x12\x0c\n\x04Seed\x18\x02 \x01(\x05\x12\x0f\n\x07Threads\x18\x03 \x01(\x05\x12\x0e\n\x06Tokens\x18\x04 \x01(\x05\x12\x0c\n\x04TopK\x18\x05 \x01(\x05\x12\x0e\n\x06Repeat\x18\x06 \x01(\x05\x12\r\n\x05\x42\x61tch\x18\x07 \x01(\x05\x12\r\n\x05NKeep\x18\x08 \x01(\x05\x12\x13\n\x0bTemperature\x18\t \x01(\x02\x12\x0f\n\x07Penalty\x18\n \x01(\x02\x12\r\n\x05\x46\x31\x36KV\x18\x0b \x01(\x08\x12\x11\n\tDebugMode\x18\x0c \x01(\x08\x12\x13\n\x0bStopPrompts\x18\r \x03(\t\x12\x11\n\tIgnoreEOS\x18\x0e \x01(\x08\x12\x19\n\x11TailFreeSamplingZ\x18\x0f \x01(\x02\x12\x10\n\x08TypicalP\x18\x10 \x01(\x02\x12\x18\n\x10\x46requencyPenalty\x18\x11 \x01(\x02\x12\x17\n\x0fPresencePenalty\x18\x12 \x01(\x02\x12\x10\n\x08Mirostat\x18\x13 \x01(\x05\x12\x13\n\x0bMirostatETA\x18\x14 \x01(\x02\x12\x13\n\x0bMirostatTAU\x18\x15 \x01(\x02\x12\x12\n\nPenalizeNL\x18\x16 \x01(\x08\x12\x11\n\tLogitBias\x18\x17 \x01(\t\x12\r\n\x05MLock\x18\x19 \x01(\x08\x12\x0c\n\x04MMap\x18\x1a \x01(\x08\x12\x16\n\x0ePromptCacheAll\x18\x1b \x01(\x08\x12\x15\n\rPromptCacheRO\x18\x1c \x01(\x08\x12\x0f\n\x07Grammar\x18\x1d \x01(\t\x12\x0f\n\x07MainGPU\x18\x1e \x01(\t\x12\x13\n\x0bTensorSplit\x18\x1f \x01(\t\x12\x0c\n\x04TopP\x18  \x01(\x02\x12\x17\n\x0fPromptCachePath\x18! \x01(\t\x12\r\n\x05\x44\x65\x62ug\x18\" \x01(\x08\x12\x17\n\x0f\x45mbeddingTokens\x18# \x03(\x05\x12\x12\n\nEmbeddings\x18$ \x01(\t\x12\x14\n\x0cRopeFreqBase\x18% \x01(\x02\x12\x15\n\rRopeFreqScale\x18& \x01(\x02\x12\x1b\n\x13NegativePromptScale\x18\' \x01(\x02\x12\x16\n\x0eNegativePrompt\x18( \x01(\t\x12\x0e\n\x06NDraft\x18) \x01(\x05\x12\x0e\n\x06Images\x18* \x03(\t\x12\x1c\n\x14UseTokenizerTemplate\x18+ \x01(\x08\x12\"\n\x08Messages\x18, \x03(\x0b\x32\x10.backend.Message\"\x18\n\x05Reply\x12\x0f\n\x07message\x18\x01 \x01(\x0c\"\xb0\x08\n\x0cModelOptions\x12\r\n\x05Model\x18\x01 \x01(\t\x12\x13\n\x0b\x43ontextSize\x18\x02 \x01(\x05\x12\x0c\n\x04Seed\x18\x03 \x01(\x05\x12\x0e\n\x06NBatch\x18\x04 \x01(\x05\x12\x11\n\tF16Memory\x18\x05 \x01(\x08\x12\r\n\x05MLock\x18\x06 \x01(\x08\x12\x0c\n\x04MMap\x18\x07 \x01(\x08\x12\x11\n\tVocabOnly\x18\x08 \x01(\x08\x12\x0f\n\x07LowVRAM\x18\t \x01(\x08\x12\x12\n\nEmbeddings\x18\n \x01(\x08\x12\x0c\n\x04NUMA\x18\x0b \x01(\x08\x12\x12\n\nNGPULayers\x18\x0c \x01(\x05\x12\x0f\n\x07MainGPU\x18\r \x01(\t\x12\x13\n\x0bTensorSplit\x18\x0e \x01(\t\x12\x0f\n\x07Threads\x18\x0f \x01(\x05\x12\x19\n\x11LibrarySearchPath\x18\x10 \x01(\t\x12\x14\n\x0cRopeFreqBase\x18\x11 \x01(\x02\x12\x15\n\rRopeFreqScale\x18\x12 \x01(\x02\x12\x12\n\nRMSNormEps\x18\x13 \x01(\x02\x12\x0c\n\x04NGQA\x18\x14 \x01(\x05\x12\x11\n\tModelFile\x18\x15 \x01(\t\x12\x0e\n\x06\x44\x65vice\x18\x16 \x01(\t\x12\x11\n\tUseTriton\x18\x17 \x01(\x08\x12\x15\n\rModelBaseName\x18\x18 \x01(\t\x12\x18\n\x10UseFastTokenizer\x18\x19 \x01(\x08\x12\x14\n\x0cPipelineType\x18\x1a \x01(\t\x12\x15\n\rSchedulerType\x18\x1b \x01(\t\x12\x0c\n\x04\x43UDA\x18\x1c \x01(\x08\x12\x10\n\x08\x43\x46GScale\x18\x1d \x01(\x02\x12\x0f\n\x07IMG2IMG\x18\x1e \x01(\x08\x12\x11\n\tCLIPModel\x18\x1f \x01(\t\x12\x15\n\rCLIPSubfolder\x18  \x01(\t\x12\x10\n\x08\x43LIPSkip\x18! \x01(\x05\x12\x12\n\nControlNet\x18\x30 \x01(\t\x12\x11\n\tTokenizer\x18\" \x01(\t\x12\x10\n\x08LoraBase\x18# \x01(\t\x12\x13\n\x0bLoraAdapter\x18$ \x01(\t\x12\x11\n\tLoraScale\x18* \x01(\x02\x12\x11\n\tNoMulMatQ\x18% \x01(\x08\x12\x12\n\nDraftModel\x18\' \x01(\t\x12\x11\n\tAudioPath\x18& \x01(\t\x12\x14\n\x0cQuantization\x18( \x01(\t\x12\x1c\n\x14GPUMemoryUtilization\x18\x32 \x01(\x02\x12\x17\n\x0fTrustRemoteCode\x18\x33 \x01(\x08\x12\x14\n\x0c\x45nforceEager\x18\x34 \x01(\x08\x12\x11\n\tSwapSpace\x18\x35 \x01(\x05\x12\x13\n\x0bMaxModelLen\x18\x36 \x01(\x05\x12\x0e\n\x06MMProj\x18) \x01(\t\x12\x13\n\x0bRopeScaling\x18+ \x01(\t\x12\x15\n\rYarnExtFactor\x18, \x01(\x02\x12\x16\n\x0eYarnAttnFactor\x18- \x01(\x02\x12\x14\n\x0cYarnBetaFast\x18. \x01(\x02\x12\x14\n\x0cYarnBetaSlow\x18/ \x01(\x02\x12\x0c\n\x04Type\x18\x31 \x01(\t\"*\n\x06Result\x12\x0f\n\x07message\x18\x01 \x01(\t\x12\x0f\n\x07success\x18\x02 \x01(\x08\"%\n\x0f\x45mbeddingResult\x12\x12\n\nembeddings\x18\x01 \x03(\x02\"C\n\x11TranscriptRequest\x12\x0b\n\x03\x64st\x18\x02 \x01(\t\x12\x10\n\x08language\x18\x03 \x01(\t\x12\x0f\n\x07threads\x18\x04 \x01(\r\"N\n\x10TranscriptResult\x12,\n\x08segments\x18\x01 \x03(\x0b\x32\x1a.backend.TranscriptSegment\x12\x0c\n\x04text\x18\x02 \x01(\t\"Y\n\x11TranscriptSegment\x12\n\n\x02id\x18\x01 \x01(\x05\x12\r\n\x05start\x18\x02 \x01(\x03\x12\x0b\n\x03\x65nd\x18\x03 \x01(\x03\x12\x0c\n\x04text\x18\x04 \x01(\t\x12\x0e\n\x06tokens\x18\x05 \x03(\x05\"\xd7\x01\n\x14GenerateImageRequest\x12\x0e\n\x06height\x18\x01 \x01(\x05\x12\r\n\x05width\x18\x02 \x01(\x05\x12\x0c\n\x04mode\x18\x03 \x01(\x05\x12\x0c\n\x04step\x18\x04 \x01(\x05\x12\x0c\n\x04seed\x18\x05 \x01(\x05\x12\x17\n\x0fpositive_prompt\x18\x06 \x01(\t\x12\x17\n\x0fnegative_prompt\x18\x07 \x01(\t\x12\x0b\n\x03\x64st\x18\x08 \x01(\t\x12\x0b\n\x03src\x18\t \x01(\t\x12\x18\n\x10\x45nableParameters\x18\n \x01(\t\x12\x10\n\x08\x43LIPSkip\x18\x0b \x01(\x05\"E\n\nTTSRequest\x12\x0c\n\x04text\x18\x01 \x01(\t\x12\r\n\x05model\x18\x02 \x01(\t\x12\x0b\n\x03\x64st\x18\x03 \x01(\t\x12\r\n\x05voice\x18\x04 \x01(\t\"6\n\x14TokenizationResponse\x12\x0e\n\x06length\x18\x01 \x01(\x05\x12\x0e\n\x06tokens\x18\x02 \x03(\x05\"\x8e\x01\n\x0fMemoryUsageData\x12\r\n\x05total\x18\x01 \x01(\x04\x12:\n\tbreakdown\x18\x02 \x03(\x0b\x32\'.backend.MemoryUsageData.BreakdownEntry\x1a\x30\n\x0e\x42reakdownEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\x04:\x02\x38\x01\"\xad\x01\n\x0eStatusResponse\x12,\n\x05state\x18\x01 \x01(\x0e\x32\x1d.backend.StatusResponse.State\x12(\n\x06memory\x18\x02 \x01(\x0b\x32\x18.backend.MemoryUsageData\"C\n\x05State\x12\x11\n\rUNINITIALIZED\x10\x00\x12\x08\n\x04\x42USY\x10\x01\x12\t\n\x05READY\x10\x02\x12\x12\n\x05\x45RROR\x10\xff\xff\xff\xff\xff\xff\xff\xff\xff\x01\">\n\x07Message\x12\x0c\n\x04Role\x18\x01 \x01(\t\x12%\n\x07\x43ontent\x18\x02 \x01(\x0b\x32\x14.google.protobuf.Any2\xfb\x06\n\x07\x42\x61\x63kend\x12\x32\n\x06Health\x12\x16.backend.HealthMessage\x1a\x0e.backend.Reply\"\x00\x12\x34\n\x07Predict\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x12\x35\n\tLoadModel\x12\x15.backend.ModelOptions\x1a\x0f.backend.Result\"\x00\x12<\n\rPredictStream\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x30\x01\x12@\n\tEmbedding\x12\x17.backend.PredictOptions\x1a\x18.backend.EmbeddingResult\"\x00\x12\x41\n\rGenerateImage\x12\x1d.backend.GenerateImageRequest\x1a\x0f.backend.Result\"\x00\x12M\n\x12\x41udioTranscription\x12\x1a.backend.TranscriptRequest\x1a\x19.backend.TranscriptResult\"\x00\x12-\n\x03TTS\x12\x13.backend.TTSRequest\x1a\x0f.backend.Result\"\x00\x12J\n\x0eTokenizeString\x12\x17.backend.PredictOptions\x1a\x1d.backend.TokenizationResponse\"\x00\x12;\n\x06Status\x12\x16.backend.HealthMessage\x1a\x17.backend.StatusResponse\"\x00\x12\x39\n\tStoresSet\x12\x19.backend.StoresSetOptions\x1a\x0f.backend.Result\"\x00\x12?\n\x0cStoresDelete\x12\x1c.backend.StoresDeleteOptions\x1a\x0f.backend.Result\"\x00\x12\x42\n\tStoresGet\x12\x19.backend.StoresGetOptions\x1a\x18.backend.StoresGetResult\"\x00\x12\x45\n\nStoresFind\x12\x1a.backend.StoresFindOptions\x1a\x19.backend.StoresFindResult\"\x00\x42Z\n\x19io.skynet.localai.backendB\x0eLocalAIBackendP\x01Z+github.com/go-skynet/LocalAI/pkg/grpc/protob\x06proto3')
 
 _globals = globals()
 _builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, _globals)
 _builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, 'backend_pb2', _globals)
 if _descriptor._USE_C_DESCRIPTORS == False:
-
-  DESCRIPTOR._options = None
-  DESCRIPTOR._serialized_options = b'\n\031io.skynet.localai.backendB\016LocalAIBackendP\001Z+github.com/go-skynet/LocalAI/pkg/grpc/proto'
-  _MEMORYUSAGEDATA_BREAKDOWNENTRY._options = None
-  _MEMORYUSAGEDATA_BREAKDOWNENTRY._serialized_options = b'8\001'
-  _globals['_HEALTHMESSAGE']._serialized_start=26
-  _globals['_HEALTHMESSAGE']._serialized_end=41
-  _globals['_PREDICTOPTIONS']._serialized_start=44
-  _globals['_PREDICTOPTIONS']._serialized_end=850
-  _globals['_REPLY']._serialized_start=852
-  _globals['_REPLY']._serialized_end=876
-  _globals['_MODELOPTIONS']._serialized_start=879
-  _globals['_MODELOPTIONS']._serialized_end=1951
-  _globals['_RESULT']._serialized_start=1953
-  _globals['_RESULT']._serialized_end=1995
-  _globals['_EMBEDDINGRESULT']._serialized_start=1997
-  _globals['_EMBEDDINGRESULT']._serialized_end=2034
-  _globals['_TRANSCRIPTREQUEST']._serialized_start=2036
-  _globals['_TRANSCRIPTREQUEST']._serialized_end=2103
-  _globals['_TRANSCRIPTRESULT']._serialized_start=2105
-  _globals['_TRANSCRIPTRESULT']._serialized_end=2183
-  _globals['_TRANSCRIPTSEGMENT']._serialized_start=2185
-  _globals['_TRANSCRIPTSEGMENT']._serialized_end=2274
-  _globals['_GENERATEIMAGEREQUEST']._serialized_start=2277
-  _globals['_GENERATEIMAGEREQUEST']._serialized_end=2492
-  _globals['_TTSREQUEST']._serialized_start=2494
-  _globals['_TTSREQUEST']._serialized_end=2563
-  _globals['_TOKENIZATIONRESPONSE']._serialized_start=2565
-  _globals['_TOKENIZATIONRESPONSE']._serialized_end=2619
-  _globals['_MEMORYUSAGEDATA']._serialized_start=2622
-  _globals['_MEMORYUSAGEDATA']._serialized_end=2764
-  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_start=2716
-  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_end=2764
-  _globals['_STATUSRESPONSE']._serialized_start=2767
-  _globals['_STATUSRESPONSE']._serialized_end=2940
-  _globals['_STATUSRESPONSE_STATE']._serialized_start=2873
-  _globals['_STATUSRESPONSE_STATE']._serialized_end=2940
-  _globals['_BACKEND']._serialized_start=2943
-  _globals['_BACKEND']._serialized_end=3571
+  _globals['DESCRIPTOR']._options = None
+  _globals['DESCRIPTOR']._serialized_options = b'\n\031io.skynet.localai.backendB\016LocalAIBackendP\001Z+github.com/go-skynet/LocalAI/pkg/grpc/proto'
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._options = None
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_options = b'8\001'
+  _globals['_STORESKEY']._serialized_start=53
+  _globals['_STORESKEY']._serialized_end=80
+  _globals['_STORESVALUE']._serialized_start=82
+  _globals['_STORESVALUE']._serialized_end=110
+  _globals['_STORESSETOPTIONS']._serialized_start=112
+  _globals['_STORESSETOPTIONS']._serialized_end=202
+  _globals['_STORESDELETEOPTIONS']._serialized_start=204
+  _globals['_STORESDELETEOPTIONS']._serialized_end=259
+  _globals['_STORESGETOPTIONS']._serialized_start=261
+  _globals['_STORESGETOPTIONS']._serialized_end=313
+  _globals['_STORESGETRESULT']._serialized_start=315
+  _globals['_STORESGETRESULT']._serialized_end=404
+  _globals['_STORESFINDOPTIONS']._serialized_start=406
+  _globals['_STORESFINDOPTIONS']._serialized_end=472
+  _globals['_STORESFINDRESULT']._serialized_start=474
+  _globals['_STORESFINDRESULT']._serialized_end=586
+  _globals['_HEALTHMESSAGE']._serialized_start=588
+  _globals['_HEALTHMESSAGE']._serialized_end=603
+  _globals['_PREDICTOPTIONS']._serialized_start=606
+  _globals['_PREDICTOPTIONS']._serialized_end=1478
+  _globals['_REPLY']._serialized_start=1480
+  _globals['_REPLY']._serialized_end=1504
+  _globals['_MODELOPTIONS']._serialized_start=1507
+  _globals['_MODELOPTIONS']._serialized_end=2579
+  _globals['_RESULT']._serialized_start=2581
+  _globals['_RESULT']._serialized_end=2623
+  _globals['_EMBEDDINGRESULT']._serialized_start=2625
+  _globals['_EMBEDDINGRESULT']._serialized_end=2662
+  _globals['_TRANSCRIPTREQUEST']._serialized_start=2664
+  _globals['_TRANSCRIPTREQUEST']._serialized_end=2731
+  _globals['_TRANSCRIPTRESULT']._serialized_start=2733
+  _globals['_TRANSCRIPTRESULT']._serialized_end=2811
+  _globals['_TRANSCRIPTSEGMENT']._serialized_start=2813
+  _globals['_TRANSCRIPTSEGMENT']._serialized_end=2902
+  _globals['_GENERATEIMAGEREQUEST']._serialized_start=2905
+  _globals['_GENERATEIMAGEREQUEST']._serialized_end=3120
+  _globals['_TTSREQUEST']._serialized_start=3122
+  _globals['_TTSREQUEST']._serialized_end=3191
+  _globals['_TOKENIZATIONRESPONSE']._serialized_start=3193
+  _globals['_TOKENIZATIONRESPONSE']._serialized_end=3247
+  _globals['_MEMORYUSAGEDATA']._serialized_start=3250
+  _globals['_MEMORYUSAGEDATA']._serialized_end=3392
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_start=3344
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_end=3392
+  _globals['_STATUSRESPONSE']._serialized_start=3395
+  _globals['_STATUSRESPONSE']._serialized_end=3568
+  _globals['_STATUSRESPONSE_STATE']._serialized_start=3501
+  _globals['_STATUSRESPONSE_STATE']._serialized_end=3568
+  _globals['_MESSAGE']._serialized_start=3570
+  _globals['_MESSAGE']._serialized_end=3632
+  _globals['_BACKEND']._serialized_start=3635
+  _globals['_BACKEND']._serialized_end=4526
 # @@protoc_insertion_point(module_scope)
diff --git a/backend/python/autogptq/backend_pb2_grpc.py b/backend/python/autogptq/backend_pb2_grpc.py
index 79a7677fb27f..e06fccf3d451 100644
--- a/backend/python/autogptq/backend_pb2_grpc.py
+++ b/backend/python/autogptq/backend_pb2_grpc.py
@@ -64,6 +64,26 @@ def __init__(self, channel):
                 request_serializer=backend__pb2.HealthMessage.SerializeToString,
                 response_deserializer=backend__pb2.StatusResponse.FromString,
                 )
+        self.StoresSet = channel.unary_unary(
+                '/backend.Backend/StoresSet',
+                request_serializer=backend__pb2.StoresSetOptions.SerializeToString,
+                response_deserializer=backend__pb2.Result.FromString,
+                )
+        self.StoresDelete = channel.unary_unary(
+                '/backend.Backend/StoresDelete',
+                request_serializer=backend__pb2.StoresDeleteOptions.SerializeToString,
+                response_deserializer=backend__pb2.Result.FromString,
+                )
+        self.StoresGet = channel.unary_unary(
+                '/backend.Backend/StoresGet',
+                request_serializer=backend__pb2.StoresGetOptions.SerializeToString,
+                response_deserializer=backend__pb2.StoresGetResult.FromString,
+                )
+        self.StoresFind = channel.unary_unary(
+                '/backend.Backend/StoresFind',
+                request_serializer=backend__pb2.StoresFindOptions.SerializeToString,
+                response_deserializer=backend__pb2.StoresFindResult.FromString,
+                )
 
 
 class BackendServicer(object):
@@ -129,6 +149,30 @@ def Status(self, request, context):
         context.set_details('Method not implemented!')
         raise NotImplementedError('Method not implemented!')
 
+    def StoresSet(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresDelete(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresGet(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresFind(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
 
 def add_BackendServicer_to_server(servicer, server):
     rpc_method_handlers = {
@@ -182,6 +226,26 @@ def add_BackendServicer_to_server(servicer, server):
                     request_deserializer=backend__pb2.HealthMessage.FromString,
                     response_serializer=backend__pb2.StatusResponse.SerializeToString,
             ),
+            'StoresSet': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresSet,
+                    request_deserializer=backend__pb2.StoresSetOptions.FromString,
+                    response_serializer=backend__pb2.Result.SerializeToString,
+            ),
+            'StoresDelete': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresDelete,
+                    request_deserializer=backend__pb2.StoresDeleteOptions.FromString,
+                    response_serializer=backend__pb2.Result.SerializeToString,
+            ),
+            'StoresGet': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresGet,
+                    request_deserializer=backend__pb2.StoresGetOptions.FromString,
+                    response_serializer=backend__pb2.StoresGetResult.SerializeToString,
+            ),
+            'StoresFind': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresFind,
+                    request_deserializer=backend__pb2.StoresFindOptions.FromString,
+                    response_serializer=backend__pb2.StoresFindResult.SerializeToString,
+            ),
     }
     generic_handler = grpc.method_handlers_generic_handler(
             'backend.Backend', rpc_method_handlers)
@@ -361,3 +425,71 @@ def Status(request,
             backend__pb2.StatusResponse.FromString,
             options, channel_credentials,
             insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresSet(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresSet',
+            backend__pb2.StoresSetOptions.SerializeToString,
+            backend__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresDelete(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresDelete',
+            backend__pb2.StoresDeleteOptions.SerializeToString,
+            backend__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresGet(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresGet',
+            backend__pb2.StoresGetOptions.SerializeToString,
+            backend__pb2.StoresGetResult.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresFind(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresFind',
+            backend__pb2.StoresFindOptions.SerializeToString,
+            backend__pb2.StoresFindResult.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
diff --git a/backend/python/bark/backend_pb2.py b/backend/python/bark/backend_pb2.py
index 08b896c7cad5..8d366c16d63b 100644
--- a/backend/python/bark/backend_pb2.py
+++ b/backend/python/bark/backend_pb2.py
@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 # Generated by the protocol buffer compiler.  DO NOT EDIT!
 # source: backend.proto
+# Protobuf Python Version: 4.25.1
 """Generated protocol buffer code."""
 from google.protobuf import descriptor as _descriptor
 from google.protobuf import descriptor_pool as _descriptor_pool
@@ -11,51 +12,69 @@
 _sym_db = _symbol_database.Default()
 
 
+from google.protobuf import any_pb2 as google_dot_protobuf_dot_any__pb2
 
 
-DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\rbackend.proto\x12\x07\x62\x61\x63kend\"\x0f\n\rHealthMessage\"\xa6\x06\n\x0ePredictOptions\x12\x0e\n\x06Prompt\x18\x01 \x01(\t\x12\x0c\n\x04Seed\x18\x02 \x01(\x05\x12\x0f\n\x07Threads\x18\x03 \x01(\x05\x12\x0e\n\x06Tokens\x18\x04 \x01(\x05\x12\x0c\n\x04TopK\x18\x05 \x01(\x05\x12\x0e\n\x06Repeat\x18\x06 \x01(\x05\x12\r\n\x05\x42\x61tch\x18\x07 \x01(\x05\x12\r\n\x05NKeep\x18\x08 \x01(\x05\x12\x13\n\x0bTemperature\x18\t \x01(\x02\x12\x0f\n\x07Penalty\x18\n \x01(\x02\x12\r\n\x05\x46\x31\x36KV\x18\x0b \x01(\x08\x12\x11\n\tDebugMode\x18\x0c \x01(\x08\x12\x13\n\x0bStopPrompts\x18\r \x03(\t\x12\x11\n\tIgnoreEOS\x18\x0e \x01(\x08\x12\x19\n\x11TailFreeSamplingZ\x18\x0f \x01(\x02\x12\x10\n\x08TypicalP\x18\x10 \x01(\x02\x12\x18\n\x10\x46requencyPenalty\x18\x11 \x01(\x02\x12\x17\n\x0fPresencePenalty\x18\x12 \x01(\x02\x12\x10\n\x08Mirostat\x18\x13 \x01(\x05\x12\x13\n\x0bMirostatETA\x18\x14 \x01(\x02\x12\x13\n\x0bMirostatTAU\x18\x15 \x01(\x02\x12\x12\n\nPenalizeNL\x18\x16 \x01(\x08\x12\x11\n\tLogitBias\x18\x17 \x01(\t\x12\r\n\x05MLock\x18\x19 \x01(\x08\x12\x0c\n\x04MMap\x18\x1a \x01(\x08\x12\x16\n\x0ePromptCacheAll\x18\x1b \x01(\x08\x12\x15\n\rPromptCacheRO\x18\x1c \x01(\x08\x12\x0f\n\x07Grammar\x18\x1d \x01(\t\x12\x0f\n\x07MainGPU\x18\x1e \x01(\t\x12\x13\n\x0bTensorSplit\x18\x1f \x01(\t\x12\x0c\n\x04TopP\x18  \x01(\x02\x12\x17\n\x0fPromptCachePath\x18! \x01(\t\x12\r\n\x05\x44\x65\x62ug\x18\" \x01(\x08\x12\x17\n\x0f\x45mbeddingTokens\x18# \x03(\x05\x12\x12\n\nEmbeddings\x18$ \x01(\t\x12\x14\n\x0cRopeFreqBase\x18% \x01(\x02\x12\x15\n\rRopeFreqScale\x18& \x01(\x02\x12\x1b\n\x13NegativePromptScale\x18\' \x01(\x02\x12\x16\n\x0eNegativePrompt\x18( \x01(\t\x12\x0e\n\x06NDraft\x18) \x01(\x05\x12\x0e\n\x06Images\x18* \x03(\t\"\x18\n\x05Reply\x12\x0f\n\x07message\x18\x01 \x01(\x0c\"\xb0\x08\n\x0cModelOptions\x12\r\n\x05Model\x18\x01 \x01(\t\x12\x13\n\x0b\x43ontextSize\x18\x02 \x01(\x05\x12\x0c\n\x04Seed\x18\x03 \x01(\x05\x12\x0e\n\x06NBatch\x18\x04 \x01(\x05\x12\x11\n\tF16Memory\x18\x05 \x01(\x08\x12\r\n\x05MLock\x18\x06 \x01(\x08\x12\x0c\n\x04MMap\x18\x07 \x01(\x08\x12\x11\n\tVocabOnly\x18\x08 \x01(\x08\x12\x0f\n\x07LowVRAM\x18\t \x01(\x08\x12\x12\n\nEmbeddings\x18\n \x01(\x08\x12\x0c\n\x04NUMA\x18\x0b \x01(\x08\x12\x12\n\nNGPULayers\x18\x0c \x01(\x05\x12\x0f\n\x07MainGPU\x18\r \x01(\t\x12\x13\n\x0bTensorSplit\x18\x0e \x01(\t\x12\x0f\n\x07Threads\x18\x0f \x01(\x05\x12\x19\n\x11LibrarySearchPath\x18\x10 \x01(\t\x12\x14\n\x0cRopeFreqBase\x18\x11 \x01(\x02\x12\x15\n\rRopeFreqScale\x18\x12 \x01(\x02\x12\x12\n\nRMSNormEps\x18\x13 \x01(\x02\x12\x0c\n\x04NGQA\x18\x14 \x01(\x05\x12\x11\n\tModelFile\x18\x15 \x01(\t\x12\x0e\n\x06\x44\x65vice\x18\x16 \x01(\t\x12\x11\n\tUseTriton\x18\x17 \x01(\x08\x12\x15\n\rModelBaseName\x18\x18 \x01(\t\x12\x18\n\x10UseFastTokenizer\x18\x19 \x01(\x08\x12\x14\n\x0cPipelineType\x18\x1a \x01(\t\x12\x15\n\rSchedulerType\x18\x1b \x01(\t\x12\x0c\n\x04\x43UDA\x18\x1c \x01(\x08\x12\x10\n\x08\x43\x46GScale\x18\x1d \x01(\x02\x12\x0f\n\x07IMG2IMG\x18\x1e \x01(\x08\x12\x11\n\tCLIPModel\x18\x1f \x01(\t\x12\x15\n\rCLIPSubfolder\x18  \x01(\t\x12\x10\n\x08\x43LIPSkip\x18! \x01(\x05\x12\x12\n\nControlNet\x18\x30 \x01(\t\x12\x11\n\tTokenizer\x18\" \x01(\t\x12\x10\n\x08LoraBase\x18# \x01(\t\x12\x13\n\x0bLoraAdapter\x18$ \x01(\t\x12\x11\n\tLoraScale\x18* \x01(\x02\x12\x11\n\tNoMulMatQ\x18% \x01(\x08\x12\x12\n\nDraftModel\x18\' \x01(\t\x12\x11\n\tAudioPath\x18& \x01(\t\x12\x14\n\x0cQuantization\x18( \x01(\t\x12\x1c\n\x14GPUMemoryUtilization\x18\x32 \x01(\x02\x12\x17\n\x0fTrustRemoteCode\x18\x33 \x01(\x08\x12\x14\n\x0c\x45nforceEager\x18\x34 \x01(\x08\x12\x11\n\tSwapSpace\x18\x35 \x01(\x05\x12\x13\n\x0bMaxModelLen\x18\x36 \x01(\x05\x12\x0e\n\x06MMProj\x18) \x01(\t\x12\x13\n\x0bRopeScaling\x18+ \x01(\t\x12\x15\n\rYarnExtFactor\x18, \x01(\x02\x12\x16\n\x0eYarnAttnFactor\x18- \x01(\x02\x12\x14\n\x0cYarnBetaFast\x18. \x01(\x02\x12\x14\n\x0cYarnBetaSlow\x18/ \x01(\x02\x12\x0c\n\x04Type\x18\x31 \x01(\t\"*\n\x06Result\x12\x0f\n\x07message\x18\x01 \x01(\t\x12\x0f\n\x07success\x18\x02 \x01(\x08\"%\n\x0f\x45mbeddingResult\x12\x12\n\nembeddings\x18\x01 \x03(\x02\"C\n\x11TranscriptRequest\x12\x0b\n\x03\x64st\x18\x02 \x01(\t\x12\x10\n\x08language\x18\x03 \x01(\t\x12\x0f\n\x07threads\x18\x04 \x01(\r\"N\n\x10TranscriptResult\x12,\n\x08segments\x18\x01 \x03(\x0b\x32\x1a.backend.TranscriptSegment\x12\x0c\n\x04text\x18\x02 \x01(\t\"Y\n\x11TranscriptSegment\x12\n\n\x02id\x18\x01 \x01(\x05\x12\r\n\x05start\x18\x02 \x01(\x03\x12\x0b\n\x03\x65nd\x18\x03 \x01(\x03\x12\x0c\n\x04text\x18\x04 \x01(\t\x12\x0e\n\x06tokens\x18\x05 \x03(\x05\"\xd7\x01\n\x14GenerateImageRequest\x12\x0e\n\x06height\x18\x01 \x01(\x05\x12\r\n\x05width\x18\x02 \x01(\x05\x12\x0c\n\x04mode\x18\x03 \x01(\x05\x12\x0c\n\x04step\x18\x04 \x01(\x05\x12\x0c\n\x04seed\x18\x05 \x01(\x05\x12\x17\n\x0fpositive_prompt\x18\x06 \x01(\t\x12\x17\n\x0fnegative_prompt\x18\x07 \x01(\t\x12\x0b\n\x03\x64st\x18\x08 \x01(\t\x12\x0b\n\x03src\x18\t \x01(\t\x12\x18\n\x10\x45nableParameters\x18\n \x01(\t\x12\x10\n\x08\x43LIPSkip\x18\x0b \x01(\x05\"E\n\nTTSRequest\x12\x0c\n\x04text\x18\x01 \x01(\t\x12\r\n\x05model\x18\x02 \x01(\t\x12\x0b\n\x03\x64st\x18\x03 \x01(\t\x12\r\n\x05voice\x18\x04 \x01(\t\"6\n\x14TokenizationResponse\x12\x0e\n\x06length\x18\x01 \x01(\x05\x12\x0e\n\x06tokens\x18\x02 \x03(\x05\"\x8e\x01\n\x0fMemoryUsageData\x12\r\n\x05total\x18\x01 \x01(\x04\x12:\n\tbreakdown\x18\x02 \x03(\x0b\x32\'.backend.MemoryUsageData.BreakdownEntry\x1a\x30\n\x0e\x42reakdownEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\x04:\x02\x38\x01\"\xad\x01\n\x0eStatusResponse\x12,\n\x05state\x18\x01 \x01(\x0e\x32\x1d.backend.StatusResponse.State\x12(\n\x06memory\x18\x02 \x01(\x0b\x32\x18.backend.MemoryUsageData\"C\n\x05State\x12\x11\n\rUNINITIALIZED\x10\x00\x12\x08\n\x04\x42USY\x10\x01\x12\t\n\x05READY\x10\x02\x12\x12\n\x05\x45RROR\x10\xff\xff\xff\xff\xff\xff\xff\xff\xff\x01\x32\xf4\x04\n\x07\x42\x61\x63kend\x12\x32\n\x06Health\x12\x16.backend.HealthMessage\x1a\x0e.backend.Reply\"\x00\x12\x34\n\x07Predict\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x12\x35\n\tLoadModel\x12\x15.backend.ModelOptions\x1a\x0f.backend.Result\"\x00\x12<\n\rPredictStream\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x30\x01\x12@\n\tEmbedding\x12\x17.backend.PredictOptions\x1a\x18.backend.EmbeddingResult\"\x00\x12\x41\n\rGenerateImage\x12\x1d.backend.GenerateImageRequest\x1a\x0f.backend.Result\"\x00\x12M\n\x12\x41udioTranscription\x12\x1a.backend.TranscriptRequest\x1a\x19.backend.TranscriptResult\"\x00\x12-\n\x03TTS\x12\x13.backend.TTSRequest\x1a\x0f.backend.Result\"\x00\x12J\n\x0eTokenizeString\x12\x17.backend.PredictOptions\x1a\x1d.backend.TokenizationResponse\"\x00\x12;\n\x06Status\x12\x16.backend.HealthMessage\x1a\x17.backend.StatusResponse\"\x00\x42Z\n\x19io.skynet.localai.backendB\x0eLocalAIBackendP\x01Z+github.com/go-skynet/LocalAI/pkg/grpc/protob\x06proto3')
+DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\rbackend.proto\x12\x07\x62\x61\x63kend\x1a\x19google/protobuf/any.proto\"\x1b\n\tStoresKey\x12\x0e\n\x06\x46loats\x18\x01 \x03(\x02\"\x1c\n\x0bStoresValue\x12\r\n\x05\x42ytes\x18\x01 \x01(\x0c\"Z\n\x10StoresSetOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\"7\n\x13StoresDeleteOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\"4\n\x10StoresGetOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\"Y\n\x0fStoresGetResult\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\"B\n\x11StoresFindOptions\x12\x1f\n\x03Key\x18\x01 \x01(\x0b\x32\x12.backend.StoresKey\x12\x0c\n\x04TopK\x18\x02 \x01(\x05\"p\n\x10StoresFindResult\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\x12\x14\n\x0cSimilarities\x18\x03 \x03(\x02\"\x0f\n\rHealthMessage\"\xe8\x06\n\x0ePredictOptions\x12\x0e\n\x06Prompt\x18\x01 \x01(\t\x12\x0c\n\x04Seed\x18\x02 \x01(\x05\x12\x0f\n\x07Threads\x18\x03 \x01(\x05\x12\x0e\n\x06Tokens\x18\x04 \x01(\x05\x12\x0c\n\x04TopK\x18\x05 \x01(\x05\x12\x0e\n\x06Repeat\x18\x06 \x01(\x05\x12\r\n\x05\x42\x61tch\x18\x07 \x01(\x05\x12\r\n\x05NKeep\x18\x08 \x01(\x05\x12\x13\n\x0bTemperature\x18\t \x01(\x02\x12\x0f\n\x07Penalty\x18\n \x01(\x02\x12\r\n\x05\x46\x31\x36KV\x18\x0b \x01(\x08\x12\x11\n\tDebugMode\x18\x0c \x01(\x08\x12\x13\n\x0bStopPrompts\x18\r \x03(\t\x12\x11\n\tIgnoreEOS\x18\x0e \x01(\x08\x12\x19\n\x11TailFreeSamplingZ\x18\x0f \x01(\x02\x12\x10\n\x08TypicalP\x18\x10 \x01(\x02\x12\x18\n\x10\x46requencyPenalty\x18\x11 \x01(\x02\x12\x17\n\x0fPresencePenalty\x18\x12 \x01(\x02\x12\x10\n\x08Mirostat\x18\x13 \x01(\x05\x12\x13\n\x0bMirostatETA\x18\x14 \x01(\x02\x12\x13\n\x0bMirostatTAU\x18\x15 \x01(\x02\x12\x12\n\nPenalizeNL\x18\x16 \x01(\x08\x12\x11\n\tLogitBias\x18\x17 \x01(\t\x12\r\n\x05MLock\x18\x19 \x01(\x08\x12\x0c\n\x04MMap\x18\x1a \x01(\x08\x12\x16\n\x0ePromptCacheAll\x18\x1b \x01(\x08\x12\x15\n\rPromptCacheRO\x18\x1c \x01(\x08\x12\x0f\n\x07Grammar\x18\x1d \x01(\t\x12\x0f\n\x07MainGPU\x18\x1e \x01(\t\x12\x13\n\x0bTensorSplit\x18\x1f \x01(\t\x12\x0c\n\x04TopP\x18  \x01(\x02\x12\x17\n\x0fPromptCachePath\x18! \x01(\t\x12\r\n\x05\x44\x65\x62ug\x18\" \x01(\x08\x12\x17\n\x0f\x45mbeddingTokens\x18# \x03(\x05\x12\x12\n\nEmbeddings\x18$ \x01(\t\x12\x14\n\x0cRopeFreqBase\x18% \x01(\x02\x12\x15\n\rRopeFreqScale\x18& \x01(\x02\x12\x1b\n\x13NegativePromptScale\x18\' \x01(\x02\x12\x16\n\x0eNegativePrompt\x18( \x01(\t\x12\x0e\n\x06NDraft\x18) \x01(\x05\x12\x0e\n\x06Images\x18* \x03(\t\x12\x1c\n\x14UseTokenizerTemplate\x18+ \x01(\x08\x12\"\n\x08Messages\x18, \x03(\x0b\x32\x10.backend.Message\"\x18\n\x05Reply\x12\x0f\n\x07message\x18\x01 \x01(\x0c\"\xb0\x08\n\x0cModelOptions\x12\r\n\x05Model\x18\x01 \x01(\t\x12\x13\n\x0b\x43ontextSize\x18\x02 \x01(\x05\x12\x0c\n\x04Seed\x18\x03 \x01(\x05\x12\x0e\n\x06NBatch\x18\x04 \x01(\x05\x12\x11\n\tF16Memory\x18\x05 \x01(\x08\x12\r\n\x05MLock\x18\x06 \x01(\x08\x12\x0c\n\x04MMap\x18\x07 \x01(\x08\x12\x11\n\tVocabOnly\x18\x08 \x01(\x08\x12\x0f\n\x07LowVRAM\x18\t \x01(\x08\x12\x12\n\nEmbeddings\x18\n \x01(\x08\x12\x0c\n\x04NUMA\x18\x0b \x01(\x08\x12\x12\n\nNGPULayers\x18\x0c \x01(\x05\x12\x0f\n\x07MainGPU\x18\r \x01(\t\x12\x13\n\x0bTensorSplit\x18\x0e \x01(\t\x12\x0f\n\x07Threads\x18\x0f \x01(\x05\x12\x19\n\x11LibrarySearchPath\x18\x10 \x01(\t\x12\x14\n\x0cRopeFreqBase\x18\x11 \x01(\x02\x12\x15\n\rRopeFreqScale\x18\x12 \x01(\x02\x12\x12\n\nRMSNormEps\x18\x13 \x01(\x02\x12\x0c\n\x04NGQA\x18\x14 \x01(\x05\x12\x11\n\tModelFile\x18\x15 \x01(\t\x12\x0e\n\x06\x44\x65vice\x18\x16 \x01(\t\x12\x11\n\tUseTriton\x18\x17 \x01(\x08\x12\x15\n\rModelBaseName\x18\x18 \x01(\t\x12\x18\n\x10UseFastTokenizer\x18\x19 \x01(\x08\x12\x14\n\x0cPipelineType\x18\x1a \x01(\t\x12\x15\n\rSchedulerType\x18\x1b \x01(\t\x12\x0c\n\x04\x43UDA\x18\x1c \x01(\x08\x12\x10\n\x08\x43\x46GScale\x18\x1d \x01(\x02\x12\x0f\n\x07IMG2IMG\x18\x1e \x01(\x08\x12\x11\n\tCLIPModel\x18\x1f \x01(\t\x12\x15\n\rCLIPSubfolder\x18  \x01(\t\x12\x10\n\x08\x43LIPSkip\x18! \x01(\x05\x12\x12\n\nControlNet\x18\x30 \x01(\t\x12\x11\n\tTokenizer\x18\" \x01(\t\x12\x10\n\x08LoraBase\x18# \x01(\t\x12\x13\n\x0bLoraAdapter\x18$ \x01(\t\x12\x11\n\tLoraScale\x18* \x01(\x02\x12\x11\n\tNoMulMatQ\x18% \x01(\x08\x12\x12\n\nDraftModel\x18\' \x01(\t\x12\x11\n\tAudioPath\x18& \x01(\t\x12\x14\n\x0cQuantization\x18( \x01(\t\x12\x1c\n\x14GPUMemoryUtilization\x18\x32 \x01(\x02\x12\x17\n\x0fTrustRemoteCode\x18\x33 \x01(\x08\x12\x14\n\x0c\x45nforceEager\x18\x34 \x01(\x08\x12\x11\n\tSwapSpace\x18\x35 \x01(\x05\x12\x13\n\x0bMaxModelLen\x18\x36 \x01(\x05\x12\x0e\n\x06MMProj\x18) \x01(\t\x12\x13\n\x0bRopeScaling\x18+ \x01(\t\x12\x15\n\rYarnExtFactor\x18, \x01(\x02\x12\x16\n\x0eYarnAttnFactor\x18- \x01(\x02\x12\x14\n\x0cYarnBetaFast\x18. \x01(\x02\x12\x14\n\x0cYarnBetaSlow\x18/ \x01(\x02\x12\x0c\n\x04Type\x18\x31 \x01(\t\"*\n\x06Result\x12\x0f\n\x07message\x18\x01 \x01(\t\x12\x0f\n\x07success\x18\x02 \x01(\x08\"%\n\x0f\x45mbeddingResult\x12\x12\n\nembeddings\x18\x01 \x03(\x02\"C\n\x11TranscriptRequest\x12\x0b\n\x03\x64st\x18\x02 \x01(\t\x12\x10\n\x08language\x18\x03 \x01(\t\x12\x0f\n\x07threads\x18\x04 \x01(\r\"N\n\x10TranscriptResult\x12,\n\x08segments\x18\x01 \x03(\x0b\x32\x1a.backend.TranscriptSegment\x12\x0c\n\x04text\x18\x02 \x01(\t\"Y\n\x11TranscriptSegment\x12\n\n\x02id\x18\x01 \x01(\x05\x12\r\n\x05start\x18\x02 \x01(\x03\x12\x0b\n\x03\x65nd\x18\x03 \x01(\x03\x12\x0c\n\x04text\x18\x04 \x01(\t\x12\x0e\n\x06tokens\x18\x05 \x03(\x05\"\xd7\x01\n\x14GenerateImageRequest\x12\x0e\n\x06height\x18\x01 \x01(\x05\x12\r\n\x05width\x18\x02 \x01(\x05\x12\x0c\n\x04mode\x18\x03 \x01(\x05\x12\x0c\n\x04step\x18\x04 \x01(\x05\x12\x0c\n\x04seed\x18\x05 \x01(\x05\x12\x17\n\x0fpositive_prompt\x18\x06 \x01(\t\x12\x17\n\x0fnegative_prompt\x18\x07 \x01(\t\x12\x0b\n\x03\x64st\x18\x08 \x01(\t\x12\x0b\n\x03src\x18\t \x01(\t\x12\x18\n\x10\x45nableParameters\x18\n \x01(\t\x12\x10\n\x08\x43LIPSkip\x18\x0b \x01(\x05\"E\n\nTTSRequest\x12\x0c\n\x04text\x18\x01 \x01(\t\x12\r\n\x05model\x18\x02 \x01(\t\x12\x0b\n\x03\x64st\x18\x03 \x01(\t\x12\r\n\x05voice\x18\x04 \x01(\t\"6\n\x14TokenizationResponse\x12\x0e\n\x06length\x18\x01 \x01(\x05\x12\x0e\n\x06tokens\x18\x02 \x03(\x05\"\x8e\x01\n\x0fMemoryUsageData\x12\r\n\x05total\x18\x01 \x01(\x04\x12:\n\tbreakdown\x18\x02 \x03(\x0b\x32\'.backend.MemoryUsageData.BreakdownEntry\x1a\x30\n\x0e\x42reakdownEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\x04:\x02\x38\x01\"\xad\x01\n\x0eStatusResponse\x12,\n\x05state\x18\x01 \x01(\x0e\x32\x1d.backend.StatusResponse.State\x12(\n\x06memory\x18\x02 \x01(\x0b\x32\x18.backend.MemoryUsageData\"C\n\x05State\x12\x11\n\rUNINITIALIZED\x10\x00\x12\x08\n\x04\x42USY\x10\x01\x12\t\n\x05READY\x10\x02\x12\x12\n\x05\x45RROR\x10\xff\xff\xff\xff\xff\xff\xff\xff\xff\x01\">\n\x07Message\x12\x0c\n\x04Role\x18\x01 \x01(\t\x12%\n\x07\x43ontent\x18\x02 \x01(\x0b\x32\x14.google.protobuf.Any2\xfb\x06\n\x07\x42\x61\x63kend\x12\x32\n\x06Health\x12\x16.backend.HealthMessage\x1a\x0e.backend.Reply\"\x00\x12\x34\n\x07Predict\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x12\x35\n\tLoadModel\x12\x15.backend.ModelOptions\x1a\x0f.backend.Result\"\x00\x12<\n\rPredictStream\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x30\x01\x12@\n\tEmbedding\x12\x17.backend.PredictOptions\x1a\x18.backend.EmbeddingResult\"\x00\x12\x41\n\rGenerateImage\x12\x1d.backend.GenerateImageRequest\x1a\x0f.backend.Result\"\x00\x12M\n\x12\x41udioTranscription\x12\x1a.backend.TranscriptRequest\x1a\x19.backend.TranscriptResult\"\x00\x12-\n\x03TTS\x12\x13.backend.TTSRequest\x1a\x0f.backend.Result\"\x00\x12J\n\x0eTokenizeString\x12\x17.backend.PredictOptions\x1a\x1d.backend.TokenizationResponse\"\x00\x12;\n\x06Status\x12\x16.backend.HealthMessage\x1a\x17.backend.StatusResponse\"\x00\x12\x39\n\tStoresSet\x12\x19.backend.StoresSetOptions\x1a\x0f.backend.Result\"\x00\x12?\n\x0cStoresDelete\x12\x1c.backend.StoresDeleteOptions\x1a\x0f.backend.Result\"\x00\x12\x42\n\tStoresGet\x12\x19.backend.StoresGetOptions\x1a\x18.backend.StoresGetResult\"\x00\x12\x45\n\nStoresFind\x12\x1a.backend.StoresFindOptions\x1a\x19.backend.StoresFindResult\"\x00\x42Z\n\x19io.skynet.localai.backendB\x0eLocalAIBackendP\x01Z+github.com/go-skynet/LocalAI/pkg/grpc/protob\x06proto3')
 
 _globals = globals()
 _builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, _globals)
 _builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, 'backend_pb2', _globals)
 if _descriptor._USE_C_DESCRIPTORS == False:
-
-  DESCRIPTOR._options = None
-  DESCRIPTOR._serialized_options = b'\n\031io.skynet.localai.backendB\016LocalAIBackendP\001Z+github.com/go-skynet/LocalAI/pkg/grpc/proto'
-  _MEMORYUSAGEDATA_BREAKDOWNENTRY._options = None
-  _MEMORYUSAGEDATA_BREAKDOWNENTRY._serialized_options = b'8\001'
-  _globals['_HEALTHMESSAGE']._serialized_start=26
-  _globals['_HEALTHMESSAGE']._serialized_end=41
-  _globals['_PREDICTOPTIONS']._serialized_start=44
-  _globals['_PREDICTOPTIONS']._serialized_end=850
-  _globals['_REPLY']._serialized_start=852
-  _globals['_REPLY']._serialized_end=876
-  _globals['_MODELOPTIONS']._serialized_start=879
-  _globals['_MODELOPTIONS']._serialized_end=1951
-  _globals['_RESULT']._serialized_start=1953
-  _globals['_RESULT']._serialized_end=1995
-  _globals['_EMBEDDINGRESULT']._serialized_start=1997
-  _globals['_EMBEDDINGRESULT']._serialized_end=2034
-  _globals['_TRANSCRIPTREQUEST']._serialized_start=2036
-  _globals['_TRANSCRIPTREQUEST']._serialized_end=2103
-  _globals['_TRANSCRIPTRESULT']._serialized_start=2105
-  _globals['_TRANSCRIPTRESULT']._serialized_end=2183
-  _globals['_TRANSCRIPTSEGMENT']._serialized_start=2185
-  _globals['_TRANSCRIPTSEGMENT']._serialized_end=2274
-  _globals['_GENERATEIMAGEREQUEST']._serialized_start=2277
-  _globals['_GENERATEIMAGEREQUEST']._serialized_end=2492
-  _globals['_TTSREQUEST']._serialized_start=2494
-  _globals['_TTSREQUEST']._serialized_end=2563
-  _globals['_TOKENIZATIONRESPONSE']._serialized_start=2565
-  _globals['_TOKENIZATIONRESPONSE']._serialized_end=2619
-  _globals['_MEMORYUSAGEDATA']._serialized_start=2622
-  _globals['_MEMORYUSAGEDATA']._serialized_end=2764
-  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_start=2716
-  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_end=2764
-  _globals['_STATUSRESPONSE']._serialized_start=2767
-  _globals['_STATUSRESPONSE']._serialized_end=2940
-  _globals['_STATUSRESPONSE_STATE']._serialized_start=2873
-  _globals['_STATUSRESPONSE_STATE']._serialized_end=2940
-  _globals['_BACKEND']._serialized_start=2943
-  _globals['_BACKEND']._serialized_end=3571
+  _globals['DESCRIPTOR']._options = None
+  _globals['DESCRIPTOR']._serialized_options = b'\n\031io.skynet.localai.backendB\016LocalAIBackendP\001Z+github.com/go-skynet/LocalAI/pkg/grpc/proto'
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._options = None
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_options = b'8\001'
+  _globals['_STORESKEY']._serialized_start=53
+  _globals['_STORESKEY']._serialized_end=80
+  _globals['_STORESVALUE']._serialized_start=82
+  _globals['_STORESVALUE']._serialized_end=110
+  _globals['_STORESSETOPTIONS']._serialized_start=112
+  _globals['_STORESSETOPTIONS']._serialized_end=202
+  _globals['_STORESDELETEOPTIONS']._serialized_start=204
+  _globals['_STORESDELETEOPTIONS']._serialized_end=259
+  _globals['_STORESGETOPTIONS']._serialized_start=261
+  _globals['_STORESGETOPTIONS']._serialized_end=313
+  _globals['_STORESGETRESULT']._serialized_start=315
+  _globals['_STORESGETRESULT']._serialized_end=404
+  _globals['_STORESFINDOPTIONS']._serialized_start=406
+  _globals['_STORESFINDOPTIONS']._serialized_end=472
+  _globals['_STORESFINDRESULT']._serialized_start=474
+  _globals['_STORESFINDRESULT']._serialized_end=586
+  _globals['_HEALTHMESSAGE']._serialized_start=588
+  _globals['_HEALTHMESSAGE']._serialized_end=603
+  _globals['_PREDICTOPTIONS']._serialized_start=606
+  _globals['_PREDICTOPTIONS']._serialized_end=1478
+  _globals['_REPLY']._serialized_start=1480
+  _globals['_REPLY']._serialized_end=1504
+  _globals['_MODELOPTIONS']._serialized_start=1507
+  _globals['_MODELOPTIONS']._serialized_end=2579
+  _globals['_RESULT']._serialized_start=2581
+  _globals['_RESULT']._serialized_end=2623
+  _globals['_EMBEDDINGRESULT']._serialized_start=2625
+  _globals['_EMBEDDINGRESULT']._serialized_end=2662
+  _globals['_TRANSCRIPTREQUEST']._serialized_start=2664
+  _globals['_TRANSCRIPTREQUEST']._serialized_end=2731
+  _globals['_TRANSCRIPTRESULT']._serialized_start=2733
+  _globals['_TRANSCRIPTRESULT']._serialized_end=2811
+  _globals['_TRANSCRIPTSEGMENT']._serialized_start=2813
+  _globals['_TRANSCRIPTSEGMENT']._serialized_end=2902
+  _globals['_GENERATEIMAGEREQUEST']._serialized_start=2905
+  _globals['_GENERATEIMAGEREQUEST']._serialized_end=3120
+  _globals['_TTSREQUEST']._serialized_start=3122
+  _globals['_TTSREQUEST']._serialized_end=3191
+  _globals['_TOKENIZATIONRESPONSE']._serialized_start=3193
+  _globals['_TOKENIZATIONRESPONSE']._serialized_end=3247
+  _globals['_MEMORYUSAGEDATA']._serialized_start=3250
+  _globals['_MEMORYUSAGEDATA']._serialized_end=3392
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_start=3344
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_end=3392
+  _globals['_STATUSRESPONSE']._serialized_start=3395
+  _globals['_STATUSRESPONSE']._serialized_end=3568
+  _globals['_STATUSRESPONSE_STATE']._serialized_start=3501
+  _globals['_STATUSRESPONSE_STATE']._serialized_end=3568
+  _globals['_MESSAGE']._serialized_start=3570
+  _globals['_MESSAGE']._serialized_end=3632
+  _globals['_BACKEND']._serialized_start=3635
+  _globals['_BACKEND']._serialized_end=4526
 # @@protoc_insertion_point(module_scope)
diff --git a/backend/python/bark/backend_pb2_grpc.py b/backend/python/bark/backend_pb2_grpc.py
index 79a7677fb27f..e06fccf3d451 100644
--- a/backend/python/bark/backend_pb2_grpc.py
+++ b/backend/python/bark/backend_pb2_grpc.py
@@ -64,6 +64,26 @@ def __init__(self, channel):
                 request_serializer=backend__pb2.HealthMessage.SerializeToString,
                 response_deserializer=backend__pb2.StatusResponse.FromString,
                 )
+        self.StoresSet = channel.unary_unary(
+                '/backend.Backend/StoresSet',
+                request_serializer=backend__pb2.StoresSetOptions.SerializeToString,
+                response_deserializer=backend__pb2.Result.FromString,
+                )
+        self.StoresDelete = channel.unary_unary(
+                '/backend.Backend/StoresDelete',
+                request_serializer=backend__pb2.StoresDeleteOptions.SerializeToString,
+                response_deserializer=backend__pb2.Result.FromString,
+                )
+        self.StoresGet = channel.unary_unary(
+                '/backend.Backend/StoresGet',
+                request_serializer=backend__pb2.StoresGetOptions.SerializeToString,
+                response_deserializer=backend__pb2.StoresGetResult.FromString,
+                )
+        self.StoresFind = channel.unary_unary(
+                '/backend.Backend/StoresFind',
+                request_serializer=backend__pb2.StoresFindOptions.SerializeToString,
+                response_deserializer=backend__pb2.StoresFindResult.FromString,
+                )
 
 
 class BackendServicer(object):
@@ -129,6 +149,30 @@ def Status(self, request, context):
         context.set_details('Method not implemented!')
         raise NotImplementedError('Method not implemented!')
 
+    def StoresSet(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresDelete(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresGet(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresFind(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
 
 def add_BackendServicer_to_server(servicer, server):
     rpc_method_handlers = {
@@ -182,6 +226,26 @@ def add_BackendServicer_to_server(servicer, server):
                     request_deserializer=backend__pb2.HealthMessage.FromString,
                     response_serializer=backend__pb2.StatusResponse.SerializeToString,
             ),
+            'StoresSet': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresSet,
+                    request_deserializer=backend__pb2.StoresSetOptions.FromString,
+                    response_serializer=backend__pb2.Result.SerializeToString,
+            ),
+            'StoresDelete': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresDelete,
+                    request_deserializer=backend__pb2.StoresDeleteOptions.FromString,
+                    response_serializer=backend__pb2.Result.SerializeToString,
+            ),
+            'StoresGet': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresGet,
+                    request_deserializer=backend__pb2.StoresGetOptions.FromString,
+                    response_serializer=backend__pb2.StoresGetResult.SerializeToString,
+            ),
+            'StoresFind': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresFind,
+                    request_deserializer=backend__pb2.StoresFindOptions.FromString,
+                    response_serializer=backend__pb2.StoresFindResult.SerializeToString,
+            ),
     }
     generic_handler = grpc.method_handlers_generic_handler(
             'backend.Backend', rpc_method_handlers)
@@ -361,3 +425,71 @@ def Status(request,
             backend__pb2.StatusResponse.FromString,
             options, channel_credentials,
             insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresSet(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresSet',
+            backend__pb2.StoresSetOptions.SerializeToString,
+            backend__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresDelete(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresDelete',
+            backend__pb2.StoresDeleteOptions.SerializeToString,
+            backend__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresGet(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresGet',
+            backend__pb2.StoresGetOptions.SerializeToString,
+            backend__pb2.StoresGetResult.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresFind(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresFind',
+            backend__pb2.StoresFindOptions.SerializeToString,
+            backend__pb2.StoresFindResult.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
diff --git a/backend/python/coqui/backend_pb2.py b/backend/python/coqui/backend_pb2.py
index 08b896c7cad5..8d366c16d63b 100644
--- a/backend/python/coqui/backend_pb2.py
+++ b/backend/python/coqui/backend_pb2.py
@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 # Generated by the protocol buffer compiler.  DO NOT EDIT!
 # source: backend.proto
+# Protobuf Python Version: 4.25.1
 """Generated protocol buffer code."""
 from google.protobuf import descriptor as _descriptor
 from google.protobuf import descriptor_pool as _descriptor_pool
@@ -11,51 +12,69 @@
 _sym_db = _symbol_database.Default()
 
 
+from google.protobuf import any_pb2 as google_dot_protobuf_dot_any__pb2
 
 
-DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\rbackend.proto\x12\x07\x62\x61\x63kend\"\x0f\n\rHealthMessage\"\xa6\x06\n\x0ePredictOptions\x12\x0e\n\x06Prompt\x18\x01 \x01(\t\x12\x0c\n\x04Seed\x18\x02 \x01(\x05\x12\x0f\n\x07Threads\x18\x03 \x01(\x05\x12\x0e\n\x06Tokens\x18\x04 \x01(\x05\x12\x0c\n\x04TopK\x18\x05 \x01(\x05\x12\x0e\n\x06Repeat\x18\x06 \x01(\x05\x12\r\n\x05\x42\x61tch\x18\x07 \x01(\x05\x12\r\n\x05NKeep\x18\x08 \x01(\x05\x12\x13\n\x0bTemperature\x18\t \x01(\x02\x12\x0f\n\x07Penalty\x18\n \x01(\x02\x12\r\n\x05\x46\x31\x36KV\x18\x0b \x01(\x08\x12\x11\n\tDebugMode\x18\x0c \x01(\x08\x12\x13\n\x0bStopPrompts\x18\r \x03(\t\x12\x11\n\tIgnoreEOS\x18\x0e \x01(\x08\x12\x19\n\x11TailFreeSamplingZ\x18\x0f \x01(\x02\x12\x10\n\x08TypicalP\x18\x10 \x01(\x02\x12\x18\n\x10\x46requencyPenalty\x18\x11 \x01(\x02\x12\x17\n\x0fPresencePenalty\x18\x12 \x01(\x02\x12\x10\n\x08Mirostat\x18\x13 \x01(\x05\x12\x13\n\x0bMirostatETA\x18\x14 \x01(\x02\x12\x13\n\x0bMirostatTAU\x18\x15 \x01(\x02\x12\x12\n\nPenalizeNL\x18\x16 \x01(\x08\x12\x11\n\tLogitBias\x18\x17 \x01(\t\x12\r\n\x05MLock\x18\x19 \x01(\x08\x12\x0c\n\x04MMap\x18\x1a \x01(\x08\x12\x16\n\x0ePromptCacheAll\x18\x1b \x01(\x08\x12\x15\n\rPromptCacheRO\x18\x1c \x01(\x08\x12\x0f\n\x07Grammar\x18\x1d \x01(\t\x12\x0f\n\x07MainGPU\x18\x1e \x01(\t\x12\x13\n\x0bTensorSplit\x18\x1f \x01(\t\x12\x0c\n\x04TopP\x18  \x01(\x02\x12\x17\n\x0fPromptCachePath\x18! \x01(\t\x12\r\n\x05\x44\x65\x62ug\x18\" \x01(\x08\x12\x17\n\x0f\x45mbeddingTokens\x18# \x03(\x05\x12\x12\n\nEmbeddings\x18$ \x01(\t\x12\x14\n\x0cRopeFreqBase\x18% \x01(\x02\x12\x15\n\rRopeFreqScale\x18& \x01(\x02\x12\x1b\n\x13NegativePromptScale\x18\' \x01(\x02\x12\x16\n\x0eNegativePrompt\x18( \x01(\t\x12\x0e\n\x06NDraft\x18) \x01(\x05\x12\x0e\n\x06Images\x18* \x03(\t\"\x18\n\x05Reply\x12\x0f\n\x07message\x18\x01 \x01(\x0c\"\xb0\x08\n\x0cModelOptions\x12\r\n\x05Model\x18\x01 \x01(\t\x12\x13\n\x0b\x43ontextSize\x18\x02 \x01(\x05\x12\x0c\n\x04Seed\x18\x03 \x01(\x05\x12\x0e\n\x06NBatch\x18\x04 \x01(\x05\x12\x11\n\tF16Memory\x18\x05 \x01(\x08\x12\r\n\x05MLock\x18\x06 \x01(\x08\x12\x0c\n\x04MMap\x18\x07 \x01(\x08\x12\x11\n\tVocabOnly\x18\x08 \x01(\x08\x12\x0f\n\x07LowVRAM\x18\t \x01(\x08\x12\x12\n\nEmbeddings\x18\n \x01(\x08\x12\x0c\n\x04NUMA\x18\x0b \x01(\x08\x12\x12\n\nNGPULayers\x18\x0c \x01(\x05\x12\x0f\n\x07MainGPU\x18\r \x01(\t\x12\x13\n\x0bTensorSplit\x18\x0e \x01(\t\x12\x0f\n\x07Threads\x18\x0f \x01(\x05\x12\x19\n\x11LibrarySearchPath\x18\x10 \x01(\t\x12\x14\n\x0cRopeFreqBase\x18\x11 \x01(\x02\x12\x15\n\rRopeFreqScale\x18\x12 \x01(\x02\x12\x12\n\nRMSNormEps\x18\x13 \x01(\x02\x12\x0c\n\x04NGQA\x18\x14 \x01(\x05\x12\x11\n\tModelFile\x18\x15 \x01(\t\x12\x0e\n\x06\x44\x65vice\x18\x16 \x01(\t\x12\x11\n\tUseTriton\x18\x17 \x01(\x08\x12\x15\n\rModelBaseName\x18\x18 \x01(\t\x12\x18\n\x10UseFastTokenizer\x18\x19 \x01(\x08\x12\x14\n\x0cPipelineType\x18\x1a \x01(\t\x12\x15\n\rSchedulerType\x18\x1b \x01(\t\x12\x0c\n\x04\x43UDA\x18\x1c \x01(\x08\x12\x10\n\x08\x43\x46GScale\x18\x1d \x01(\x02\x12\x0f\n\x07IMG2IMG\x18\x1e \x01(\x08\x12\x11\n\tCLIPModel\x18\x1f \x01(\t\x12\x15\n\rCLIPSubfolder\x18  \x01(\t\x12\x10\n\x08\x43LIPSkip\x18! \x01(\x05\x12\x12\n\nControlNet\x18\x30 \x01(\t\x12\x11\n\tTokenizer\x18\" \x01(\t\x12\x10\n\x08LoraBase\x18# \x01(\t\x12\x13\n\x0bLoraAdapter\x18$ \x01(\t\x12\x11\n\tLoraScale\x18* \x01(\x02\x12\x11\n\tNoMulMatQ\x18% \x01(\x08\x12\x12\n\nDraftModel\x18\' \x01(\t\x12\x11\n\tAudioPath\x18& \x01(\t\x12\x14\n\x0cQuantization\x18( \x01(\t\x12\x1c\n\x14GPUMemoryUtilization\x18\x32 \x01(\x02\x12\x17\n\x0fTrustRemoteCode\x18\x33 \x01(\x08\x12\x14\n\x0c\x45nforceEager\x18\x34 \x01(\x08\x12\x11\n\tSwapSpace\x18\x35 \x01(\x05\x12\x13\n\x0bMaxModelLen\x18\x36 \x01(\x05\x12\x0e\n\x06MMProj\x18) \x01(\t\x12\x13\n\x0bRopeScaling\x18+ \x01(\t\x12\x15\n\rYarnExtFactor\x18, \x01(\x02\x12\x16\n\x0eYarnAttnFactor\x18- \x01(\x02\x12\x14\n\x0cYarnBetaFast\x18. \x01(\x02\x12\x14\n\x0cYarnBetaSlow\x18/ \x01(\x02\x12\x0c\n\x04Type\x18\x31 \x01(\t\"*\n\x06Result\x12\x0f\n\x07message\x18\x01 \x01(\t\x12\x0f\n\x07success\x18\x02 \x01(\x08\"%\n\x0f\x45mbeddingResult\x12\x12\n\nembeddings\x18\x01 \x03(\x02\"C\n\x11TranscriptRequest\x12\x0b\n\x03\x64st\x18\x02 \x01(\t\x12\x10\n\x08language\x18\x03 \x01(\t\x12\x0f\n\x07threads\x18\x04 \x01(\r\"N\n\x10TranscriptResult\x12,\n\x08segments\x18\x01 \x03(\x0b\x32\x1a.backend.TranscriptSegment\x12\x0c\n\x04text\x18\x02 \x01(\t\"Y\n\x11TranscriptSegment\x12\n\n\x02id\x18\x01 \x01(\x05\x12\r\n\x05start\x18\x02 \x01(\x03\x12\x0b\n\x03\x65nd\x18\x03 \x01(\x03\x12\x0c\n\x04text\x18\x04 \x01(\t\x12\x0e\n\x06tokens\x18\x05 \x03(\x05\"\xd7\x01\n\x14GenerateImageRequest\x12\x0e\n\x06height\x18\x01 \x01(\x05\x12\r\n\x05width\x18\x02 \x01(\x05\x12\x0c\n\x04mode\x18\x03 \x01(\x05\x12\x0c\n\x04step\x18\x04 \x01(\x05\x12\x0c\n\x04seed\x18\x05 \x01(\x05\x12\x17\n\x0fpositive_prompt\x18\x06 \x01(\t\x12\x17\n\x0fnegative_prompt\x18\x07 \x01(\t\x12\x0b\n\x03\x64st\x18\x08 \x01(\t\x12\x0b\n\x03src\x18\t \x01(\t\x12\x18\n\x10\x45nableParameters\x18\n \x01(\t\x12\x10\n\x08\x43LIPSkip\x18\x0b \x01(\x05\"E\n\nTTSRequest\x12\x0c\n\x04text\x18\x01 \x01(\t\x12\r\n\x05model\x18\x02 \x01(\t\x12\x0b\n\x03\x64st\x18\x03 \x01(\t\x12\r\n\x05voice\x18\x04 \x01(\t\"6\n\x14TokenizationResponse\x12\x0e\n\x06length\x18\x01 \x01(\x05\x12\x0e\n\x06tokens\x18\x02 \x03(\x05\"\x8e\x01\n\x0fMemoryUsageData\x12\r\n\x05total\x18\x01 \x01(\x04\x12:\n\tbreakdown\x18\x02 \x03(\x0b\x32\'.backend.MemoryUsageData.BreakdownEntry\x1a\x30\n\x0e\x42reakdownEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\x04:\x02\x38\x01\"\xad\x01\n\x0eStatusResponse\x12,\n\x05state\x18\x01 \x01(\x0e\x32\x1d.backend.StatusResponse.State\x12(\n\x06memory\x18\x02 \x01(\x0b\x32\x18.backend.MemoryUsageData\"C\n\x05State\x12\x11\n\rUNINITIALIZED\x10\x00\x12\x08\n\x04\x42USY\x10\x01\x12\t\n\x05READY\x10\x02\x12\x12\n\x05\x45RROR\x10\xff\xff\xff\xff\xff\xff\xff\xff\xff\x01\x32\xf4\x04\n\x07\x42\x61\x63kend\x12\x32\n\x06Health\x12\x16.backend.HealthMessage\x1a\x0e.backend.Reply\"\x00\x12\x34\n\x07Predict\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x12\x35\n\tLoadModel\x12\x15.backend.ModelOptions\x1a\x0f.backend.Result\"\x00\x12<\n\rPredictStream\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x30\x01\x12@\n\tEmbedding\x12\x17.backend.PredictOptions\x1a\x18.backend.EmbeddingResult\"\x00\x12\x41\n\rGenerateImage\x12\x1d.backend.GenerateImageRequest\x1a\x0f.backend.Result\"\x00\x12M\n\x12\x41udioTranscription\x12\x1a.backend.TranscriptRequest\x1a\x19.backend.TranscriptResult\"\x00\x12-\n\x03TTS\x12\x13.backend.TTSRequest\x1a\x0f.backend.Result\"\x00\x12J\n\x0eTokenizeString\x12\x17.backend.PredictOptions\x1a\x1d.backend.TokenizationResponse\"\x00\x12;\n\x06Status\x12\x16.backend.HealthMessage\x1a\x17.backend.StatusResponse\"\x00\x42Z\n\x19io.skynet.localai.backendB\x0eLocalAIBackendP\x01Z+github.com/go-skynet/LocalAI/pkg/grpc/protob\x06proto3')
+DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\rbackend.proto\x12\x07\x62\x61\x63kend\x1a\x19google/protobuf/any.proto\"\x1b\n\tStoresKey\x12\x0e\n\x06\x46loats\x18\x01 \x03(\x02\"\x1c\n\x0bStoresValue\x12\r\n\x05\x42ytes\x18\x01 \x01(\x0c\"Z\n\x10StoresSetOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\"7\n\x13StoresDeleteOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\"4\n\x10StoresGetOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\"Y\n\x0fStoresGetResult\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\"B\n\x11StoresFindOptions\x12\x1f\n\x03Key\x18\x01 \x01(\x0b\x32\x12.backend.StoresKey\x12\x0c\n\x04TopK\x18\x02 \x01(\x05\"p\n\x10StoresFindResult\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\x12\x14\n\x0cSimilarities\x18\x03 \x03(\x02\"\x0f\n\rHealthMessage\"\xe8\x06\n\x0ePredictOptions\x12\x0e\n\x06Prompt\x18\x01 \x01(\t\x12\x0c\n\x04Seed\x18\x02 \x01(\x05\x12\x0f\n\x07Threads\x18\x03 \x01(\x05\x12\x0e\n\x06Tokens\x18\x04 \x01(\x05\x12\x0c\n\x04TopK\x18\x05 \x01(\x05\x12\x0e\n\x06Repeat\x18\x06 \x01(\x05\x12\r\n\x05\x42\x61tch\x18\x07 \x01(\x05\x12\r\n\x05NKeep\x18\x08 \x01(\x05\x12\x13\n\x0bTemperature\x18\t \x01(\x02\x12\x0f\n\x07Penalty\x18\n \x01(\x02\x12\r\n\x05\x46\x31\x36KV\x18\x0b \x01(\x08\x12\x11\n\tDebugMode\x18\x0c \x01(\x08\x12\x13\n\x0bStopPrompts\x18\r \x03(\t\x12\x11\n\tIgnoreEOS\x18\x0e \x01(\x08\x12\x19\n\x11TailFreeSamplingZ\x18\x0f \x01(\x02\x12\x10\n\x08TypicalP\x18\x10 \x01(\x02\x12\x18\n\x10\x46requencyPenalty\x18\x11 \x01(\x02\x12\x17\n\x0fPresencePenalty\x18\x12 \x01(\x02\x12\x10\n\x08Mirostat\x18\x13 \x01(\x05\x12\x13\n\x0bMirostatETA\x18\x14 \x01(\x02\x12\x13\n\x0bMirostatTAU\x18\x15 \x01(\x02\x12\x12\n\nPenalizeNL\x18\x16 \x01(\x08\x12\x11\n\tLogitBias\x18\x17 \x01(\t\x12\r\n\x05MLock\x18\x19 \x01(\x08\x12\x0c\n\x04MMap\x18\x1a \x01(\x08\x12\x16\n\x0ePromptCacheAll\x18\x1b \x01(\x08\x12\x15\n\rPromptCacheRO\x18\x1c \x01(\x08\x12\x0f\n\x07Grammar\x18\x1d \x01(\t\x12\x0f\n\x07MainGPU\x18\x1e \x01(\t\x12\x13\n\x0bTensorSplit\x18\x1f \x01(\t\x12\x0c\n\x04TopP\x18  \x01(\x02\x12\x17\n\x0fPromptCachePath\x18! \x01(\t\x12\r\n\x05\x44\x65\x62ug\x18\" \x01(\x08\x12\x17\n\x0f\x45mbeddingTokens\x18# \x03(\x05\x12\x12\n\nEmbeddings\x18$ \x01(\t\x12\x14\n\x0cRopeFreqBase\x18% \x01(\x02\x12\x15\n\rRopeFreqScale\x18& \x01(\x02\x12\x1b\n\x13NegativePromptScale\x18\' \x01(\x02\x12\x16\n\x0eNegativePrompt\x18( \x01(\t\x12\x0e\n\x06NDraft\x18) \x01(\x05\x12\x0e\n\x06Images\x18* \x03(\t\x12\x1c\n\x14UseTokenizerTemplate\x18+ \x01(\x08\x12\"\n\x08Messages\x18, \x03(\x0b\x32\x10.backend.Message\"\x18\n\x05Reply\x12\x0f\n\x07message\x18\x01 \x01(\x0c\"\xb0\x08\n\x0cModelOptions\x12\r\n\x05Model\x18\x01 \x01(\t\x12\x13\n\x0b\x43ontextSize\x18\x02 \x01(\x05\x12\x0c\n\x04Seed\x18\x03 \x01(\x05\x12\x0e\n\x06NBatch\x18\x04 \x01(\x05\x12\x11\n\tF16Memory\x18\x05 \x01(\x08\x12\r\n\x05MLock\x18\x06 \x01(\x08\x12\x0c\n\x04MMap\x18\x07 \x01(\x08\x12\x11\n\tVocabOnly\x18\x08 \x01(\x08\x12\x0f\n\x07LowVRAM\x18\t \x01(\x08\x12\x12\n\nEmbeddings\x18\n \x01(\x08\x12\x0c\n\x04NUMA\x18\x0b \x01(\x08\x12\x12\n\nNGPULayers\x18\x0c \x01(\x05\x12\x0f\n\x07MainGPU\x18\r \x01(\t\x12\x13\n\x0bTensorSplit\x18\x0e \x01(\t\x12\x0f\n\x07Threads\x18\x0f \x01(\x05\x12\x19\n\x11LibrarySearchPath\x18\x10 \x01(\t\x12\x14\n\x0cRopeFreqBase\x18\x11 \x01(\x02\x12\x15\n\rRopeFreqScale\x18\x12 \x01(\x02\x12\x12\n\nRMSNormEps\x18\x13 \x01(\x02\x12\x0c\n\x04NGQA\x18\x14 \x01(\x05\x12\x11\n\tModelFile\x18\x15 \x01(\t\x12\x0e\n\x06\x44\x65vice\x18\x16 \x01(\t\x12\x11\n\tUseTriton\x18\x17 \x01(\x08\x12\x15\n\rModelBaseName\x18\x18 \x01(\t\x12\x18\n\x10UseFastTokenizer\x18\x19 \x01(\x08\x12\x14\n\x0cPipelineType\x18\x1a \x01(\t\x12\x15\n\rSchedulerType\x18\x1b \x01(\t\x12\x0c\n\x04\x43UDA\x18\x1c \x01(\x08\x12\x10\n\x08\x43\x46GScale\x18\x1d \x01(\x02\x12\x0f\n\x07IMG2IMG\x18\x1e \x01(\x08\x12\x11\n\tCLIPModel\x18\x1f \x01(\t\x12\x15\n\rCLIPSubfolder\x18  \x01(\t\x12\x10\n\x08\x43LIPSkip\x18! \x01(\x05\x12\x12\n\nControlNet\x18\x30 \x01(\t\x12\x11\n\tTokenizer\x18\" \x01(\t\x12\x10\n\x08LoraBase\x18# \x01(\t\x12\x13\n\x0bLoraAdapter\x18$ \x01(\t\x12\x11\n\tLoraScale\x18* \x01(\x02\x12\x11\n\tNoMulMatQ\x18% \x01(\x08\x12\x12\n\nDraftModel\x18\' \x01(\t\x12\x11\n\tAudioPath\x18& \x01(\t\x12\x14\n\x0cQuantization\x18( \x01(\t\x12\x1c\n\x14GPUMemoryUtilization\x18\x32 \x01(\x02\x12\x17\n\x0fTrustRemoteCode\x18\x33 \x01(\x08\x12\x14\n\x0c\x45nforceEager\x18\x34 \x01(\x08\x12\x11\n\tSwapSpace\x18\x35 \x01(\x05\x12\x13\n\x0bMaxModelLen\x18\x36 \x01(\x05\x12\x0e\n\x06MMProj\x18) \x01(\t\x12\x13\n\x0bRopeScaling\x18+ \x01(\t\x12\x15\n\rYarnExtFactor\x18, \x01(\x02\x12\x16\n\x0eYarnAttnFactor\x18- \x01(\x02\x12\x14\n\x0cYarnBetaFast\x18. \x01(\x02\x12\x14\n\x0cYarnBetaSlow\x18/ \x01(\x02\x12\x0c\n\x04Type\x18\x31 \x01(\t\"*\n\x06Result\x12\x0f\n\x07message\x18\x01 \x01(\t\x12\x0f\n\x07success\x18\x02 \x01(\x08\"%\n\x0f\x45mbeddingResult\x12\x12\n\nembeddings\x18\x01 \x03(\x02\"C\n\x11TranscriptRequest\x12\x0b\n\x03\x64st\x18\x02 \x01(\t\x12\x10\n\x08language\x18\x03 \x01(\t\x12\x0f\n\x07threads\x18\x04 \x01(\r\"N\n\x10TranscriptResult\x12,\n\x08segments\x18\x01 \x03(\x0b\x32\x1a.backend.TranscriptSegment\x12\x0c\n\x04text\x18\x02 \x01(\t\"Y\n\x11TranscriptSegment\x12\n\n\x02id\x18\x01 \x01(\x05\x12\r\n\x05start\x18\x02 \x01(\x03\x12\x0b\n\x03\x65nd\x18\x03 \x01(\x03\x12\x0c\n\x04text\x18\x04 \x01(\t\x12\x0e\n\x06tokens\x18\x05 \x03(\x05\"\xd7\x01\n\x14GenerateImageRequest\x12\x0e\n\x06height\x18\x01 \x01(\x05\x12\r\n\x05width\x18\x02 \x01(\x05\x12\x0c\n\x04mode\x18\x03 \x01(\x05\x12\x0c\n\x04step\x18\x04 \x01(\x05\x12\x0c\n\x04seed\x18\x05 \x01(\x05\x12\x17\n\x0fpositive_prompt\x18\x06 \x01(\t\x12\x17\n\x0fnegative_prompt\x18\x07 \x01(\t\x12\x0b\n\x03\x64st\x18\x08 \x01(\t\x12\x0b\n\x03src\x18\t \x01(\t\x12\x18\n\x10\x45nableParameters\x18\n \x01(\t\x12\x10\n\x08\x43LIPSkip\x18\x0b \x01(\x05\"E\n\nTTSRequest\x12\x0c\n\x04text\x18\x01 \x01(\t\x12\r\n\x05model\x18\x02 \x01(\t\x12\x0b\n\x03\x64st\x18\x03 \x01(\t\x12\r\n\x05voice\x18\x04 \x01(\t\"6\n\x14TokenizationResponse\x12\x0e\n\x06length\x18\x01 \x01(\x05\x12\x0e\n\x06tokens\x18\x02 \x03(\x05\"\x8e\x01\n\x0fMemoryUsageData\x12\r\n\x05total\x18\x01 \x01(\x04\x12:\n\tbreakdown\x18\x02 \x03(\x0b\x32\'.backend.MemoryUsageData.BreakdownEntry\x1a\x30\n\x0e\x42reakdownEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\x04:\x02\x38\x01\"\xad\x01\n\x0eStatusResponse\x12,\n\x05state\x18\x01 \x01(\x0e\x32\x1d.backend.StatusResponse.State\x12(\n\x06memory\x18\x02 \x01(\x0b\x32\x18.backend.MemoryUsageData\"C\n\x05State\x12\x11\n\rUNINITIALIZED\x10\x00\x12\x08\n\x04\x42USY\x10\x01\x12\t\n\x05READY\x10\x02\x12\x12\n\x05\x45RROR\x10\xff\xff\xff\xff\xff\xff\xff\xff\xff\x01\">\n\x07Message\x12\x0c\n\x04Role\x18\x01 \x01(\t\x12%\n\x07\x43ontent\x18\x02 \x01(\x0b\x32\x14.google.protobuf.Any2\xfb\x06\n\x07\x42\x61\x63kend\x12\x32\n\x06Health\x12\x16.backend.HealthMessage\x1a\x0e.backend.Reply\"\x00\x12\x34\n\x07Predict\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x12\x35\n\tLoadModel\x12\x15.backend.ModelOptions\x1a\x0f.backend.Result\"\x00\x12<\n\rPredictStream\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x30\x01\x12@\n\tEmbedding\x12\x17.backend.PredictOptions\x1a\x18.backend.EmbeddingResult\"\x00\x12\x41\n\rGenerateImage\x12\x1d.backend.GenerateImageRequest\x1a\x0f.backend.Result\"\x00\x12M\n\x12\x41udioTranscription\x12\x1a.backend.TranscriptRequest\x1a\x19.backend.TranscriptResult\"\x00\x12-\n\x03TTS\x12\x13.backend.TTSRequest\x1a\x0f.backend.Result\"\x00\x12J\n\x0eTokenizeString\x12\x17.backend.PredictOptions\x1a\x1d.backend.TokenizationResponse\"\x00\x12;\n\x06Status\x12\x16.backend.HealthMessage\x1a\x17.backend.StatusResponse\"\x00\x12\x39\n\tStoresSet\x12\x19.backend.StoresSetOptions\x1a\x0f.backend.Result\"\x00\x12?\n\x0cStoresDelete\x12\x1c.backend.StoresDeleteOptions\x1a\x0f.backend.Result\"\x00\x12\x42\n\tStoresGet\x12\x19.backend.StoresGetOptions\x1a\x18.backend.StoresGetResult\"\x00\x12\x45\n\nStoresFind\x12\x1a.backend.StoresFindOptions\x1a\x19.backend.StoresFindResult\"\x00\x42Z\n\x19io.skynet.localai.backendB\x0eLocalAIBackendP\x01Z+github.com/go-skynet/LocalAI/pkg/grpc/protob\x06proto3')
 
 _globals = globals()
 _builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, _globals)
 _builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, 'backend_pb2', _globals)
 if _descriptor._USE_C_DESCRIPTORS == False:
-
-  DESCRIPTOR._options = None
-  DESCRIPTOR._serialized_options = b'\n\031io.skynet.localai.backendB\016LocalAIBackendP\001Z+github.com/go-skynet/LocalAI/pkg/grpc/proto'
-  _MEMORYUSAGEDATA_BREAKDOWNENTRY._options = None
-  _MEMORYUSAGEDATA_BREAKDOWNENTRY._serialized_options = b'8\001'
-  _globals['_HEALTHMESSAGE']._serialized_start=26
-  _globals['_HEALTHMESSAGE']._serialized_end=41
-  _globals['_PREDICTOPTIONS']._serialized_start=44
-  _globals['_PREDICTOPTIONS']._serialized_end=850
-  _globals['_REPLY']._serialized_start=852
-  _globals['_REPLY']._serialized_end=876
-  _globals['_MODELOPTIONS']._serialized_start=879
-  _globals['_MODELOPTIONS']._serialized_end=1951
-  _globals['_RESULT']._serialized_start=1953
-  _globals['_RESULT']._serialized_end=1995
-  _globals['_EMBEDDINGRESULT']._serialized_start=1997
-  _globals['_EMBEDDINGRESULT']._serialized_end=2034
-  _globals['_TRANSCRIPTREQUEST']._serialized_start=2036
-  _globals['_TRANSCRIPTREQUEST']._serialized_end=2103
-  _globals['_TRANSCRIPTRESULT']._serialized_start=2105
-  _globals['_TRANSCRIPTRESULT']._serialized_end=2183
-  _globals['_TRANSCRIPTSEGMENT']._serialized_start=2185
-  _globals['_TRANSCRIPTSEGMENT']._serialized_end=2274
-  _globals['_GENERATEIMAGEREQUEST']._serialized_start=2277
-  _globals['_GENERATEIMAGEREQUEST']._serialized_end=2492
-  _globals['_TTSREQUEST']._serialized_start=2494
-  _globals['_TTSREQUEST']._serialized_end=2563
-  _globals['_TOKENIZATIONRESPONSE']._serialized_start=2565
-  _globals['_TOKENIZATIONRESPONSE']._serialized_end=2619
-  _globals['_MEMORYUSAGEDATA']._serialized_start=2622
-  _globals['_MEMORYUSAGEDATA']._serialized_end=2764
-  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_start=2716
-  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_end=2764
-  _globals['_STATUSRESPONSE']._serialized_start=2767
-  _globals['_STATUSRESPONSE']._serialized_end=2940
-  _globals['_STATUSRESPONSE_STATE']._serialized_start=2873
-  _globals['_STATUSRESPONSE_STATE']._serialized_end=2940
-  _globals['_BACKEND']._serialized_start=2943
-  _globals['_BACKEND']._serialized_end=3571
+  _globals['DESCRIPTOR']._options = None
+  _globals['DESCRIPTOR']._serialized_options = b'\n\031io.skynet.localai.backendB\016LocalAIBackendP\001Z+github.com/go-skynet/LocalAI/pkg/grpc/proto'
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._options = None
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_options = b'8\001'
+  _globals['_STORESKEY']._serialized_start=53
+  _globals['_STORESKEY']._serialized_end=80
+  _globals['_STORESVALUE']._serialized_start=82
+  _globals['_STORESVALUE']._serialized_end=110
+  _globals['_STORESSETOPTIONS']._serialized_start=112
+  _globals['_STORESSETOPTIONS']._serialized_end=202
+  _globals['_STORESDELETEOPTIONS']._serialized_start=204
+  _globals['_STORESDELETEOPTIONS']._serialized_end=259
+  _globals['_STORESGETOPTIONS']._serialized_start=261
+  _globals['_STORESGETOPTIONS']._serialized_end=313
+  _globals['_STORESGETRESULT']._serialized_start=315
+  _globals['_STORESGETRESULT']._serialized_end=404
+  _globals['_STORESFINDOPTIONS']._serialized_start=406
+  _globals['_STORESFINDOPTIONS']._serialized_end=472
+  _globals['_STORESFINDRESULT']._serialized_start=474
+  _globals['_STORESFINDRESULT']._serialized_end=586
+  _globals['_HEALTHMESSAGE']._serialized_start=588
+  _globals['_HEALTHMESSAGE']._serialized_end=603
+  _globals['_PREDICTOPTIONS']._serialized_start=606
+  _globals['_PREDICTOPTIONS']._serialized_end=1478
+  _globals['_REPLY']._serialized_start=1480
+  _globals['_REPLY']._serialized_end=1504
+  _globals['_MODELOPTIONS']._serialized_start=1507
+  _globals['_MODELOPTIONS']._serialized_end=2579
+  _globals['_RESULT']._serialized_start=2581
+  _globals['_RESULT']._serialized_end=2623
+  _globals['_EMBEDDINGRESULT']._serialized_start=2625
+  _globals['_EMBEDDINGRESULT']._serialized_end=2662
+  _globals['_TRANSCRIPTREQUEST']._serialized_start=2664
+  _globals['_TRANSCRIPTREQUEST']._serialized_end=2731
+  _globals['_TRANSCRIPTRESULT']._serialized_start=2733
+  _globals['_TRANSCRIPTRESULT']._serialized_end=2811
+  _globals['_TRANSCRIPTSEGMENT']._serialized_start=2813
+  _globals['_TRANSCRIPTSEGMENT']._serialized_end=2902
+  _globals['_GENERATEIMAGEREQUEST']._serialized_start=2905
+  _globals['_GENERATEIMAGEREQUEST']._serialized_end=3120
+  _globals['_TTSREQUEST']._serialized_start=3122
+  _globals['_TTSREQUEST']._serialized_end=3191
+  _globals['_TOKENIZATIONRESPONSE']._serialized_start=3193
+  _globals['_TOKENIZATIONRESPONSE']._serialized_end=3247
+  _globals['_MEMORYUSAGEDATA']._serialized_start=3250
+  _globals['_MEMORYUSAGEDATA']._serialized_end=3392
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_start=3344
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_end=3392
+  _globals['_STATUSRESPONSE']._serialized_start=3395
+  _globals['_STATUSRESPONSE']._serialized_end=3568
+  _globals['_STATUSRESPONSE_STATE']._serialized_start=3501
+  _globals['_STATUSRESPONSE_STATE']._serialized_end=3568
+  _globals['_MESSAGE']._serialized_start=3570
+  _globals['_MESSAGE']._serialized_end=3632
+  _globals['_BACKEND']._serialized_start=3635
+  _globals['_BACKEND']._serialized_end=4526
 # @@protoc_insertion_point(module_scope)
diff --git a/backend/python/coqui/backend_pb2_grpc.py b/backend/python/coqui/backend_pb2_grpc.py
index 79a7677fb27f..e06fccf3d451 100644
--- a/backend/python/coqui/backend_pb2_grpc.py
+++ b/backend/python/coqui/backend_pb2_grpc.py
@@ -64,6 +64,26 @@ def __init__(self, channel):
                 request_serializer=backend__pb2.HealthMessage.SerializeToString,
                 response_deserializer=backend__pb2.StatusResponse.FromString,
                 )
+        self.StoresSet = channel.unary_unary(
+                '/backend.Backend/StoresSet',
+                request_serializer=backend__pb2.StoresSetOptions.SerializeToString,
+                response_deserializer=backend__pb2.Result.FromString,
+                )
+        self.StoresDelete = channel.unary_unary(
+                '/backend.Backend/StoresDelete',
+                request_serializer=backend__pb2.StoresDeleteOptions.SerializeToString,
+                response_deserializer=backend__pb2.Result.FromString,
+                )
+        self.StoresGet = channel.unary_unary(
+                '/backend.Backend/StoresGet',
+                request_serializer=backend__pb2.StoresGetOptions.SerializeToString,
+                response_deserializer=backend__pb2.StoresGetResult.FromString,
+                )
+        self.StoresFind = channel.unary_unary(
+                '/backend.Backend/StoresFind',
+                request_serializer=backend__pb2.StoresFindOptions.SerializeToString,
+                response_deserializer=backend__pb2.StoresFindResult.FromString,
+                )
 
 
 class BackendServicer(object):
@@ -129,6 +149,30 @@ def Status(self, request, context):
         context.set_details('Method not implemented!')
         raise NotImplementedError('Method not implemented!')
 
+    def StoresSet(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresDelete(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresGet(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresFind(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
 
 def add_BackendServicer_to_server(servicer, server):
     rpc_method_handlers = {
@@ -182,6 +226,26 @@ def add_BackendServicer_to_server(servicer, server):
                     request_deserializer=backend__pb2.HealthMessage.FromString,
                     response_serializer=backend__pb2.StatusResponse.SerializeToString,
             ),
+            'StoresSet': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresSet,
+                    request_deserializer=backend__pb2.StoresSetOptions.FromString,
+                    response_serializer=backend__pb2.Result.SerializeToString,
+            ),
+            'StoresDelete': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresDelete,
+                    request_deserializer=backend__pb2.StoresDeleteOptions.FromString,
+                    response_serializer=backend__pb2.Result.SerializeToString,
+            ),
+            'StoresGet': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresGet,
+                    request_deserializer=backend__pb2.StoresGetOptions.FromString,
+                    response_serializer=backend__pb2.StoresGetResult.SerializeToString,
+            ),
+            'StoresFind': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresFind,
+                    request_deserializer=backend__pb2.StoresFindOptions.FromString,
+                    response_serializer=backend__pb2.StoresFindResult.SerializeToString,
+            ),
     }
     generic_handler = grpc.method_handlers_generic_handler(
             'backend.Backend', rpc_method_handlers)
@@ -361,3 +425,71 @@ def Status(request,
             backend__pb2.StatusResponse.FromString,
             options, channel_credentials,
             insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresSet(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresSet',
+            backend__pb2.StoresSetOptions.SerializeToString,
+            backend__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresDelete(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresDelete',
+            backend__pb2.StoresDeleteOptions.SerializeToString,
+            backend__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresGet(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresGet',
+            backend__pb2.StoresGetOptions.SerializeToString,
+            backend__pb2.StoresGetResult.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresFind(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresFind',
+            backend__pb2.StoresFindOptions.SerializeToString,
+            backend__pb2.StoresFindResult.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
diff --git a/backend/python/diffusers/backend_pb2.py b/backend/python/diffusers/backend_pb2.py
index 08b896c7cad5..8d366c16d63b 100644
--- a/backend/python/diffusers/backend_pb2.py
+++ b/backend/python/diffusers/backend_pb2.py
@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 # Generated by the protocol buffer compiler.  DO NOT EDIT!
 # source: backend.proto
+# Protobuf Python Version: 4.25.1
 """Generated protocol buffer code."""
 from google.protobuf import descriptor as _descriptor
 from google.protobuf import descriptor_pool as _descriptor_pool
@@ -11,51 +12,69 @@
 _sym_db = _symbol_database.Default()
 
 
+from google.protobuf import any_pb2 as google_dot_protobuf_dot_any__pb2
 
 
-DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\rbackend.proto\x12\x07\x62\x61\x63kend\"\x0f\n\rHealthMessage\"\xa6\x06\n\x0ePredictOptions\x12\x0e\n\x06Prompt\x18\x01 \x01(\t\x12\x0c\n\x04Seed\x18\x02 \x01(\x05\x12\x0f\n\x07Threads\x18\x03 \x01(\x05\x12\x0e\n\x06Tokens\x18\x04 \x01(\x05\x12\x0c\n\x04TopK\x18\x05 \x01(\x05\x12\x0e\n\x06Repeat\x18\x06 \x01(\x05\x12\r\n\x05\x42\x61tch\x18\x07 \x01(\x05\x12\r\n\x05NKeep\x18\x08 \x01(\x05\x12\x13\n\x0bTemperature\x18\t \x01(\x02\x12\x0f\n\x07Penalty\x18\n \x01(\x02\x12\r\n\x05\x46\x31\x36KV\x18\x0b \x01(\x08\x12\x11\n\tDebugMode\x18\x0c \x01(\x08\x12\x13\n\x0bStopPrompts\x18\r \x03(\t\x12\x11\n\tIgnoreEOS\x18\x0e \x01(\x08\x12\x19\n\x11TailFreeSamplingZ\x18\x0f \x01(\x02\x12\x10\n\x08TypicalP\x18\x10 \x01(\x02\x12\x18\n\x10\x46requencyPenalty\x18\x11 \x01(\x02\x12\x17\n\x0fPresencePenalty\x18\x12 \x01(\x02\x12\x10\n\x08Mirostat\x18\x13 \x01(\x05\x12\x13\n\x0bMirostatETA\x18\x14 \x01(\x02\x12\x13\n\x0bMirostatTAU\x18\x15 \x01(\x02\x12\x12\n\nPenalizeNL\x18\x16 \x01(\x08\x12\x11\n\tLogitBias\x18\x17 \x01(\t\x12\r\n\x05MLock\x18\x19 \x01(\x08\x12\x0c\n\x04MMap\x18\x1a \x01(\x08\x12\x16\n\x0ePromptCacheAll\x18\x1b \x01(\x08\x12\x15\n\rPromptCacheRO\x18\x1c \x01(\x08\x12\x0f\n\x07Grammar\x18\x1d \x01(\t\x12\x0f\n\x07MainGPU\x18\x1e \x01(\t\x12\x13\n\x0bTensorSplit\x18\x1f \x01(\t\x12\x0c\n\x04TopP\x18  \x01(\x02\x12\x17\n\x0fPromptCachePath\x18! \x01(\t\x12\r\n\x05\x44\x65\x62ug\x18\" \x01(\x08\x12\x17\n\x0f\x45mbeddingTokens\x18# \x03(\x05\x12\x12\n\nEmbeddings\x18$ \x01(\t\x12\x14\n\x0cRopeFreqBase\x18% \x01(\x02\x12\x15\n\rRopeFreqScale\x18& \x01(\x02\x12\x1b\n\x13NegativePromptScale\x18\' \x01(\x02\x12\x16\n\x0eNegativePrompt\x18( \x01(\t\x12\x0e\n\x06NDraft\x18) \x01(\x05\x12\x0e\n\x06Images\x18* \x03(\t\"\x18\n\x05Reply\x12\x0f\n\x07message\x18\x01 \x01(\x0c\"\xb0\x08\n\x0cModelOptions\x12\r\n\x05Model\x18\x01 \x01(\t\x12\x13\n\x0b\x43ontextSize\x18\x02 \x01(\x05\x12\x0c\n\x04Seed\x18\x03 \x01(\x05\x12\x0e\n\x06NBatch\x18\x04 \x01(\x05\x12\x11\n\tF16Memory\x18\x05 \x01(\x08\x12\r\n\x05MLock\x18\x06 \x01(\x08\x12\x0c\n\x04MMap\x18\x07 \x01(\x08\x12\x11\n\tVocabOnly\x18\x08 \x01(\x08\x12\x0f\n\x07LowVRAM\x18\t \x01(\x08\x12\x12\n\nEmbeddings\x18\n \x01(\x08\x12\x0c\n\x04NUMA\x18\x0b \x01(\x08\x12\x12\n\nNGPULayers\x18\x0c \x01(\x05\x12\x0f\n\x07MainGPU\x18\r \x01(\t\x12\x13\n\x0bTensorSplit\x18\x0e \x01(\t\x12\x0f\n\x07Threads\x18\x0f \x01(\x05\x12\x19\n\x11LibrarySearchPath\x18\x10 \x01(\t\x12\x14\n\x0cRopeFreqBase\x18\x11 \x01(\x02\x12\x15\n\rRopeFreqScale\x18\x12 \x01(\x02\x12\x12\n\nRMSNormEps\x18\x13 \x01(\x02\x12\x0c\n\x04NGQA\x18\x14 \x01(\x05\x12\x11\n\tModelFile\x18\x15 \x01(\t\x12\x0e\n\x06\x44\x65vice\x18\x16 \x01(\t\x12\x11\n\tUseTriton\x18\x17 \x01(\x08\x12\x15\n\rModelBaseName\x18\x18 \x01(\t\x12\x18\n\x10UseFastTokenizer\x18\x19 \x01(\x08\x12\x14\n\x0cPipelineType\x18\x1a \x01(\t\x12\x15\n\rSchedulerType\x18\x1b \x01(\t\x12\x0c\n\x04\x43UDA\x18\x1c \x01(\x08\x12\x10\n\x08\x43\x46GScale\x18\x1d \x01(\x02\x12\x0f\n\x07IMG2IMG\x18\x1e \x01(\x08\x12\x11\n\tCLIPModel\x18\x1f \x01(\t\x12\x15\n\rCLIPSubfolder\x18  \x01(\t\x12\x10\n\x08\x43LIPSkip\x18! \x01(\x05\x12\x12\n\nControlNet\x18\x30 \x01(\t\x12\x11\n\tTokenizer\x18\" \x01(\t\x12\x10\n\x08LoraBase\x18# \x01(\t\x12\x13\n\x0bLoraAdapter\x18$ \x01(\t\x12\x11\n\tLoraScale\x18* \x01(\x02\x12\x11\n\tNoMulMatQ\x18% \x01(\x08\x12\x12\n\nDraftModel\x18\' \x01(\t\x12\x11\n\tAudioPath\x18& \x01(\t\x12\x14\n\x0cQuantization\x18( \x01(\t\x12\x1c\n\x14GPUMemoryUtilization\x18\x32 \x01(\x02\x12\x17\n\x0fTrustRemoteCode\x18\x33 \x01(\x08\x12\x14\n\x0c\x45nforceEager\x18\x34 \x01(\x08\x12\x11\n\tSwapSpace\x18\x35 \x01(\x05\x12\x13\n\x0bMaxModelLen\x18\x36 \x01(\x05\x12\x0e\n\x06MMProj\x18) \x01(\t\x12\x13\n\x0bRopeScaling\x18+ \x01(\t\x12\x15\n\rYarnExtFactor\x18, \x01(\x02\x12\x16\n\x0eYarnAttnFactor\x18- \x01(\x02\x12\x14\n\x0cYarnBetaFast\x18. \x01(\x02\x12\x14\n\x0cYarnBetaSlow\x18/ \x01(\x02\x12\x0c\n\x04Type\x18\x31 \x01(\t\"*\n\x06Result\x12\x0f\n\x07message\x18\x01 \x01(\t\x12\x0f\n\x07success\x18\x02 \x01(\x08\"%\n\x0f\x45mbeddingResult\x12\x12\n\nembeddings\x18\x01 \x03(\x02\"C\n\x11TranscriptRequest\x12\x0b\n\x03\x64st\x18\x02 \x01(\t\x12\x10\n\x08language\x18\x03 \x01(\t\x12\x0f\n\x07threads\x18\x04 \x01(\r\"N\n\x10TranscriptResult\x12,\n\x08segments\x18\x01 \x03(\x0b\x32\x1a.backend.TranscriptSegment\x12\x0c\n\x04text\x18\x02 \x01(\t\"Y\n\x11TranscriptSegment\x12\n\n\x02id\x18\x01 \x01(\x05\x12\r\n\x05start\x18\x02 \x01(\x03\x12\x0b\n\x03\x65nd\x18\x03 \x01(\x03\x12\x0c\n\x04text\x18\x04 \x01(\t\x12\x0e\n\x06tokens\x18\x05 \x03(\x05\"\xd7\x01\n\x14GenerateImageRequest\x12\x0e\n\x06height\x18\x01 \x01(\x05\x12\r\n\x05width\x18\x02 \x01(\x05\x12\x0c\n\x04mode\x18\x03 \x01(\x05\x12\x0c\n\x04step\x18\x04 \x01(\x05\x12\x0c\n\x04seed\x18\x05 \x01(\x05\x12\x17\n\x0fpositive_prompt\x18\x06 \x01(\t\x12\x17\n\x0fnegative_prompt\x18\x07 \x01(\t\x12\x0b\n\x03\x64st\x18\x08 \x01(\t\x12\x0b\n\x03src\x18\t \x01(\t\x12\x18\n\x10\x45nableParameters\x18\n \x01(\t\x12\x10\n\x08\x43LIPSkip\x18\x0b \x01(\x05\"E\n\nTTSRequest\x12\x0c\n\x04text\x18\x01 \x01(\t\x12\r\n\x05model\x18\x02 \x01(\t\x12\x0b\n\x03\x64st\x18\x03 \x01(\t\x12\r\n\x05voice\x18\x04 \x01(\t\"6\n\x14TokenizationResponse\x12\x0e\n\x06length\x18\x01 \x01(\x05\x12\x0e\n\x06tokens\x18\x02 \x03(\x05\"\x8e\x01\n\x0fMemoryUsageData\x12\r\n\x05total\x18\x01 \x01(\x04\x12:\n\tbreakdown\x18\x02 \x03(\x0b\x32\'.backend.MemoryUsageData.BreakdownEntry\x1a\x30\n\x0e\x42reakdownEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\x04:\x02\x38\x01\"\xad\x01\n\x0eStatusResponse\x12,\n\x05state\x18\x01 \x01(\x0e\x32\x1d.backend.StatusResponse.State\x12(\n\x06memory\x18\x02 \x01(\x0b\x32\x18.backend.MemoryUsageData\"C\n\x05State\x12\x11\n\rUNINITIALIZED\x10\x00\x12\x08\n\x04\x42USY\x10\x01\x12\t\n\x05READY\x10\x02\x12\x12\n\x05\x45RROR\x10\xff\xff\xff\xff\xff\xff\xff\xff\xff\x01\x32\xf4\x04\n\x07\x42\x61\x63kend\x12\x32\n\x06Health\x12\x16.backend.HealthMessage\x1a\x0e.backend.Reply\"\x00\x12\x34\n\x07Predict\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x12\x35\n\tLoadModel\x12\x15.backend.ModelOptions\x1a\x0f.backend.Result\"\x00\x12<\n\rPredictStream\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x30\x01\x12@\n\tEmbedding\x12\x17.backend.PredictOptions\x1a\x18.backend.EmbeddingResult\"\x00\x12\x41\n\rGenerateImage\x12\x1d.backend.GenerateImageRequest\x1a\x0f.backend.Result\"\x00\x12M\n\x12\x41udioTranscription\x12\x1a.backend.TranscriptRequest\x1a\x19.backend.TranscriptResult\"\x00\x12-\n\x03TTS\x12\x13.backend.TTSRequest\x1a\x0f.backend.Result\"\x00\x12J\n\x0eTokenizeString\x12\x17.backend.PredictOptions\x1a\x1d.backend.TokenizationResponse\"\x00\x12;\n\x06Status\x12\x16.backend.HealthMessage\x1a\x17.backend.StatusResponse\"\x00\x42Z\n\x19io.skynet.localai.backendB\x0eLocalAIBackendP\x01Z+github.com/go-skynet/LocalAI/pkg/grpc/protob\x06proto3')
+DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\rbackend.proto\x12\x07\x62\x61\x63kend\x1a\x19google/protobuf/any.proto\"\x1b\n\tStoresKey\x12\x0e\n\x06\x46loats\x18\x01 \x03(\x02\"\x1c\n\x0bStoresValue\x12\r\n\x05\x42ytes\x18\x01 \x01(\x0c\"Z\n\x10StoresSetOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\"7\n\x13StoresDeleteOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\"4\n\x10StoresGetOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\"Y\n\x0fStoresGetResult\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\"B\n\x11StoresFindOptions\x12\x1f\n\x03Key\x18\x01 \x01(\x0b\x32\x12.backend.StoresKey\x12\x0c\n\x04TopK\x18\x02 \x01(\x05\"p\n\x10StoresFindResult\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\x12\x14\n\x0cSimilarities\x18\x03 \x03(\x02\"\x0f\n\rHealthMessage\"\xe8\x06\n\x0ePredictOptions\x12\x0e\n\x06Prompt\x18\x01 \x01(\t\x12\x0c\n\x04Seed\x18\x02 \x01(\x05\x12\x0f\n\x07Threads\x18\x03 \x01(\x05\x12\x0e\n\x06Tokens\x18\x04 \x01(\x05\x12\x0c\n\x04TopK\x18\x05 \x01(\x05\x12\x0e\n\x06Repeat\x18\x06 \x01(\x05\x12\r\n\x05\x42\x61tch\x18\x07 \x01(\x05\x12\r\n\x05NKeep\x18\x08 \x01(\x05\x12\x13\n\x0bTemperature\x18\t \x01(\x02\x12\x0f\n\x07Penalty\x18\n \x01(\x02\x12\r\n\x05\x46\x31\x36KV\x18\x0b \x01(\x08\x12\x11\n\tDebugMode\x18\x0c \x01(\x08\x12\x13\n\x0bStopPrompts\x18\r \x03(\t\x12\x11\n\tIgnoreEOS\x18\x0e \x01(\x08\x12\x19\n\x11TailFreeSamplingZ\x18\x0f \x01(\x02\x12\x10\n\x08TypicalP\x18\x10 \x01(\x02\x12\x18\n\x10\x46requencyPenalty\x18\x11 \x01(\x02\x12\x17\n\x0fPresencePenalty\x18\x12 \x01(\x02\x12\x10\n\x08Mirostat\x18\x13 \x01(\x05\x12\x13\n\x0bMirostatETA\x18\x14 \x01(\x02\x12\x13\n\x0bMirostatTAU\x18\x15 \x01(\x02\x12\x12\n\nPenalizeNL\x18\x16 \x01(\x08\x12\x11\n\tLogitBias\x18\x17 \x01(\t\x12\r\n\x05MLock\x18\x19 \x01(\x08\x12\x0c\n\x04MMap\x18\x1a \x01(\x08\x12\x16\n\x0ePromptCacheAll\x18\x1b \x01(\x08\x12\x15\n\rPromptCacheRO\x18\x1c \x01(\x08\x12\x0f\n\x07Grammar\x18\x1d \x01(\t\x12\x0f\n\x07MainGPU\x18\x1e \x01(\t\x12\x13\n\x0bTensorSplit\x18\x1f \x01(\t\x12\x0c\n\x04TopP\x18  \x01(\x02\x12\x17\n\x0fPromptCachePath\x18! \x01(\t\x12\r\n\x05\x44\x65\x62ug\x18\" \x01(\x08\x12\x17\n\x0f\x45mbeddingTokens\x18# \x03(\x05\x12\x12\n\nEmbeddings\x18$ \x01(\t\x12\x14\n\x0cRopeFreqBase\x18% \x01(\x02\x12\x15\n\rRopeFreqScale\x18& \x01(\x02\x12\x1b\n\x13NegativePromptScale\x18\' \x01(\x02\x12\x16\n\x0eNegativePrompt\x18( \x01(\t\x12\x0e\n\x06NDraft\x18) \x01(\x05\x12\x0e\n\x06Images\x18* \x03(\t\x12\x1c\n\x14UseTokenizerTemplate\x18+ \x01(\x08\x12\"\n\x08Messages\x18, \x03(\x0b\x32\x10.backend.Message\"\x18\n\x05Reply\x12\x0f\n\x07message\x18\x01 \x01(\x0c\"\xb0\x08\n\x0cModelOptions\x12\r\n\x05Model\x18\x01 \x01(\t\x12\x13\n\x0b\x43ontextSize\x18\x02 \x01(\x05\x12\x0c\n\x04Seed\x18\x03 \x01(\x05\x12\x0e\n\x06NBatch\x18\x04 \x01(\x05\x12\x11\n\tF16Memory\x18\x05 \x01(\x08\x12\r\n\x05MLock\x18\x06 \x01(\x08\x12\x0c\n\x04MMap\x18\x07 \x01(\x08\x12\x11\n\tVocabOnly\x18\x08 \x01(\x08\x12\x0f\n\x07LowVRAM\x18\t \x01(\x08\x12\x12\n\nEmbeddings\x18\n \x01(\x08\x12\x0c\n\x04NUMA\x18\x0b \x01(\x08\x12\x12\n\nNGPULayers\x18\x0c \x01(\x05\x12\x0f\n\x07MainGPU\x18\r \x01(\t\x12\x13\n\x0bTensorSplit\x18\x0e \x01(\t\x12\x0f\n\x07Threads\x18\x0f \x01(\x05\x12\x19\n\x11LibrarySearchPath\x18\x10 \x01(\t\x12\x14\n\x0cRopeFreqBase\x18\x11 \x01(\x02\x12\x15\n\rRopeFreqScale\x18\x12 \x01(\x02\x12\x12\n\nRMSNormEps\x18\x13 \x01(\x02\x12\x0c\n\x04NGQA\x18\x14 \x01(\x05\x12\x11\n\tModelFile\x18\x15 \x01(\t\x12\x0e\n\x06\x44\x65vice\x18\x16 \x01(\t\x12\x11\n\tUseTriton\x18\x17 \x01(\x08\x12\x15\n\rModelBaseName\x18\x18 \x01(\t\x12\x18\n\x10UseFastTokenizer\x18\x19 \x01(\x08\x12\x14\n\x0cPipelineType\x18\x1a \x01(\t\x12\x15\n\rSchedulerType\x18\x1b \x01(\t\x12\x0c\n\x04\x43UDA\x18\x1c \x01(\x08\x12\x10\n\x08\x43\x46GScale\x18\x1d \x01(\x02\x12\x0f\n\x07IMG2IMG\x18\x1e \x01(\x08\x12\x11\n\tCLIPModel\x18\x1f \x01(\t\x12\x15\n\rCLIPSubfolder\x18  \x01(\t\x12\x10\n\x08\x43LIPSkip\x18! \x01(\x05\x12\x12\n\nControlNet\x18\x30 \x01(\t\x12\x11\n\tTokenizer\x18\" \x01(\t\x12\x10\n\x08LoraBase\x18# \x01(\t\x12\x13\n\x0bLoraAdapter\x18$ \x01(\t\x12\x11\n\tLoraScale\x18* \x01(\x02\x12\x11\n\tNoMulMatQ\x18% \x01(\x08\x12\x12\n\nDraftModel\x18\' \x01(\t\x12\x11\n\tAudioPath\x18& \x01(\t\x12\x14\n\x0cQuantization\x18( \x01(\t\x12\x1c\n\x14GPUMemoryUtilization\x18\x32 \x01(\x02\x12\x17\n\x0fTrustRemoteCode\x18\x33 \x01(\x08\x12\x14\n\x0c\x45nforceEager\x18\x34 \x01(\x08\x12\x11\n\tSwapSpace\x18\x35 \x01(\x05\x12\x13\n\x0bMaxModelLen\x18\x36 \x01(\x05\x12\x0e\n\x06MMProj\x18) \x01(\t\x12\x13\n\x0bRopeScaling\x18+ \x01(\t\x12\x15\n\rYarnExtFactor\x18, \x01(\x02\x12\x16\n\x0eYarnAttnFactor\x18- \x01(\x02\x12\x14\n\x0cYarnBetaFast\x18. \x01(\x02\x12\x14\n\x0cYarnBetaSlow\x18/ \x01(\x02\x12\x0c\n\x04Type\x18\x31 \x01(\t\"*\n\x06Result\x12\x0f\n\x07message\x18\x01 \x01(\t\x12\x0f\n\x07success\x18\x02 \x01(\x08\"%\n\x0f\x45mbeddingResult\x12\x12\n\nembeddings\x18\x01 \x03(\x02\"C\n\x11TranscriptRequest\x12\x0b\n\x03\x64st\x18\x02 \x01(\t\x12\x10\n\x08language\x18\x03 \x01(\t\x12\x0f\n\x07threads\x18\x04 \x01(\r\"N\n\x10TranscriptResult\x12,\n\x08segments\x18\x01 \x03(\x0b\x32\x1a.backend.TranscriptSegment\x12\x0c\n\x04text\x18\x02 \x01(\t\"Y\n\x11TranscriptSegment\x12\n\n\x02id\x18\x01 \x01(\x05\x12\r\n\x05start\x18\x02 \x01(\x03\x12\x0b\n\x03\x65nd\x18\x03 \x01(\x03\x12\x0c\n\x04text\x18\x04 \x01(\t\x12\x0e\n\x06tokens\x18\x05 \x03(\x05\"\xd7\x01\n\x14GenerateImageRequest\x12\x0e\n\x06height\x18\x01 \x01(\x05\x12\r\n\x05width\x18\x02 \x01(\x05\x12\x0c\n\x04mode\x18\x03 \x01(\x05\x12\x0c\n\x04step\x18\x04 \x01(\x05\x12\x0c\n\x04seed\x18\x05 \x01(\x05\x12\x17\n\x0fpositive_prompt\x18\x06 \x01(\t\x12\x17\n\x0fnegative_prompt\x18\x07 \x01(\t\x12\x0b\n\x03\x64st\x18\x08 \x01(\t\x12\x0b\n\x03src\x18\t \x01(\t\x12\x18\n\x10\x45nableParameters\x18\n \x01(\t\x12\x10\n\x08\x43LIPSkip\x18\x0b \x01(\x05\"E\n\nTTSRequest\x12\x0c\n\x04text\x18\x01 \x01(\t\x12\r\n\x05model\x18\x02 \x01(\t\x12\x0b\n\x03\x64st\x18\x03 \x01(\t\x12\r\n\x05voice\x18\x04 \x01(\t\"6\n\x14TokenizationResponse\x12\x0e\n\x06length\x18\x01 \x01(\x05\x12\x0e\n\x06tokens\x18\x02 \x03(\x05\"\x8e\x01\n\x0fMemoryUsageData\x12\r\n\x05total\x18\x01 \x01(\x04\x12:\n\tbreakdown\x18\x02 \x03(\x0b\x32\'.backend.MemoryUsageData.BreakdownEntry\x1a\x30\n\x0e\x42reakdownEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\x04:\x02\x38\x01\"\xad\x01\n\x0eStatusResponse\x12,\n\x05state\x18\x01 \x01(\x0e\x32\x1d.backend.StatusResponse.State\x12(\n\x06memory\x18\x02 \x01(\x0b\x32\x18.backend.MemoryUsageData\"C\n\x05State\x12\x11\n\rUNINITIALIZED\x10\x00\x12\x08\n\x04\x42USY\x10\x01\x12\t\n\x05READY\x10\x02\x12\x12\n\x05\x45RROR\x10\xff\xff\xff\xff\xff\xff\xff\xff\xff\x01\">\n\x07Message\x12\x0c\n\x04Role\x18\x01 \x01(\t\x12%\n\x07\x43ontent\x18\x02 \x01(\x0b\x32\x14.google.protobuf.Any2\xfb\x06\n\x07\x42\x61\x63kend\x12\x32\n\x06Health\x12\x16.backend.HealthMessage\x1a\x0e.backend.Reply\"\x00\x12\x34\n\x07Predict\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x12\x35\n\tLoadModel\x12\x15.backend.ModelOptions\x1a\x0f.backend.Result\"\x00\x12<\n\rPredictStream\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x30\x01\x12@\n\tEmbedding\x12\x17.backend.PredictOptions\x1a\x18.backend.EmbeddingResult\"\x00\x12\x41\n\rGenerateImage\x12\x1d.backend.GenerateImageRequest\x1a\x0f.backend.Result\"\x00\x12M\n\x12\x41udioTranscription\x12\x1a.backend.TranscriptRequest\x1a\x19.backend.TranscriptResult\"\x00\x12-\n\x03TTS\x12\x13.backend.TTSRequest\x1a\x0f.backend.Result\"\x00\x12J\n\x0eTokenizeString\x12\x17.backend.PredictOptions\x1a\x1d.backend.TokenizationResponse\"\x00\x12;\n\x06Status\x12\x16.backend.HealthMessage\x1a\x17.backend.StatusResponse\"\x00\x12\x39\n\tStoresSet\x12\x19.backend.StoresSetOptions\x1a\x0f.backend.Result\"\x00\x12?\n\x0cStoresDelete\x12\x1c.backend.StoresDeleteOptions\x1a\x0f.backend.Result\"\x00\x12\x42\n\tStoresGet\x12\x19.backend.StoresGetOptions\x1a\x18.backend.StoresGetResult\"\x00\x12\x45\n\nStoresFind\x12\x1a.backend.StoresFindOptions\x1a\x19.backend.StoresFindResult\"\x00\x42Z\n\x19io.skynet.localai.backendB\x0eLocalAIBackendP\x01Z+github.com/go-skynet/LocalAI/pkg/grpc/protob\x06proto3')
 
 _globals = globals()
 _builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, _globals)
 _builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, 'backend_pb2', _globals)
 if _descriptor._USE_C_DESCRIPTORS == False:
-
-  DESCRIPTOR._options = None
-  DESCRIPTOR._serialized_options = b'\n\031io.skynet.localai.backendB\016LocalAIBackendP\001Z+github.com/go-skynet/LocalAI/pkg/grpc/proto'
-  _MEMORYUSAGEDATA_BREAKDOWNENTRY._options = None
-  _MEMORYUSAGEDATA_BREAKDOWNENTRY._serialized_options = b'8\001'
-  _globals['_HEALTHMESSAGE']._serialized_start=26
-  _globals['_HEALTHMESSAGE']._serialized_end=41
-  _globals['_PREDICTOPTIONS']._serialized_start=44
-  _globals['_PREDICTOPTIONS']._serialized_end=850
-  _globals['_REPLY']._serialized_start=852
-  _globals['_REPLY']._serialized_end=876
-  _globals['_MODELOPTIONS']._serialized_start=879
-  _globals['_MODELOPTIONS']._serialized_end=1951
-  _globals['_RESULT']._serialized_start=1953
-  _globals['_RESULT']._serialized_end=1995
-  _globals['_EMBEDDINGRESULT']._serialized_start=1997
-  _globals['_EMBEDDINGRESULT']._serialized_end=2034
-  _globals['_TRANSCRIPTREQUEST']._serialized_start=2036
-  _globals['_TRANSCRIPTREQUEST']._serialized_end=2103
-  _globals['_TRANSCRIPTRESULT']._serialized_start=2105
-  _globals['_TRANSCRIPTRESULT']._serialized_end=2183
-  _globals['_TRANSCRIPTSEGMENT']._serialized_start=2185
-  _globals['_TRANSCRIPTSEGMENT']._serialized_end=2274
-  _globals['_GENERATEIMAGEREQUEST']._serialized_start=2277
-  _globals['_GENERATEIMAGEREQUEST']._serialized_end=2492
-  _globals['_TTSREQUEST']._serialized_start=2494
-  _globals['_TTSREQUEST']._serialized_end=2563
-  _globals['_TOKENIZATIONRESPONSE']._serialized_start=2565
-  _globals['_TOKENIZATIONRESPONSE']._serialized_end=2619
-  _globals['_MEMORYUSAGEDATA']._serialized_start=2622
-  _globals['_MEMORYUSAGEDATA']._serialized_end=2764
-  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_start=2716
-  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_end=2764
-  _globals['_STATUSRESPONSE']._serialized_start=2767
-  _globals['_STATUSRESPONSE']._serialized_end=2940
-  _globals['_STATUSRESPONSE_STATE']._serialized_start=2873
-  _globals['_STATUSRESPONSE_STATE']._serialized_end=2940
-  _globals['_BACKEND']._serialized_start=2943
-  _globals['_BACKEND']._serialized_end=3571
+  _globals['DESCRIPTOR']._options = None
+  _globals['DESCRIPTOR']._serialized_options = b'\n\031io.skynet.localai.backendB\016LocalAIBackendP\001Z+github.com/go-skynet/LocalAI/pkg/grpc/proto'
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._options = None
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_options = b'8\001'
+  _globals['_STORESKEY']._serialized_start=53
+  _globals['_STORESKEY']._serialized_end=80
+  _globals['_STORESVALUE']._serialized_start=82
+  _globals['_STORESVALUE']._serialized_end=110
+  _globals['_STORESSETOPTIONS']._serialized_start=112
+  _globals['_STORESSETOPTIONS']._serialized_end=202
+  _globals['_STORESDELETEOPTIONS']._serialized_start=204
+  _globals['_STORESDELETEOPTIONS']._serialized_end=259
+  _globals['_STORESGETOPTIONS']._serialized_start=261
+  _globals['_STORESGETOPTIONS']._serialized_end=313
+  _globals['_STORESGETRESULT']._serialized_start=315
+  _globals['_STORESGETRESULT']._serialized_end=404
+  _globals['_STORESFINDOPTIONS']._serialized_start=406
+  _globals['_STORESFINDOPTIONS']._serialized_end=472
+  _globals['_STORESFINDRESULT']._serialized_start=474
+  _globals['_STORESFINDRESULT']._serialized_end=586
+  _globals['_HEALTHMESSAGE']._serialized_start=588
+  _globals['_HEALTHMESSAGE']._serialized_end=603
+  _globals['_PREDICTOPTIONS']._serialized_start=606
+  _globals['_PREDICTOPTIONS']._serialized_end=1478
+  _globals['_REPLY']._serialized_start=1480
+  _globals['_REPLY']._serialized_end=1504
+  _globals['_MODELOPTIONS']._serialized_start=1507
+  _globals['_MODELOPTIONS']._serialized_end=2579
+  _globals['_RESULT']._serialized_start=2581
+  _globals['_RESULT']._serialized_end=2623
+  _globals['_EMBEDDINGRESULT']._serialized_start=2625
+  _globals['_EMBEDDINGRESULT']._serialized_end=2662
+  _globals['_TRANSCRIPTREQUEST']._serialized_start=2664
+  _globals['_TRANSCRIPTREQUEST']._serialized_end=2731
+  _globals['_TRANSCRIPTRESULT']._serialized_start=2733
+  _globals['_TRANSCRIPTRESULT']._serialized_end=2811
+  _globals['_TRANSCRIPTSEGMENT']._serialized_start=2813
+  _globals['_TRANSCRIPTSEGMENT']._serialized_end=2902
+  _globals['_GENERATEIMAGEREQUEST']._serialized_start=2905
+  _globals['_GENERATEIMAGEREQUEST']._serialized_end=3120
+  _globals['_TTSREQUEST']._serialized_start=3122
+  _globals['_TTSREQUEST']._serialized_end=3191
+  _globals['_TOKENIZATIONRESPONSE']._serialized_start=3193
+  _globals['_TOKENIZATIONRESPONSE']._serialized_end=3247
+  _globals['_MEMORYUSAGEDATA']._serialized_start=3250
+  _globals['_MEMORYUSAGEDATA']._serialized_end=3392
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_start=3344
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_end=3392
+  _globals['_STATUSRESPONSE']._serialized_start=3395
+  _globals['_STATUSRESPONSE']._serialized_end=3568
+  _globals['_STATUSRESPONSE_STATE']._serialized_start=3501
+  _globals['_STATUSRESPONSE_STATE']._serialized_end=3568
+  _globals['_MESSAGE']._serialized_start=3570
+  _globals['_MESSAGE']._serialized_end=3632
+  _globals['_BACKEND']._serialized_start=3635
+  _globals['_BACKEND']._serialized_end=4526
 # @@protoc_insertion_point(module_scope)
diff --git a/backend/python/diffusers/backend_pb2_grpc.py b/backend/python/diffusers/backend_pb2_grpc.py
index 79a7677fb27f..e06fccf3d451 100644
--- a/backend/python/diffusers/backend_pb2_grpc.py
+++ b/backend/python/diffusers/backend_pb2_grpc.py
@@ -64,6 +64,26 @@ def __init__(self, channel):
                 request_serializer=backend__pb2.HealthMessage.SerializeToString,
                 response_deserializer=backend__pb2.StatusResponse.FromString,
                 )
+        self.StoresSet = channel.unary_unary(
+                '/backend.Backend/StoresSet',
+                request_serializer=backend__pb2.StoresSetOptions.SerializeToString,
+                response_deserializer=backend__pb2.Result.FromString,
+                )
+        self.StoresDelete = channel.unary_unary(
+                '/backend.Backend/StoresDelete',
+                request_serializer=backend__pb2.StoresDeleteOptions.SerializeToString,
+                response_deserializer=backend__pb2.Result.FromString,
+                )
+        self.StoresGet = channel.unary_unary(
+                '/backend.Backend/StoresGet',
+                request_serializer=backend__pb2.StoresGetOptions.SerializeToString,
+                response_deserializer=backend__pb2.StoresGetResult.FromString,
+                )
+        self.StoresFind = channel.unary_unary(
+                '/backend.Backend/StoresFind',
+                request_serializer=backend__pb2.StoresFindOptions.SerializeToString,
+                response_deserializer=backend__pb2.StoresFindResult.FromString,
+                )
 
 
 class BackendServicer(object):
@@ -129,6 +149,30 @@ def Status(self, request, context):
         context.set_details('Method not implemented!')
         raise NotImplementedError('Method not implemented!')
 
+    def StoresSet(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresDelete(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresGet(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresFind(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
 
 def add_BackendServicer_to_server(servicer, server):
     rpc_method_handlers = {
@@ -182,6 +226,26 @@ def add_BackendServicer_to_server(servicer, server):
                     request_deserializer=backend__pb2.HealthMessage.FromString,
                     response_serializer=backend__pb2.StatusResponse.SerializeToString,
             ),
+            'StoresSet': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresSet,
+                    request_deserializer=backend__pb2.StoresSetOptions.FromString,
+                    response_serializer=backend__pb2.Result.SerializeToString,
+            ),
+            'StoresDelete': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresDelete,
+                    request_deserializer=backend__pb2.StoresDeleteOptions.FromString,
+                    response_serializer=backend__pb2.Result.SerializeToString,
+            ),
+            'StoresGet': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresGet,
+                    request_deserializer=backend__pb2.StoresGetOptions.FromString,
+                    response_serializer=backend__pb2.StoresGetResult.SerializeToString,
+            ),
+            'StoresFind': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresFind,
+                    request_deserializer=backend__pb2.StoresFindOptions.FromString,
+                    response_serializer=backend__pb2.StoresFindResult.SerializeToString,
+            ),
     }
     generic_handler = grpc.method_handlers_generic_handler(
             'backend.Backend', rpc_method_handlers)
@@ -361,3 +425,71 @@ def Status(request,
             backend__pb2.StatusResponse.FromString,
             options, channel_credentials,
             insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresSet(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresSet',
+            backend__pb2.StoresSetOptions.SerializeToString,
+            backend__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresDelete(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresDelete',
+            backend__pb2.StoresDeleteOptions.SerializeToString,
+            backend__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresGet(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresGet',
+            backend__pb2.StoresGetOptions.SerializeToString,
+            backend__pb2.StoresGetResult.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresFind(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresFind',
+            backend__pb2.StoresFindOptions.SerializeToString,
+            backend__pb2.StoresFindResult.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
diff --git a/backend/python/exllama/backend_pb2.py b/backend/python/exllama/backend_pb2.py
index 08b896c7cad5..8d366c16d63b 100644
--- a/backend/python/exllama/backend_pb2.py
+++ b/backend/python/exllama/backend_pb2.py
@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 # Generated by the protocol buffer compiler.  DO NOT EDIT!
 # source: backend.proto
+# Protobuf Python Version: 4.25.1
 """Generated protocol buffer code."""
 from google.protobuf import descriptor as _descriptor
 from google.protobuf import descriptor_pool as _descriptor_pool
@@ -11,51 +12,69 @@
 _sym_db = _symbol_database.Default()
 
 
+from google.protobuf import any_pb2 as google_dot_protobuf_dot_any__pb2
 
 
-DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\rbackend.proto\x12\x07\x62\x61\x63kend\"\x0f\n\rHealthMessage\"\xa6\x06\n\x0ePredictOptions\x12\x0e\n\x06Prompt\x18\x01 \x01(\t\x12\x0c\n\x04Seed\x18\x02 \x01(\x05\x12\x0f\n\x07Threads\x18\x03 \x01(\x05\x12\x0e\n\x06Tokens\x18\x04 \x01(\x05\x12\x0c\n\x04TopK\x18\x05 \x01(\x05\x12\x0e\n\x06Repeat\x18\x06 \x01(\x05\x12\r\n\x05\x42\x61tch\x18\x07 \x01(\x05\x12\r\n\x05NKeep\x18\x08 \x01(\x05\x12\x13\n\x0bTemperature\x18\t \x01(\x02\x12\x0f\n\x07Penalty\x18\n \x01(\x02\x12\r\n\x05\x46\x31\x36KV\x18\x0b \x01(\x08\x12\x11\n\tDebugMode\x18\x0c \x01(\x08\x12\x13\n\x0bStopPrompts\x18\r \x03(\t\x12\x11\n\tIgnoreEOS\x18\x0e \x01(\x08\x12\x19\n\x11TailFreeSamplingZ\x18\x0f \x01(\x02\x12\x10\n\x08TypicalP\x18\x10 \x01(\x02\x12\x18\n\x10\x46requencyPenalty\x18\x11 \x01(\x02\x12\x17\n\x0fPresencePenalty\x18\x12 \x01(\x02\x12\x10\n\x08Mirostat\x18\x13 \x01(\x05\x12\x13\n\x0bMirostatETA\x18\x14 \x01(\x02\x12\x13\n\x0bMirostatTAU\x18\x15 \x01(\x02\x12\x12\n\nPenalizeNL\x18\x16 \x01(\x08\x12\x11\n\tLogitBias\x18\x17 \x01(\t\x12\r\n\x05MLock\x18\x19 \x01(\x08\x12\x0c\n\x04MMap\x18\x1a \x01(\x08\x12\x16\n\x0ePromptCacheAll\x18\x1b \x01(\x08\x12\x15\n\rPromptCacheRO\x18\x1c \x01(\x08\x12\x0f\n\x07Grammar\x18\x1d \x01(\t\x12\x0f\n\x07MainGPU\x18\x1e \x01(\t\x12\x13\n\x0bTensorSplit\x18\x1f \x01(\t\x12\x0c\n\x04TopP\x18  \x01(\x02\x12\x17\n\x0fPromptCachePath\x18! \x01(\t\x12\r\n\x05\x44\x65\x62ug\x18\" \x01(\x08\x12\x17\n\x0f\x45mbeddingTokens\x18# \x03(\x05\x12\x12\n\nEmbeddings\x18$ \x01(\t\x12\x14\n\x0cRopeFreqBase\x18% \x01(\x02\x12\x15\n\rRopeFreqScale\x18& \x01(\x02\x12\x1b\n\x13NegativePromptScale\x18\' \x01(\x02\x12\x16\n\x0eNegativePrompt\x18( \x01(\t\x12\x0e\n\x06NDraft\x18) \x01(\x05\x12\x0e\n\x06Images\x18* \x03(\t\"\x18\n\x05Reply\x12\x0f\n\x07message\x18\x01 \x01(\x0c\"\xb0\x08\n\x0cModelOptions\x12\r\n\x05Model\x18\x01 \x01(\t\x12\x13\n\x0b\x43ontextSize\x18\x02 \x01(\x05\x12\x0c\n\x04Seed\x18\x03 \x01(\x05\x12\x0e\n\x06NBatch\x18\x04 \x01(\x05\x12\x11\n\tF16Memory\x18\x05 \x01(\x08\x12\r\n\x05MLock\x18\x06 \x01(\x08\x12\x0c\n\x04MMap\x18\x07 \x01(\x08\x12\x11\n\tVocabOnly\x18\x08 \x01(\x08\x12\x0f\n\x07LowVRAM\x18\t \x01(\x08\x12\x12\n\nEmbeddings\x18\n \x01(\x08\x12\x0c\n\x04NUMA\x18\x0b \x01(\x08\x12\x12\n\nNGPULayers\x18\x0c \x01(\x05\x12\x0f\n\x07MainGPU\x18\r \x01(\t\x12\x13\n\x0bTensorSplit\x18\x0e \x01(\t\x12\x0f\n\x07Threads\x18\x0f \x01(\x05\x12\x19\n\x11LibrarySearchPath\x18\x10 \x01(\t\x12\x14\n\x0cRopeFreqBase\x18\x11 \x01(\x02\x12\x15\n\rRopeFreqScale\x18\x12 \x01(\x02\x12\x12\n\nRMSNormEps\x18\x13 \x01(\x02\x12\x0c\n\x04NGQA\x18\x14 \x01(\x05\x12\x11\n\tModelFile\x18\x15 \x01(\t\x12\x0e\n\x06\x44\x65vice\x18\x16 \x01(\t\x12\x11\n\tUseTriton\x18\x17 \x01(\x08\x12\x15\n\rModelBaseName\x18\x18 \x01(\t\x12\x18\n\x10UseFastTokenizer\x18\x19 \x01(\x08\x12\x14\n\x0cPipelineType\x18\x1a \x01(\t\x12\x15\n\rSchedulerType\x18\x1b \x01(\t\x12\x0c\n\x04\x43UDA\x18\x1c \x01(\x08\x12\x10\n\x08\x43\x46GScale\x18\x1d \x01(\x02\x12\x0f\n\x07IMG2IMG\x18\x1e \x01(\x08\x12\x11\n\tCLIPModel\x18\x1f \x01(\t\x12\x15\n\rCLIPSubfolder\x18  \x01(\t\x12\x10\n\x08\x43LIPSkip\x18! \x01(\x05\x12\x12\n\nControlNet\x18\x30 \x01(\t\x12\x11\n\tTokenizer\x18\" \x01(\t\x12\x10\n\x08LoraBase\x18# \x01(\t\x12\x13\n\x0bLoraAdapter\x18$ \x01(\t\x12\x11\n\tLoraScale\x18* \x01(\x02\x12\x11\n\tNoMulMatQ\x18% \x01(\x08\x12\x12\n\nDraftModel\x18\' \x01(\t\x12\x11\n\tAudioPath\x18& \x01(\t\x12\x14\n\x0cQuantization\x18( \x01(\t\x12\x1c\n\x14GPUMemoryUtilization\x18\x32 \x01(\x02\x12\x17\n\x0fTrustRemoteCode\x18\x33 \x01(\x08\x12\x14\n\x0c\x45nforceEager\x18\x34 \x01(\x08\x12\x11\n\tSwapSpace\x18\x35 \x01(\x05\x12\x13\n\x0bMaxModelLen\x18\x36 \x01(\x05\x12\x0e\n\x06MMProj\x18) \x01(\t\x12\x13\n\x0bRopeScaling\x18+ \x01(\t\x12\x15\n\rYarnExtFactor\x18, \x01(\x02\x12\x16\n\x0eYarnAttnFactor\x18- \x01(\x02\x12\x14\n\x0cYarnBetaFast\x18. \x01(\x02\x12\x14\n\x0cYarnBetaSlow\x18/ \x01(\x02\x12\x0c\n\x04Type\x18\x31 \x01(\t\"*\n\x06Result\x12\x0f\n\x07message\x18\x01 \x01(\t\x12\x0f\n\x07success\x18\x02 \x01(\x08\"%\n\x0f\x45mbeddingResult\x12\x12\n\nembeddings\x18\x01 \x03(\x02\"C\n\x11TranscriptRequest\x12\x0b\n\x03\x64st\x18\x02 \x01(\t\x12\x10\n\x08language\x18\x03 \x01(\t\x12\x0f\n\x07threads\x18\x04 \x01(\r\"N\n\x10TranscriptResult\x12,\n\x08segments\x18\x01 \x03(\x0b\x32\x1a.backend.TranscriptSegment\x12\x0c\n\x04text\x18\x02 \x01(\t\"Y\n\x11TranscriptSegment\x12\n\n\x02id\x18\x01 \x01(\x05\x12\r\n\x05start\x18\x02 \x01(\x03\x12\x0b\n\x03\x65nd\x18\x03 \x01(\x03\x12\x0c\n\x04text\x18\x04 \x01(\t\x12\x0e\n\x06tokens\x18\x05 \x03(\x05\"\xd7\x01\n\x14GenerateImageRequest\x12\x0e\n\x06height\x18\x01 \x01(\x05\x12\r\n\x05width\x18\x02 \x01(\x05\x12\x0c\n\x04mode\x18\x03 \x01(\x05\x12\x0c\n\x04step\x18\x04 \x01(\x05\x12\x0c\n\x04seed\x18\x05 \x01(\x05\x12\x17\n\x0fpositive_prompt\x18\x06 \x01(\t\x12\x17\n\x0fnegative_prompt\x18\x07 \x01(\t\x12\x0b\n\x03\x64st\x18\x08 \x01(\t\x12\x0b\n\x03src\x18\t \x01(\t\x12\x18\n\x10\x45nableParameters\x18\n \x01(\t\x12\x10\n\x08\x43LIPSkip\x18\x0b \x01(\x05\"E\n\nTTSRequest\x12\x0c\n\x04text\x18\x01 \x01(\t\x12\r\n\x05model\x18\x02 \x01(\t\x12\x0b\n\x03\x64st\x18\x03 \x01(\t\x12\r\n\x05voice\x18\x04 \x01(\t\"6\n\x14TokenizationResponse\x12\x0e\n\x06length\x18\x01 \x01(\x05\x12\x0e\n\x06tokens\x18\x02 \x03(\x05\"\x8e\x01\n\x0fMemoryUsageData\x12\r\n\x05total\x18\x01 \x01(\x04\x12:\n\tbreakdown\x18\x02 \x03(\x0b\x32\'.backend.MemoryUsageData.BreakdownEntry\x1a\x30\n\x0e\x42reakdownEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\x04:\x02\x38\x01\"\xad\x01\n\x0eStatusResponse\x12,\n\x05state\x18\x01 \x01(\x0e\x32\x1d.backend.StatusResponse.State\x12(\n\x06memory\x18\x02 \x01(\x0b\x32\x18.backend.MemoryUsageData\"C\n\x05State\x12\x11\n\rUNINITIALIZED\x10\x00\x12\x08\n\x04\x42USY\x10\x01\x12\t\n\x05READY\x10\x02\x12\x12\n\x05\x45RROR\x10\xff\xff\xff\xff\xff\xff\xff\xff\xff\x01\x32\xf4\x04\n\x07\x42\x61\x63kend\x12\x32\n\x06Health\x12\x16.backend.HealthMessage\x1a\x0e.backend.Reply\"\x00\x12\x34\n\x07Predict\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x12\x35\n\tLoadModel\x12\x15.backend.ModelOptions\x1a\x0f.backend.Result\"\x00\x12<\n\rPredictStream\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x30\x01\x12@\n\tEmbedding\x12\x17.backend.PredictOptions\x1a\x18.backend.EmbeddingResult\"\x00\x12\x41\n\rGenerateImage\x12\x1d.backend.GenerateImageRequest\x1a\x0f.backend.Result\"\x00\x12M\n\x12\x41udioTranscription\x12\x1a.backend.TranscriptRequest\x1a\x19.backend.TranscriptResult\"\x00\x12-\n\x03TTS\x12\x13.backend.TTSRequest\x1a\x0f.backend.Result\"\x00\x12J\n\x0eTokenizeString\x12\x17.backend.PredictOptions\x1a\x1d.backend.TokenizationResponse\"\x00\x12;\n\x06Status\x12\x16.backend.HealthMessage\x1a\x17.backend.StatusResponse\"\x00\x42Z\n\x19io.skynet.localai.backendB\x0eLocalAIBackendP\x01Z+github.com/go-skynet/LocalAI/pkg/grpc/protob\x06proto3')
+DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\rbackend.proto\x12\x07\x62\x61\x63kend\x1a\x19google/protobuf/any.proto\"\x1b\n\tStoresKey\x12\x0e\n\x06\x46loats\x18\x01 \x03(\x02\"\x1c\n\x0bStoresValue\x12\r\n\x05\x42ytes\x18\x01 \x01(\x0c\"Z\n\x10StoresSetOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\"7\n\x13StoresDeleteOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\"4\n\x10StoresGetOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\"Y\n\x0fStoresGetResult\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\"B\n\x11StoresFindOptions\x12\x1f\n\x03Key\x18\x01 \x01(\x0b\x32\x12.backend.StoresKey\x12\x0c\n\x04TopK\x18\x02 \x01(\x05\"p\n\x10StoresFindResult\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\x12\x14\n\x0cSimilarities\x18\x03 \x03(\x02\"\x0f\n\rHealthMessage\"\xe8\x06\n\x0ePredictOptions\x12\x0e\n\x06Prompt\x18\x01 \x01(\t\x12\x0c\n\x04Seed\x18\x02 \x01(\x05\x12\x0f\n\x07Threads\x18\x03 \x01(\x05\x12\x0e\n\x06Tokens\x18\x04 \x01(\x05\x12\x0c\n\x04TopK\x18\x05 \x01(\x05\x12\x0e\n\x06Repeat\x18\x06 \x01(\x05\x12\r\n\x05\x42\x61tch\x18\x07 \x01(\x05\x12\r\n\x05NKeep\x18\x08 \x01(\x05\x12\x13\n\x0bTemperature\x18\t \x01(\x02\x12\x0f\n\x07Penalty\x18\n \x01(\x02\x12\r\n\x05\x46\x31\x36KV\x18\x0b \x01(\x08\x12\x11\n\tDebugMode\x18\x0c \x01(\x08\x12\x13\n\x0bStopPrompts\x18\r \x03(\t\x12\x11\n\tIgnoreEOS\x18\x0e \x01(\x08\x12\x19\n\x11TailFreeSamplingZ\x18\x0f \x01(\x02\x12\x10\n\x08TypicalP\x18\x10 \x01(\x02\x12\x18\n\x10\x46requencyPenalty\x18\x11 \x01(\x02\x12\x17\n\x0fPresencePenalty\x18\x12 \x01(\x02\x12\x10\n\x08Mirostat\x18\x13 \x01(\x05\x12\x13\n\x0bMirostatETA\x18\x14 \x01(\x02\x12\x13\n\x0bMirostatTAU\x18\x15 \x01(\x02\x12\x12\n\nPenalizeNL\x18\x16 \x01(\x08\x12\x11\n\tLogitBias\x18\x17 \x01(\t\x12\r\n\x05MLock\x18\x19 \x01(\x08\x12\x0c\n\x04MMap\x18\x1a \x01(\x08\x12\x16\n\x0ePromptCacheAll\x18\x1b \x01(\x08\x12\x15\n\rPromptCacheRO\x18\x1c \x01(\x08\x12\x0f\n\x07Grammar\x18\x1d \x01(\t\x12\x0f\n\x07MainGPU\x18\x1e \x01(\t\x12\x13\n\x0bTensorSplit\x18\x1f \x01(\t\x12\x0c\n\x04TopP\x18  \x01(\x02\x12\x17\n\x0fPromptCachePath\x18! \x01(\t\x12\r\n\x05\x44\x65\x62ug\x18\" \x01(\x08\x12\x17\n\x0f\x45mbeddingTokens\x18# \x03(\x05\x12\x12\n\nEmbeddings\x18$ \x01(\t\x12\x14\n\x0cRopeFreqBase\x18% \x01(\x02\x12\x15\n\rRopeFreqScale\x18& \x01(\x02\x12\x1b\n\x13NegativePromptScale\x18\' \x01(\x02\x12\x16\n\x0eNegativePrompt\x18( \x01(\t\x12\x0e\n\x06NDraft\x18) \x01(\x05\x12\x0e\n\x06Images\x18* \x03(\t\x12\x1c\n\x14UseTokenizerTemplate\x18+ \x01(\x08\x12\"\n\x08Messages\x18, \x03(\x0b\x32\x10.backend.Message\"\x18\n\x05Reply\x12\x0f\n\x07message\x18\x01 \x01(\x0c\"\xb0\x08\n\x0cModelOptions\x12\r\n\x05Model\x18\x01 \x01(\t\x12\x13\n\x0b\x43ontextSize\x18\x02 \x01(\x05\x12\x0c\n\x04Seed\x18\x03 \x01(\x05\x12\x0e\n\x06NBatch\x18\x04 \x01(\x05\x12\x11\n\tF16Memory\x18\x05 \x01(\x08\x12\r\n\x05MLock\x18\x06 \x01(\x08\x12\x0c\n\x04MMap\x18\x07 \x01(\x08\x12\x11\n\tVocabOnly\x18\x08 \x01(\x08\x12\x0f\n\x07LowVRAM\x18\t \x01(\x08\x12\x12\n\nEmbeddings\x18\n \x01(\x08\x12\x0c\n\x04NUMA\x18\x0b \x01(\x08\x12\x12\n\nNGPULayers\x18\x0c \x01(\x05\x12\x0f\n\x07MainGPU\x18\r \x01(\t\x12\x13\n\x0bTensorSplit\x18\x0e \x01(\t\x12\x0f\n\x07Threads\x18\x0f \x01(\x05\x12\x19\n\x11LibrarySearchPath\x18\x10 \x01(\t\x12\x14\n\x0cRopeFreqBase\x18\x11 \x01(\x02\x12\x15\n\rRopeFreqScale\x18\x12 \x01(\x02\x12\x12\n\nRMSNormEps\x18\x13 \x01(\x02\x12\x0c\n\x04NGQA\x18\x14 \x01(\x05\x12\x11\n\tModelFile\x18\x15 \x01(\t\x12\x0e\n\x06\x44\x65vice\x18\x16 \x01(\t\x12\x11\n\tUseTriton\x18\x17 \x01(\x08\x12\x15\n\rModelBaseName\x18\x18 \x01(\t\x12\x18\n\x10UseFastTokenizer\x18\x19 \x01(\x08\x12\x14\n\x0cPipelineType\x18\x1a \x01(\t\x12\x15\n\rSchedulerType\x18\x1b \x01(\t\x12\x0c\n\x04\x43UDA\x18\x1c \x01(\x08\x12\x10\n\x08\x43\x46GScale\x18\x1d \x01(\x02\x12\x0f\n\x07IMG2IMG\x18\x1e \x01(\x08\x12\x11\n\tCLIPModel\x18\x1f \x01(\t\x12\x15\n\rCLIPSubfolder\x18  \x01(\t\x12\x10\n\x08\x43LIPSkip\x18! \x01(\x05\x12\x12\n\nControlNet\x18\x30 \x01(\t\x12\x11\n\tTokenizer\x18\" \x01(\t\x12\x10\n\x08LoraBase\x18# \x01(\t\x12\x13\n\x0bLoraAdapter\x18$ \x01(\t\x12\x11\n\tLoraScale\x18* \x01(\x02\x12\x11\n\tNoMulMatQ\x18% \x01(\x08\x12\x12\n\nDraftModel\x18\' \x01(\t\x12\x11\n\tAudioPath\x18& \x01(\t\x12\x14\n\x0cQuantization\x18( \x01(\t\x12\x1c\n\x14GPUMemoryUtilization\x18\x32 \x01(\x02\x12\x17\n\x0fTrustRemoteCode\x18\x33 \x01(\x08\x12\x14\n\x0c\x45nforceEager\x18\x34 \x01(\x08\x12\x11\n\tSwapSpace\x18\x35 \x01(\x05\x12\x13\n\x0bMaxModelLen\x18\x36 \x01(\x05\x12\x0e\n\x06MMProj\x18) \x01(\t\x12\x13\n\x0bRopeScaling\x18+ \x01(\t\x12\x15\n\rYarnExtFactor\x18, \x01(\x02\x12\x16\n\x0eYarnAttnFactor\x18- \x01(\x02\x12\x14\n\x0cYarnBetaFast\x18. \x01(\x02\x12\x14\n\x0cYarnBetaSlow\x18/ \x01(\x02\x12\x0c\n\x04Type\x18\x31 \x01(\t\"*\n\x06Result\x12\x0f\n\x07message\x18\x01 \x01(\t\x12\x0f\n\x07success\x18\x02 \x01(\x08\"%\n\x0f\x45mbeddingResult\x12\x12\n\nembeddings\x18\x01 \x03(\x02\"C\n\x11TranscriptRequest\x12\x0b\n\x03\x64st\x18\x02 \x01(\t\x12\x10\n\x08language\x18\x03 \x01(\t\x12\x0f\n\x07threads\x18\x04 \x01(\r\"N\n\x10TranscriptResult\x12,\n\x08segments\x18\x01 \x03(\x0b\x32\x1a.backend.TranscriptSegment\x12\x0c\n\x04text\x18\x02 \x01(\t\"Y\n\x11TranscriptSegment\x12\n\n\x02id\x18\x01 \x01(\x05\x12\r\n\x05start\x18\x02 \x01(\x03\x12\x0b\n\x03\x65nd\x18\x03 \x01(\x03\x12\x0c\n\x04text\x18\x04 \x01(\t\x12\x0e\n\x06tokens\x18\x05 \x03(\x05\"\xd7\x01\n\x14GenerateImageRequest\x12\x0e\n\x06height\x18\x01 \x01(\x05\x12\r\n\x05width\x18\x02 \x01(\x05\x12\x0c\n\x04mode\x18\x03 \x01(\x05\x12\x0c\n\x04step\x18\x04 \x01(\x05\x12\x0c\n\x04seed\x18\x05 \x01(\x05\x12\x17\n\x0fpositive_prompt\x18\x06 \x01(\t\x12\x17\n\x0fnegative_prompt\x18\x07 \x01(\t\x12\x0b\n\x03\x64st\x18\x08 \x01(\t\x12\x0b\n\x03src\x18\t \x01(\t\x12\x18\n\x10\x45nableParameters\x18\n \x01(\t\x12\x10\n\x08\x43LIPSkip\x18\x0b \x01(\x05\"E\n\nTTSRequest\x12\x0c\n\x04text\x18\x01 \x01(\t\x12\r\n\x05model\x18\x02 \x01(\t\x12\x0b\n\x03\x64st\x18\x03 \x01(\t\x12\r\n\x05voice\x18\x04 \x01(\t\"6\n\x14TokenizationResponse\x12\x0e\n\x06length\x18\x01 \x01(\x05\x12\x0e\n\x06tokens\x18\x02 \x03(\x05\"\x8e\x01\n\x0fMemoryUsageData\x12\r\n\x05total\x18\x01 \x01(\x04\x12:\n\tbreakdown\x18\x02 \x03(\x0b\x32\'.backend.MemoryUsageData.BreakdownEntry\x1a\x30\n\x0e\x42reakdownEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\x04:\x02\x38\x01\"\xad\x01\n\x0eStatusResponse\x12,\n\x05state\x18\x01 \x01(\x0e\x32\x1d.backend.StatusResponse.State\x12(\n\x06memory\x18\x02 \x01(\x0b\x32\x18.backend.MemoryUsageData\"C\n\x05State\x12\x11\n\rUNINITIALIZED\x10\x00\x12\x08\n\x04\x42USY\x10\x01\x12\t\n\x05READY\x10\x02\x12\x12\n\x05\x45RROR\x10\xff\xff\xff\xff\xff\xff\xff\xff\xff\x01\">\n\x07Message\x12\x0c\n\x04Role\x18\x01 \x01(\t\x12%\n\x07\x43ontent\x18\x02 \x01(\x0b\x32\x14.google.protobuf.Any2\xfb\x06\n\x07\x42\x61\x63kend\x12\x32\n\x06Health\x12\x16.backend.HealthMessage\x1a\x0e.backend.Reply\"\x00\x12\x34\n\x07Predict\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x12\x35\n\tLoadModel\x12\x15.backend.ModelOptions\x1a\x0f.backend.Result\"\x00\x12<\n\rPredictStream\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x30\x01\x12@\n\tEmbedding\x12\x17.backend.PredictOptions\x1a\x18.backend.EmbeddingResult\"\x00\x12\x41\n\rGenerateImage\x12\x1d.backend.GenerateImageRequest\x1a\x0f.backend.Result\"\x00\x12M\n\x12\x41udioTranscription\x12\x1a.backend.TranscriptRequest\x1a\x19.backend.TranscriptResult\"\x00\x12-\n\x03TTS\x12\x13.backend.TTSRequest\x1a\x0f.backend.Result\"\x00\x12J\n\x0eTokenizeString\x12\x17.backend.PredictOptions\x1a\x1d.backend.TokenizationResponse\"\x00\x12;\n\x06Status\x12\x16.backend.HealthMessage\x1a\x17.backend.StatusResponse\"\x00\x12\x39\n\tStoresSet\x12\x19.backend.StoresSetOptions\x1a\x0f.backend.Result\"\x00\x12?\n\x0cStoresDelete\x12\x1c.backend.StoresDeleteOptions\x1a\x0f.backend.Result\"\x00\x12\x42\n\tStoresGet\x12\x19.backend.StoresGetOptions\x1a\x18.backend.StoresGetResult\"\x00\x12\x45\n\nStoresFind\x12\x1a.backend.StoresFindOptions\x1a\x19.backend.StoresFindResult\"\x00\x42Z\n\x19io.skynet.localai.backendB\x0eLocalAIBackendP\x01Z+github.com/go-skynet/LocalAI/pkg/grpc/protob\x06proto3')
 
 _globals = globals()
 _builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, _globals)
 _builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, 'backend_pb2', _globals)
 if _descriptor._USE_C_DESCRIPTORS == False:
-
-  DESCRIPTOR._options = None
-  DESCRIPTOR._serialized_options = b'\n\031io.skynet.localai.backendB\016LocalAIBackendP\001Z+github.com/go-skynet/LocalAI/pkg/grpc/proto'
-  _MEMORYUSAGEDATA_BREAKDOWNENTRY._options = None
-  _MEMORYUSAGEDATA_BREAKDOWNENTRY._serialized_options = b'8\001'
-  _globals['_HEALTHMESSAGE']._serialized_start=26
-  _globals['_HEALTHMESSAGE']._serialized_end=41
-  _globals['_PREDICTOPTIONS']._serialized_start=44
-  _globals['_PREDICTOPTIONS']._serialized_end=850
-  _globals['_REPLY']._serialized_start=852
-  _globals['_REPLY']._serialized_end=876
-  _globals['_MODELOPTIONS']._serialized_start=879
-  _globals['_MODELOPTIONS']._serialized_end=1951
-  _globals['_RESULT']._serialized_start=1953
-  _globals['_RESULT']._serialized_end=1995
-  _globals['_EMBEDDINGRESULT']._serialized_start=1997
-  _globals['_EMBEDDINGRESULT']._serialized_end=2034
-  _globals['_TRANSCRIPTREQUEST']._serialized_start=2036
-  _globals['_TRANSCRIPTREQUEST']._serialized_end=2103
-  _globals['_TRANSCRIPTRESULT']._serialized_start=2105
-  _globals['_TRANSCRIPTRESULT']._serialized_end=2183
-  _globals['_TRANSCRIPTSEGMENT']._serialized_start=2185
-  _globals['_TRANSCRIPTSEGMENT']._serialized_end=2274
-  _globals['_GENERATEIMAGEREQUEST']._serialized_start=2277
-  _globals['_GENERATEIMAGEREQUEST']._serialized_end=2492
-  _globals['_TTSREQUEST']._serialized_start=2494
-  _globals['_TTSREQUEST']._serialized_end=2563
-  _globals['_TOKENIZATIONRESPONSE']._serialized_start=2565
-  _globals['_TOKENIZATIONRESPONSE']._serialized_end=2619
-  _globals['_MEMORYUSAGEDATA']._serialized_start=2622
-  _globals['_MEMORYUSAGEDATA']._serialized_end=2764
-  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_start=2716
-  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_end=2764
-  _globals['_STATUSRESPONSE']._serialized_start=2767
-  _globals['_STATUSRESPONSE']._serialized_end=2940
-  _globals['_STATUSRESPONSE_STATE']._serialized_start=2873
-  _globals['_STATUSRESPONSE_STATE']._serialized_end=2940
-  _globals['_BACKEND']._serialized_start=2943
-  _globals['_BACKEND']._serialized_end=3571
+  _globals['DESCRIPTOR']._options = None
+  _globals['DESCRIPTOR']._serialized_options = b'\n\031io.skynet.localai.backendB\016LocalAIBackendP\001Z+github.com/go-skynet/LocalAI/pkg/grpc/proto'
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._options = None
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_options = b'8\001'
+  _globals['_STORESKEY']._serialized_start=53
+  _globals['_STORESKEY']._serialized_end=80
+  _globals['_STORESVALUE']._serialized_start=82
+  _globals['_STORESVALUE']._serialized_end=110
+  _globals['_STORESSETOPTIONS']._serialized_start=112
+  _globals['_STORESSETOPTIONS']._serialized_end=202
+  _globals['_STORESDELETEOPTIONS']._serialized_start=204
+  _globals['_STORESDELETEOPTIONS']._serialized_end=259
+  _globals['_STORESGETOPTIONS']._serialized_start=261
+  _globals['_STORESGETOPTIONS']._serialized_end=313
+  _globals['_STORESGETRESULT']._serialized_start=315
+  _globals['_STORESGETRESULT']._serialized_end=404
+  _globals['_STORESFINDOPTIONS']._serialized_start=406
+  _globals['_STORESFINDOPTIONS']._serialized_end=472
+  _globals['_STORESFINDRESULT']._serialized_start=474
+  _globals['_STORESFINDRESULT']._serialized_end=586
+  _globals['_HEALTHMESSAGE']._serialized_start=588
+  _globals['_HEALTHMESSAGE']._serialized_end=603
+  _globals['_PREDICTOPTIONS']._serialized_start=606
+  _globals['_PREDICTOPTIONS']._serialized_end=1478
+  _globals['_REPLY']._serialized_start=1480
+  _globals['_REPLY']._serialized_end=1504
+  _globals['_MODELOPTIONS']._serialized_start=1507
+  _globals['_MODELOPTIONS']._serialized_end=2579
+  _globals['_RESULT']._serialized_start=2581
+  _globals['_RESULT']._serialized_end=2623
+  _globals['_EMBEDDINGRESULT']._serialized_start=2625
+  _globals['_EMBEDDINGRESULT']._serialized_end=2662
+  _globals['_TRANSCRIPTREQUEST']._serialized_start=2664
+  _globals['_TRANSCRIPTREQUEST']._serialized_end=2731
+  _globals['_TRANSCRIPTRESULT']._serialized_start=2733
+  _globals['_TRANSCRIPTRESULT']._serialized_end=2811
+  _globals['_TRANSCRIPTSEGMENT']._serialized_start=2813
+  _globals['_TRANSCRIPTSEGMENT']._serialized_end=2902
+  _globals['_GENERATEIMAGEREQUEST']._serialized_start=2905
+  _globals['_GENERATEIMAGEREQUEST']._serialized_end=3120
+  _globals['_TTSREQUEST']._serialized_start=3122
+  _globals['_TTSREQUEST']._serialized_end=3191
+  _globals['_TOKENIZATIONRESPONSE']._serialized_start=3193
+  _globals['_TOKENIZATIONRESPONSE']._serialized_end=3247
+  _globals['_MEMORYUSAGEDATA']._serialized_start=3250
+  _globals['_MEMORYUSAGEDATA']._serialized_end=3392
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_start=3344
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_end=3392
+  _globals['_STATUSRESPONSE']._serialized_start=3395
+  _globals['_STATUSRESPONSE']._serialized_end=3568
+  _globals['_STATUSRESPONSE_STATE']._serialized_start=3501
+  _globals['_STATUSRESPONSE_STATE']._serialized_end=3568
+  _globals['_MESSAGE']._serialized_start=3570
+  _globals['_MESSAGE']._serialized_end=3632
+  _globals['_BACKEND']._serialized_start=3635
+  _globals['_BACKEND']._serialized_end=4526
 # @@protoc_insertion_point(module_scope)
diff --git a/backend/python/exllama/backend_pb2_grpc.py b/backend/python/exllama/backend_pb2_grpc.py
index 79a7677fb27f..e06fccf3d451 100644
--- a/backend/python/exllama/backend_pb2_grpc.py
+++ b/backend/python/exllama/backend_pb2_grpc.py
@@ -64,6 +64,26 @@ def __init__(self, channel):
                 request_serializer=backend__pb2.HealthMessage.SerializeToString,
                 response_deserializer=backend__pb2.StatusResponse.FromString,
                 )
+        self.StoresSet = channel.unary_unary(
+                '/backend.Backend/StoresSet',
+                request_serializer=backend__pb2.StoresSetOptions.SerializeToString,
+                response_deserializer=backend__pb2.Result.FromString,
+                )
+        self.StoresDelete = channel.unary_unary(
+                '/backend.Backend/StoresDelete',
+                request_serializer=backend__pb2.StoresDeleteOptions.SerializeToString,
+                response_deserializer=backend__pb2.Result.FromString,
+                )
+        self.StoresGet = channel.unary_unary(
+                '/backend.Backend/StoresGet',
+                request_serializer=backend__pb2.StoresGetOptions.SerializeToString,
+                response_deserializer=backend__pb2.StoresGetResult.FromString,
+                )
+        self.StoresFind = channel.unary_unary(
+                '/backend.Backend/StoresFind',
+                request_serializer=backend__pb2.StoresFindOptions.SerializeToString,
+                response_deserializer=backend__pb2.StoresFindResult.FromString,
+                )
 
 
 class BackendServicer(object):
@@ -129,6 +149,30 @@ def Status(self, request, context):
         context.set_details('Method not implemented!')
         raise NotImplementedError('Method not implemented!')
 
+    def StoresSet(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresDelete(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresGet(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresFind(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
 
 def add_BackendServicer_to_server(servicer, server):
     rpc_method_handlers = {
@@ -182,6 +226,26 @@ def add_BackendServicer_to_server(servicer, server):
                     request_deserializer=backend__pb2.HealthMessage.FromString,
                     response_serializer=backend__pb2.StatusResponse.SerializeToString,
             ),
+            'StoresSet': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresSet,
+                    request_deserializer=backend__pb2.StoresSetOptions.FromString,
+                    response_serializer=backend__pb2.Result.SerializeToString,
+            ),
+            'StoresDelete': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresDelete,
+                    request_deserializer=backend__pb2.StoresDeleteOptions.FromString,
+                    response_serializer=backend__pb2.Result.SerializeToString,
+            ),
+            'StoresGet': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresGet,
+                    request_deserializer=backend__pb2.StoresGetOptions.FromString,
+                    response_serializer=backend__pb2.StoresGetResult.SerializeToString,
+            ),
+            'StoresFind': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresFind,
+                    request_deserializer=backend__pb2.StoresFindOptions.FromString,
+                    response_serializer=backend__pb2.StoresFindResult.SerializeToString,
+            ),
     }
     generic_handler = grpc.method_handlers_generic_handler(
             'backend.Backend', rpc_method_handlers)
@@ -361,3 +425,71 @@ def Status(request,
             backend__pb2.StatusResponse.FromString,
             options, channel_credentials,
             insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresSet(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresSet',
+            backend__pb2.StoresSetOptions.SerializeToString,
+            backend__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresDelete(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresDelete',
+            backend__pb2.StoresDeleteOptions.SerializeToString,
+            backend__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresGet(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresGet',
+            backend__pb2.StoresGetOptions.SerializeToString,
+            backend__pb2.StoresGetResult.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresFind(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresFind',
+            backend__pb2.StoresFindOptions.SerializeToString,
+            backend__pb2.StoresFindResult.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
diff --git a/backend/python/exllama2/backend_pb2.py b/backend/python/exllama2/backend_pb2.py
index 08b896c7cad5..8d366c16d63b 100644
--- a/backend/python/exllama2/backend_pb2.py
+++ b/backend/python/exllama2/backend_pb2.py
@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 # Generated by the protocol buffer compiler.  DO NOT EDIT!
 # source: backend.proto
+# Protobuf Python Version: 4.25.1
 """Generated protocol buffer code."""
 from google.protobuf import descriptor as _descriptor
 from google.protobuf import descriptor_pool as _descriptor_pool
@@ -11,51 +12,69 @@
 _sym_db = _symbol_database.Default()
 
 
+from google.protobuf import any_pb2 as google_dot_protobuf_dot_any__pb2
 
 
-DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\rbackend.proto\x12\x07\x62\x61\x63kend\"\x0f\n\rHealthMessage\"\xa6\x06\n\x0ePredictOptions\x12\x0e\n\x06Prompt\x18\x01 \x01(\t\x12\x0c\n\x04Seed\x18\x02 \x01(\x05\x12\x0f\n\x07Threads\x18\x03 \x01(\x05\x12\x0e\n\x06Tokens\x18\x04 \x01(\x05\x12\x0c\n\x04TopK\x18\x05 \x01(\x05\x12\x0e\n\x06Repeat\x18\x06 \x01(\x05\x12\r\n\x05\x42\x61tch\x18\x07 \x01(\x05\x12\r\n\x05NKeep\x18\x08 \x01(\x05\x12\x13\n\x0bTemperature\x18\t \x01(\x02\x12\x0f\n\x07Penalty\x18\n \x01(\x02\x12\r\n\x05\x46\x31\x36KV\x18\x0b \x01(\x08\x12\x11\n\tDebugMode\x18\x0c \x01(\x08\x12\x13\n\x0bStopPrompts\x18\r \x03(\t\x12\x11\n\tIgnoreEOS\x18\x0e \x01(\x08\x12\x19\n\x11TailFreeSamplingZ\x18\x0f \x01(\x02\x12\x10\n\x08TypicalP\x18\x10 \x01(\x02\x12\x18\n\x10\x46requencyPenalty\x18\x11 \x01(\x02\x12\x17\n\x0fPresencePenalty\x18\x12 \x01(\x02\x12\x10\n\x08Mirostat\x18\x13 \x01(\x05\x12\x13\n\x0bMirostatETA\x18\x14 \x01(\x02\x12\x13\n\x0bMirostatTAU\x18\x15 \x01(\x02\x12\x12\n\nPenalizeNL\x18\x16 \x01(\x08\x12\x11\n\tLogitBias\x18\x17 \x01(\t\x12\r\n\x05MLock\x18\x19 \x01(\x08\x12\x0c\n\x04MMap\x18\x1a \x01(\x08\x12\x16\n\x0ePromptCacheAll\x18\x1b \x01(\x08\x12\x15\n\rPromptCacheRO\x18\x1c \x01(\x08\x12\x0f\n\x07Grammar\x18\x1d \x01(\t\x12\x0f\n\x07MainGPU\x18\x1e \x01(\t\x12\x13\n\x0bTensorSplit\x18\x1f \x01(\t\x12\x0c\n\x04TopP\x18  \x01(\x02\x12\x17\n\x0fPromptCachePath\x18! \x01(\t\x12\r\n\x05\x44\x65\x62ug\x18\" \x01(\x08\x12\x17\n\x0f\x45mbeddingTokens\x18# \x03(\x05\x12\x12\n\nEmbeddings\x18$ \x01(\t\x12\x14\n\x0cRopeFreqBase\x18% \x01(\x02\x12\x15\n\rRopeFreqScale\x18& \x01(\x02\x12\x1b\n\x13NegativePromptScale\x18\' \x01(\x02\x12\x16\n\x0eNegativePrompt\x18( \x01(\t\x12\x0e\n\x06NDraft\x18) \x01(\x05\x12\x0e\n\x06Images\x18* \x03(\t\"\x18\n\x05Reply\x12\x0f\n\x07message\x18\x01 \x01(\x0c\"\xb0\x08\n\x0cModelOptions\x12\r\n\x05Model\x18\x01 \x01(\t\x12\x13\n\x0b\x43ontextSize\x18\x02 \x01(\x05\x12\x0c\n\x04Seed\x18\x03 \x01(\x05\x12\x0e\n\x06NBatch\x18\x04 \x01(\x05\x12\x11\n\tF16Memory\x18\x05 \x01(\x08\x12\r\n\x05MLock\x18\x06 \x01(\x08\x12\x0c\n\x04MMap\x18\x07 \x01(\x08\x12\x11\n\tVocabOnly\x18\x08 \x01(\x08\x12\x0f\n\x07LowVRAM\x18\t \x01(\x08\x12\x12\n\nEmbeddings\x18\n \x01(\x08\x12\x0c\n\x04NUMA\x18\x0b \x01(\x08\x12\x12\n\nNGPULayers\x18\x0c \x01(\x05\x12\x0f\n\x07MainGPU\x18\r \x01(\t\x12\x13\n\x0bTensorSplit\x18\x0e \x01(\t\x12\x0f\n\x07Threads\x18\x0f \x01(\x05\x12\x19\n\x11LibrarySearchPath\x18\x10 \x01(\t\x12\x14\n\x0cRopeFreqBase\x18\x11 \x01(\x02\x12\x15\n\rRopeFreqScale\x18\x12 \x01(\x02\x12\x12\n\nRMSNormEps\x18\x13 \x01(\x02\x12\x0c\n\x04NGQA\x18\x14 \x01(\x05\x12\x11\n\tModelFile\x18\x15 \x01(\t\x12\x0e\n\x06\x44\x65vice\x18\x16 \x01(\t\x12\x11\n\tUseTriton\x18\x17 \x01(\x08\x12\x15\n\rModelBaseName\x18\x18 \x01(\t\x12\x18\n\x10UseFastTokenizer\x18\x19 \x01(\x08\x12\x14\n\x0cPipelineType\x18\x1a \x01(\t\x12\x15\n\rSchedulerType\x18\x1b \x01(\t\x12\x0c\n\x04\x43UDA\x18\x1c \x01(\x08\x12\x10\n\x08\x43\x46GScale\x18\x1d \x01(\x02\x12\x0f\n\x07IMG2IMG\x18\x1e \x01(\x08\x12\x11\n\tCLIPModel\x18\x1f \x01(\t\x12\x15\n\rCLIPSubfolder\x18  \x01(\t\x12\x10\n\x08\x43LIPSkip\x18! \x01(\x05\x12\x12\n\nControlNet\x18\x30 \x01(\t\x12\x11\n\tTokenizer\x18\" \x01(\t\x12\x10\n\x08LoraBase\x18# \x01(\t\x12\x13\n\x0bLoraAdapter\x18$ \x01(\t\x12\x11\n\tLoraScale\x18* \x01(\x02\x12\x11\n\tNoMulMatQ\x18% \x01(\x08\x12\x12\n\nDraftModel\x18\' \x01(\t\x12\x11\n\tAudioPath\x18& \x01(\t\x12\x14\n\x0cQuantization\x18( \x01(\t\x12\x1c\n\x14GPUMemoryUtilization\x18\x32 \x01(\x02\x12\x17\n\x0fTrustRemoteCode\x18\x33 \x01(\x08\x12\x14\n\x0c\x45nforceEager\x18\x34 \x01(\x08\x12\x11\n\tSwapSpace\x18\x35 \x01(\x05\x12\x13\n\x0bMaxModelLen\x18\x36 \x01(\x05\x12\x0e\n\x06MMProj\x18) \x01(\t\x12\x13\n\x0bRopeScaling\x18+ \x01(\t\x12\x15\n\rYarnExtFactor\x18, \x01(\x02\x12\x16\n\x0eYarnAttnFactor\x18- \x01(\x02\x12\x14\n\x0cYarnBetaFast\x18. \x01(\x02\x12\x14\n\x0cYarnBetaSlow\x18/ \x01(\x02\x12\x0c\n\x04Type\x18\x31 \x01(\t\"*\n\x06Result\x12\x0f\n\x07message\x18\x01 \x01(\t\x12\x0f\n\x07success\x18\x02 \x01(\x08\"%\n\x0f\x45mbeddingResult\x12\x12\n\nembeddings\x18\x01 \x03(\x02\"C\n\x11TranscriptRequest\x12\x0b\n\x03\x64st\x18\x02 \x01(\t\x12\x10\n\x08language\x18\x03 \x01(\t\x12\x0f\n\x07threads\x18\x04 \x01(\r\"N\n\x10TranscriptResult\x12,\n\x08segments\x18\x01 \x03(\x0b\x32\x1a.backend.TranscriptSegment\x12\x0c\n\x04text\x18\x02 \x01(\t\"Y\n\x11TranscriptSegment\x12\n\n\x02id\x18\x01 \x01(\x05\x12\r\n\x05start\x18\x02 \x01(\x03\x12\x0b\n\x03\x65nd\x18\x03 \x01(\x03\x12\x0c\n\x04text\x18\x04 \x01(\t\x12\x0e\n\x06tokens\x18\x05 \x03(\x05\"\xd7\x01\n\x14GenerateImageRequest\x12\x0e\n\x06height\x18\x01 \x01(\x05\x12\r\n\x05width\x18\x02 \x01(\x05\x12\x0c\n\x04mode\x18\x03 \x01(\x05\x12\x0c\n\x04step\x18\x04 \x01(\x05\x12\x0c\n\x04seed\x18\x05 \x01(\x05\x12\x17\n\x0fpositive_prompt\x18\x06 \x01(\t\x12\x17\n\x0fnegative_prompt\x18\x07 \x01(\t\x12\x0b\n\x03\x64st\x18\x08 \x01(\t\x12\x0b\n\x03src\x18\t \x01(\t\x12\x18\n\x10\x45nableParameters\x18\n \x01(\t\x12\x10\n\x08\x43LIPSkip\x18\x0b \x01(\x05\"E\n\nTTSRequest\x12\x0c\n\x04text\x18\x01 \x01(\t\x12\r\n\x05model\x18\x02 \x01(\t\x12\x0b\n\x03\x64st\x18\x03 \x01(\t\x12\r\n\x05voice\x18\x04 \x01(\t\"6\n\x14TokenizationResponse\x12\x0e\n\x06length\x18\x01 \x01(\x05\x12\x0e\n\x06tokens\x18\x02 \x03(\x05\"\x8e\x01\n\x0fMemoryUsageData\x12\r\n\x05total\x18\x01 \x01(\x04\x12:\n\tbreakdown\x18\x02 \x03(\x0b\x32\'.backend.MemoryUsageData.BreakdownEntry\x1a\x30\n\x0e\x42reakdownEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\x04:\x02\x38\x01\"\xad\x01\n\x0eStatusResponse\x12,\n\x05state\x18\x01 \x01(\x0e\x32\x1d.backend.StatusResponse.State\x12(\n\x06memory\x18\x02 \x01(\x0b\x32\x18.backend.MemoryUsageData\"C\n\x05State\x12\x11\n\rUNINITIALIZED\x10\x00\x12\x08\n\x04\x42USY\x10\x01\x12\t\n\x05READY\x10\x02\x12\x12\n\x05\x45RROR\x10\xff\xff\xff\xff\xff\xff\xff\xff\xff\x01\x32\xf4\x04\n\x07\x42\x61\x63kend\x12\x32\n\x06Health\x12\x16.backend.HealthMessage\x1a\x0e.backend.Reply\"\x00\x12\x34\n\x07Predict\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x12\x35\n\tLoadModel\x12\x15.backend.ModelOptions\x1a\x0f.backend.Result\"\x00\x12<\n\rPredictStream\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x30\x01\x12@\n\tEmbedding\x12\x17.backend.PredictOptions\x1a\x18.backend.EmbeddingResult\"\x00\x12\x41\n\rGenerateImage\x12\x1d.backend.GenerateImageRequest\x1a\x0f.backend.Result\"\x00\x12M\n\x12\x41udioTranscription\x12\x1a.backend.TranscriptRequest\x1a\x19.backend.TranscriptResult\"\x00\x12-\n\x03TTS\x12\x13.backend.TTSRequest\x1a\x0f.backend.Result\"\x00\x12J\n\x0eTokenizeString\x12\x17.backend.PredictOptions\x1a\x1d.backend.TokenizationResponse\"\x00\x12;\n\x06Status\x12\x16.backend.HealthMessage\x1a\x17.backend.StatusResponse\"\x00\x42Z\n\x19io.skynet.localai.backendB\x0eLocalAIBackendP\x01Z+github.com/go-skynet/LocalAI/pkg/grpc/protob\x06proto3')
+DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\rbackend.proto\x12\x07\x62\x61\x63kend\x1a\x19google/protobuf/any.proto\"\x1b\n\tStoresKey\x12\x0e\n\x06\x46loats\x18\x01 \x03(\x02\"\x1c\n\x0bStoresValue\x12\r\n\x05\x42ytes\x18\x01 \x01(\x0c\"Z\n\x10StoresSetOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\"7\n\x13StoresDeleteOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\"4\n\x10StoresGetOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\"Y\n\x0fStoresGetResult\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\"B\n\x11StoresFindOptions\x12\x1f\n\x03Key\x18\x01 \x01(\x0b\x32\x12.backend.StoresKey\x12\x0c\n\x04TopK\x18\x02 \x01(\x05\"p\n\x10StoresFindResult\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\x12\x14\n\x0cSimilarities\x18\x03 \x03(\x02\"\x0f\n\rHealthMessage\"\xe8\x06\n\x0ePredictOptions\x12\x0e\n\x06Prompt\x18\x01 \x01(\t\x12\x0c\n\x04Seed\x18\x02 \x01(\x05\x12\x0f\n\x07Threads\x18\x03 \x01(\x05\x12\x0e\n\x06Tokens\x18\x04 \x01(\x05\x12\x0c\n\x04TopK\x18\x05 \x01(\x05\x12\x0e\n\x06Repeat\x18\x06 \x01(\x05\x12\r\n\x05\x42\x61tch\x18\x07 \x01(\x05\x12\r\n\x05NKeep\x18\x08 \x01(\x05\x12\x13\n\x0bTemperature\x18\t \x01(\x02\x12\x0f\n\x07Penalty\x18\n \x01(\x02\x12\r\n\x05\x46\x31\x36KV\x18\x0b \x01(\x08\x12\x11\n\tDebugMode\x18\x0c \x01(\x08\x12\x13\n\x0bStopPrompts\x18\r \x03(\t\x12\x11\n\tIgnoreEOS\x18\x0e \x01(\x08\x12\x19\n\x11TailFreeSamplingZ\x18\x0f \x01(\x02\x12\x10\n\x08TypicalP\x18\x10 \x01(\x02\x12\x18\n\x10\x46requencyPenalty\x18\x11 \x01(\x02\x12\x17\n\x0fPresencePenalty\x18\x12 \x01(\x02\x12\x10\n\x08Mirostat\x18\x13 \x01(\x05\x12\x13\n\x0bMirostatETA\x18\x14 \x01(\x02\x12\x13\n\x0bMirostatTAU\x18\x15 \x01(\x02\x12\x12\n\nPenalizeNL\x18\x16 \x01(\x08\x12\x11\n\tLogitBias\x18\x17 \x01(\t\x12\r\n\x05MLock\x18\x19 \x01(\x08\x12\x0c\n\x04MMap\x18\x1a \x01(\x08\x12\x16\n\x0ePromptCacheAll\x18\x1b \x01(\x08\x12\x15\n\rPromptCacheRO\x18\x1c \x01(\x08\x12\x0f\n\x07Grammar\x18\x1d \x01(\t\x12\x0f\n\x07MainGPU\x18\x1e \x01(\t\x12\x13\n\x0bTensorSplit\x18\x1f \x01(\t\x12\x0c\n\x04TopP\x18  \x01(\x02\x12\x17\n\x0fPromptCachePath\x18! \x01(\t\x12\r\n\x05\x44\x65\x62ug\x18\" \x01(\x08\x12\x17\n\x0f\x45mbeddingTokens\x18# \x03(\x05\x12\x12\n\nEmbeddings\x18$ \x01(\t\x12\x14\n\x0cRopeFreqBase\x18% \x01(\x02\x12\x15\n\rRopeFreqScale\x18& \x01(\x02\x12\x1b\n\x13NegativePromptScale\x18\' \x01(\x02\x12\x16\n\x0eNegativePrompt\x18( \x01(\t\x12\x0e\n\x06NDraft\x18) \x01(\x05\x12\x0e\n\x06Images\x18* \x03(\t\x12\x1c\n\x14UseTokenizerTemplate\x18+ \x01(\x08\x12\"\n\x08Messages\x18, \x03(\x0b\x32\x10.backend.Message\"\x18\n\x05Reply\x12\x0f\n\x07message\x18\x01 \x01(\x0c\"\xb0\x08\n\x0cModelOptions\x12\r\n\x05Model\x18\x01 \x01(\t\x12\x13\n\x0b\x43ontextSize\x18\x02 \x01(\x05\x12\x0c\n\x04Seed\x18\x03 \x01(\x05\x12\x0e\n\x06NBatch\x18\x04 \x01(\x05\x12\x11\n\tF16Memory\x18\x05 \x01(\x08\x12\r\n\x05MLock\x18\x06 \x01(\x08\x12\x0c\n\x04MMap\x18\x07 \x01(\x08\x12\x11\n\tVocabOnly\x18\x08 \x01(\x08\x12\x0f\n\x07LowVRAM\x18\t \x01(\x08\x12\x12\n\nEmbeddings\x18\n \x01(\x08\x12\x0c\n\x04NUMA\x18\x0b \x01(\x08\x12\x12\n\nNGPULayers\x18\x0c \x01(\x05\x12\x0f\n\x07MainGPU\x18\r \x01(\t\x12\x13\n\x0bTensorSplit\x18\x0e \x01(\t\x12\x0f\n\x07Threads\x18\x0f \x01(\x05\x12\x19\n\x11LibrarySearchPath\x18\x10 \x01(\t\x12\x14\n\x0cRopeFreqBase\x18\x11 \x01(\x02\x12\x15\n\rRopeFreqScale\x18\x12 \x01(\x02\x12\x12\n\nRMSNormEps\x18\x13 \x01(\x02\x12\x0c\n\x04NGQA\x18\x14 \x01(\x05\x12\x11\n\tModelFile\x18\x15 \x01(\t\x12\x0e\n\x06\x44\x65vice\x18\x16 \x01(\t\x12\x11\n\tUseTriton\x18\x17 \x01(\x08\x12\x15\n\rModelBaseName\x18\x18 \x01(\t\x12\x18\n\x10UseFastTokenizer\x18\x19 \x01(\x08\x12\x14\n\x0cPipelineType\x18\x1a \x01(\t\x12\x15\n\rSchedulerType\x18\x1b \x01(\t\x12\x0c\n\x04\x43UDA\x18\x1c \x01(\x08\x12\x10\n\x08\x43\x46GScale\x18\x1d \x01(\x02\x12\x0f\n\x07IMG2IMG\x18\x1e \x01(\x08\x12\x11\n\tCLIPModel\x18\x1f \x01(\t\x12\x15\n\rCLIPSubfolder\x18  \x01(\t\x12\x10\n\x08\x43LIPSkip\x18! \x01(\x05\x12\x12\n\nControlNet\x18\x30 \x01(\t\x12\x11\n\tTokenizer\x18\" \x01(\t\x12\x10\n\x08LoraBase\x18# \x01(\t\x12\x13\n\x0bLoraAdapter\x18$ \x01(\t\x12\x11\n\tLoraScale\x18* \x01(\x02\x12\x11\n\tNoMulMatQ\x18% \x01(\x08\x12\x12\n\nDraftModel\x18\' \x01(\t\x12\x11\n\tAudioPath\x18& \x01(\t\x12\x14\n\x0cQuantization\x18( \x01(\t\x12\x1c\n\x14GPUMemoryUtilization\x18\x32 \x01(\x02\x12\x17\n\x0fTrustRemoteCode\x18\x33 \x01(\x08\x12\x14\n\x0c\x45nforceEager\x18\x34 \x01(\x08\x12\x11\n\tSwapSpace\x18\x35 \x01(\x05\x12\x13\n\x0bMaxModelLen\x18\x36 \x01(\x05\x12\x0e\n\x06MMProj\x18) \x01(\t\x12\x13\n\x0bRopeScaling\x18+ \x01(\t\x12\x15\n\rYarnExtFactor\x18, \x01(\x02\x12\x16\n\x0eYarnAttnFactor\x18- \x01(\x02\x12\x14\n\x0cYarnBetaFast\x18. \x01(\x02\x12\x14\n\x0cYarnBetaSlow\x18/ \x01(\x02\x12\x0c\n\x04Type\x18\x31 \x01(\t\"*\n\x06Result\x12\x0f\n\x07message\x18\x01 \x01(\t\x12\x0f\n\x07success\x18\x02 \x01(\x08\"%\n\x0f\x45mbeddingResult\x12\x12\n\nembeddings\x18\x01 \x03(\x02\"C\n\x11TranscriptRequest\x12\x0b\n\x03\x64st\x18\x02 \x01(\t\x12\x10\n\x08language\x18\x03 \x01(\t\x12\x0f\n\x07threads\x18\x04 \x01(\r\"N\n\x10TranscriptResult\x12,\n\x08segments\x18\x01 \x03(\x0b\x32\x1a.backend.TranscriptSegment\x12\x0c\n\x04text\x18\x02 \x01(\t\"Y\n\x11TranscriptSegment\x12\n\n\x02id\x18\x01 \x01(\x05\x12\r\n\x05start\x18\x02 \x01(\x03\x12\x0b\n\x03\x65nd\x18\x03 \x01(\x03\x12\x0c\n\x04text\x18\x04 \x01(\t\x12\x0e\n\x06tokens\x18\x05 \x03(\x05\"\xd7\x01\n\x14GenerateImageRequest\x12\x0e\n\x06height\x18\x01 \x01(\x05\x12\r\n\x05width\x18\x02 \x01(\x05\x12\x0c\n\x04mode\x18\x03 \x01(\x05\x12\x0c\n\x04step\x18\x04 \x01(\x05\x12\x0c\n\x04seed\x18\x05 \x01(\x05\x12\x17\n\x0fpositive_prompt\x18\x06 \x01(\t\x12\x17\n\x0fnegative_prompt\x18\x07 \x01(\t\x12\x0b\n\x03\x64st\x18\x08 \x01(\t\x12\x0b\n\x03src\x18\t \x01(\t\x12\x18\n\x10\x45nableParameters\x18\n \x01(\t\x12\x10\n\x08\x43LIPSkip\x18\x0b \x01(\x05\"E\n\nTTSRequest\x12\x0c\n\x04text\x18\x01 \x01(\t\x12\r\n\x05model\x18\x02 \x01(\t\x12\x0b\n\x03\x64st\x18\x03 \x01(\t\x12\r\n\x05voice\x18\x04 \x01(\t\"6\n\x14TokenizationResponse\x12\x0e\n\x06length\x18\x01 \x01(\x05\x12\x0e\n\x06tokens\x18\x02 \x03(\x05\"\x8e\x01\n\x0fMemoryUsageData\x12\r\n\x05total\x18\x01 \x01(\x04\x12:\n\tbreakdown\x18\x02 \x03(\x0b\x32\'.backend.MemoryUsageData.BreakdownEntry\x1a\x30\n\x0e\x42reakdownEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\x04:\x02\x38\x01\"\xad\x01\n\x0eStatusResponse\x12,\n\x05state\x18\x01 \x01(\x0e\x32\x1d.backend.StatusResponse.State\x12(\n\x06memory\x18\x02 \x01(\x0b\x32\x18.backend.MemoryUsageData\"C\n\x05State\x12\x11\n\rUNINITIALIZED\x10\x00\x12\x08\n\x04\x42USY\x10\x01\x12\t\n\x05READY\x10\x02\x12\x12\n\x05\x45RROR\x10\xff\xff\xff\xff\xff\xff\xff\xff\xff\x01\">\n\x07Message\x12\x0c\n\x04Role\x18\x01 \x01(\t\x12%\n\x07\x43ontent\x18\x02 \x01(\x0b\x32\x14.google.protobuf.Any2\xfb\x06\n\x07\x42\x61\x63kend\x12\x32\n\x06Health\x12\x16.backend.HealthMessage\x1a\x0e.backend.Reply\"\x00\x12\x34\n\x07Predict\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x12\x35\n\tLoadModel\x12\x15.backend.ModelOptions\x1a\x0f.backend.Result\"\x00\x12<\n\rPredictStream\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x30\x01\x12@\n\tEmbedding\x12\x17.backend.PredictOptions\x1a\x18.backend.EmbeddingResult\"\x00\x12\x41\n\rGenerateImage\x12\x1d.backend.GenerateImageRequest\x1a\x0f.backend.Result\"\x00\x12M\n\x12\x41udioTranscription\x12\x1a.backend.TranscriptRequest\x1a\x19.backend.TranscriptResult\"\x00\x12-\n\x03TTS\x12\x13.backend.TTSRequest\x1a\x0f.backend.Result\"\x00\x12J\n\x0eTokenizeString\x12\x17.backend.PredictOptions\x1a\x1d.backend.TokenizationResponse\"\x00\x12;\n\x06Status\x12\x16.backend.HealthMessage\x1a\x17.backend.StatusResponse\"\x00\x12\x39\n\tStoresSet\x12\x19.backend.StoresSetOptions\x1a\x0f.backend.Result\"\x00\x12?\n\x0cStoresDelete\x12\x1c.backend.StoresDeleteOptions\x1a\x0f.backend.Result\"\x00\x12\x42\n\tStoresGet\x12\x19.backend.StoresGetOptions\x1a\x18.backend.StoresGetResult\"\x00\x12\x45\n\nStoresFind\x12\x1a.backend.StoresFindOptions\x1a\x19.backend.StoresFindResult\"\x00\x42Z\n\x19io.skynet.localai.backendB\x0eLocalAIBackendP\x01Z+github.com/go-skynet/LocalAI/pkg/grpc/protob\x06proto3')
 
 _globals = globals()
 _builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, _globals)
 _builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, 'backend_pb2', _globals)
 if _descriptor._USE_C_DESCRIPTORS == False:
-
-  DESCRIPTOR._options = None
-  DESCRIPTOR._serialized_options = b'\n\031io.skynet.localai.backendB\016LocalAIBackendP\001Z+github.com/go-skynet/LocalAI/pkg/grpc/proto'
-  _MEMORYUSAGEDATA_BREAKDOWNENTRY._options = None
-  _MEMORYUSAGEDATA_BREAKDOWNENTRY._serialized_options = b'8\001'
-  _globals['_HEALTHMESSAGE']._serialized_start=26
-  _globals['_HEALTHMESSAGE']._serialized_end=41
-  _globals['_PREDICTOPTIONS']._serialized_start=44
-  _globals['_PREDICTOPTIONS']._serialized_end=850
-  _globals['_REPLY']._serialized_start=852
-  _globals['_REPLY']._serialized_end=876
-  _globals['_MODELOPTIONS']._serialized_start=879
-  _globals['_MODELOPTIONS']._serialized_end=1951
-  _globals['_RESULT']._serialized_start=1953
-  _globals['_RESULT']._serialized_end=1995
-  _globals['_EMBEDDINGRESULT']._serialized_start=1997
-  _globals['_EMBEDDINGRESULT']._serialized_end=2034
-  _globals['_TRANSCRIPTREQUEST']._serialized_start=2036
-  _globals['_TRANSCRIPTREQUEST']._serialized_end=2103
-  _globals['_TRANSCRIPTRESULT']._serialized_start=2105
-  _globals['_TRANSCRIPTRESULT']._serialized_end=2183
-  _globals['_TRANSCRIPTSEGMENT']._serialized_start=2185
-  _globals['_TRANSCRIPTSEGMENT']._serialized_end=2274
-  _globals['_GENERATEIMAGEREQUEST']._serialized_start=2277
-  _globals['_GENERATEIMAGEREQUEST']._serialized_end=2492
-  _globals['_TTSREQUEST']._serialized_start=2494
-  _globals['_TTSREQUEST']._serialized_end=2563
-  _globals['_TOKENIZATIONRESPONSE']._serialized_start=2565
-  _globals['_TOKENIZATIONRESPONSE']._serialized_end=2619
-  _globals['_MEMORYUSAGEDATA']._serialized_start=2622
-  _globals['_MEMORYUSAGEDATA']._serialized_end=2764
-  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_start=2716
-  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_end=2764
-  _globals['_STATUSRESPONSE']._serialized_start=2767
-  _globals['_STATUSRESPONSE']._serialized_end=2940
-  _globals['_STATUSRESPONSE_STATE']._serialized_start=2873
-  _globals['_STATUSRESPONSE_STATE']._serialized_end=2940
-  _globals['_BACKEND']._serialized_start=2943
-  _globals['_BACKEND']._serialized_end=3571
+  _globals['DESCRIPTOR']._options = None
+  _globals['DESCRIPTOR']._serialized_options = b'\n\031io.skynet.localai.backendB\016LocalAIBackendP\001Z+github.com/go-skynet/LocalAI/pkg/grpc/proto'
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._options = None
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_options = b'8\001'
+  _globals['_STORESKEY']._serialized_start=53
+  _globals['_STORESKEY']._serialized_end=80
+  _globals['_STORESVALUE']._serialized_start=82
+  _globals['_STORESVALUE']._serialized_end=110
+  _globals['_STORESSETOPTIONS']._serialized_start=112
+  _globals['_STORESSETOPTIONS']._serialized_end=202
+  _globals['_STORESDELETEOPTIONS']._serialized_start=204
+  _globals['_STORESDELETEOPTIONS']._serialized_end=259
+  _globals['_STORESGETOPTIONS']._serialized_start=261
+  _globals['_STORESGETOPTIONS']._serialized_end=313
+  _globals['_STORESGETRESULT']._serialized_start=315
+  _globals['_STORESGETRESULT']._serialized_end=404
+  _globals['_STORESFINDOPTIONS']._serialized_start=406
+  _globals['_STORESFINDOPTIONS']._serialized_end=472
+  _globals['_STORESFINDRESULT']._serialized_start=474
+  _globals['_STORESFINDRESULT']._serialized_end=586
+  _globals['_HEALTHMESSAGE']._serialized_start=588
+  _globals['_HEALTHMESSAGE']._serialized_end=603
+  _globals['_PREDICTOPTIONS']._serialized_start=606
+  _globals['_PREDICTOPTIONS']._serialized_end=1478
+  _globals['_REPLY']._serialized_start=1480
+  _globals['_REPLY']._serialized_end=1504
+  _globals['_MODELOPTIONS']._serialized_start=1507
+  _globals['_MODELOPTIONS']._serialized_end=2579
+  _globals['_RESULT']._serialized_start=2581
+  _globals['_RESULT']._serialized_end=2623
+  _globals['_EMBEDDINGRESULT']._serialized_start=2625
+  _globals['_EMBEDDINGRESULT']._serialized_end=2662
+  _globals['_TRANSCRIPTREQUEST']._serialized_start=2664
+  _globals['_TRANSCRIPTREQUEST']._serialized_end=2731
+  _globals['_TRANSCRIPTRESULT']._serialized_start=2733
+  _globals['_TRANSCRIPTRESULT']._serialized_end=2811
+  _globals['_TRANSCRIPTSEGMENT']._serialized_start=2813
+  _globals['_TRANSCRIPTSEGMENT']._serialized_end=2902
+  _globals['_GENERATEIMAGEREQUEST']._serialized_start=2905
+  _globals['_GENERATEIMAGEREQUEST']._serialized_end=3120
+  _globals['_TTSREQUEST']._serialized_start=3122
+  _globals['_TTSREQUEST']._serialized_end=3191
+  _globals['_TOKENIZATIONRESPONSE']._serialized_start=3193
+  _globals['_TOKENIZATIONRESPONSE']._serialized_end=3247
+  _globals['_MEMORYUSAGEDATA']._serialized_start=3250
+  _globals['_MEMORYUSAGEDATA']._serialized_end=3392
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_start=3344
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_end=3392
+  _globals['_STATUSRESPONSE']._serialized_start=3395
+  _globals['_STATUSRESPONSE']._serialized_end=3568
+  _globals['_STATUSRESPONSE_STATE']._serialized_start=3501
+  _globals['_STATUSRESPONSE_STATE']._serialized_end=3568
+  _globals['_MESSAGE']._serialized_start=3570
+  _globals['_MESSAGE']._serialized_end=3632
+  _globals['_BACKEND']._serialized_start=3635
+  _globals['_BACKEND']._serialized_end=4526
 # @@protoc_insertion_point(module_scope)
diff --git a/backend/python/exllama2/backend_pb2_grpc.py b/backend/python/exllama2/backend_pb2_grpc.py
index 79a7677fb27f..e06fccf3d451 100644
--- a/backend/python/exllama2/backend_pb2_grpc.py
+++ b/backend/python/exllama2/backend_pb2_grpc.py
@@ -64,6 +64,26 @@ def __init__(self, channel):
                 request_serializer=backend__pb2.HealthMessage.SerializeToString,
                 response_deserializer=backend__pb2.StatusResponse.FromString,
                 )
+        self.StoresSet = channel.unary_unary(
+                '/backend.Backend/StoresSet',
+                request_serializer=backend__pb2.StoresSetOptions.SerializeToString,
+                response_deserializer=backend__pb2.Result.FromString,
+                )
+        self.StoresDelete = channel.unary_unary(
+                '/backend.Backend/StoresDelete',
+                request_serializer=backend__pb2.StoresDeleteOptions.SerializeToString,
+                response_deserializer=backend__pb2.Result.FromString,
+                )
+        self.StoresGet = channel.unary_unary(
+                '/backend.Backend/StoresGet',
+                request_serializer=backend__pb2.StoresGetOptions.SerializeToString,
+                response_deserializer=backend__pb2.StoresGetResult.FromString,
+                )
+        self.StoresFind = channel.unary_unary(
+                '/backend.Backend/StoresFind',
+                request_serializer=backend__pb2.StoresFindOptions.SerializeToString,
+                response_deserializer=backend__pb2.StoresFindResult.FromString,
+                )
 
 
 class BackendServicer(object):
@@ -129,6 +149,30 @@ def Status(self, request, context):
         context.set_details('Method not implemented!')
         raise NotImplementedError('Method not implemented!')
 
+    def StoresSet(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresDelete(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresGet(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresFind(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
 
 def add_BackendServicer_to_server(servicer, server):
     rpc_method_handlers = {
@@ -182,6 +226,26 @@ def add_BackendServicer_to_server(servicer, server):
                     request_deserializer=backend__pb2.HealthMessage.FromString,
                     response_serializer=backend__pb2.StatusResponse.SerializeToString,
             ),
+            'StoresSet': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresSet,
+                    request_deserializer=backend__pb2.StoresSetOptions.FromString,
+                    response_serializer=backend__pb2.Result.SerializeToString,
+            ),
+            'StoresDelete': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresDelete,
+                    request_deserializer=backend__pb2.StoresDeleteOptions.FromString,
+                    response_serializer=backend__pb2.Result.SerializeToString,
+            ),
+            'StoresGet': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresGet,
+                    request_deserializer=backend__pb2.StoresGetOptions.FromString,
+                    response_serializer=backend__pb2.StoresGetResult.SerializeToString,
+            ),
+            'StoresFind': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresFind,
+                    request_deserializer=backend__pb2.StoresFindOptions.FromString,
+                    response_serializer=backend__pb2.StoresFindResult.SerializeToString,
+            ),
     }
     generic_handler = grpc.method_handlers_generic_handler(
             'backend.Backend', rpc_method_handlers)
@@ -361,3 +425,71 @@ def Status(request,
             backend__pb2.StatusResponse.FromString,
             options, channel_credentials,
             insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresSet(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresSet',
+            backend__pb2.StoresSetOptions.SerializeToString,
+            backend__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresDelete(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresDelete',
+            backend__pb2.StoresDeleteOptions.SerializeToString,
+            backend__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresGet(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresGet',
+            backend__pb2.StoresGetOptions.SerializeToString,
+            backend__pb2.StoresGetResult.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresFind(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresFind',
+            backend__pb2.StoresFindOptions.SerializeToString,
+            backend__pb2.StoresFindResult.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
diff --git a/backend/python/mamba/backend_pb2.py b/backend/python/mamba/backend_pb2.py
index 08b896c7cad5..8d366c16d63b 100644
--- a/backend/python/mamba/backend_pb2.py
+++ b/backend/python/mamba/backend_pb2.py
@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 # Generated by the protocol buffer compiler.  DO NOT EDIT!
 # source: backend.proto
+# Protobuf Python Version: 4.25.1
 """Generated protocol buffer code."""
 from google.protobuf import descriptor as _descriptor
 from google.protobuf import descriptor_pool as _descriptor_pool
@@ -11,51 +12,69 @@
 _sym_db = _symbol_database.Default()
 
 
+from google.protobuf import any_pb2 as google_dot_protobuf_dot_any__pb2
 
 
-DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\rbackend.proto\x12\x07\x62\x61\x63kend\"\x0f\n\rHealthMessage\"\xa6\x06\n\x0ePredictOptions\x12\x0e\n\x06Prompt\x18\x01 \x01(\t\x12\x0c\n\x04Seed\x18\x02 \x01(\x05\x12\x0f\n\x07Threads\x18\x03 \x01(\x05\x12\x0e\n\x06Tokens\x18\x04 \x01(\x05\x12\x0c\n\x04TopK\x18\x05 \x01(\x05\x12\x0e\n\x06Repeat\x18\x06 \x01(\x05\x12\r\n\x05\x42\x61tch\x18\x07 \x01(\x05\x12\r\n\x05NKeep\x18\x08 \x01(\x05\x12\x13\n\x0bTemperature\x18\t \x01(\x02\x12\x0f\n\x07Penalty\x18\n \x01(\x02\x12\r\n\x05\x46\x31\x36KV\x18\x0b \x01(\x08\x12\x11\n\tDebugMode\x18\x0c \x01(\x08\x12\x13\n\x0bStopPrompts\x18\r \x03(\t\x12\x11\n\tIgnoreEOS\x18\x0e \x01(\x08\x12\x19\n\x11TailFreeSamplingZ\x18\x0f \x01(\x02\x12\x10\n\x08TypicalP\x18\x10 \x01(\x02\x12\x18\n\x10\x46requencyPenalty\x18\x11 \x01(\x02\x12\x17\n\x0fPresencePenalty\x18\x12 \x01(\x02\x12\x10\n\x08Mirostat\x18\x13 \x01(\x05\x12\x13\n\x0bMirostatETA\x18\x14 \x01(\x02\x12\x13\n\x0bMirostatTAU\x18\x15 \x01(\x02\x12\x12\n\nPenalizeNL\x18\x16 \x01(\x08\x12\x11\n\tLogitBias\x18\x17 \x01(\t\x12\r\n\x05MLock\x18\x19 \x01(\x08\x12\x0c\n\x04MMap\x18\x1a \x01(\x08\x12\x16\n\x0ePromptCacheAll\x18\x1b \x01(\x08\x12\x15\n\rPromptCacheRO\x18\x1c \x01(\x08\x12\x0f\n\x07Grammar\x18\x1d \x01(\t\x12\x0f\n\x07MainGPU\x18\x1e \x01(\t\x12\x13\n\x0bTensorSplit\x18\x1f \x01(\t\x12\x0c\n\x04TopP\x18  \x01(\x02\x12\x17\n\x0fPromptCachePath\x18! \x01(\t\x12\r\n\x05\x44\x65\x62ug\x18\" \x01(\x08\x12\x17\n\x0f\x45mbeddingTokens\x18# \x03(\x05\x12\x12\n\nEmbeddings\x18$ \x01(\t\x12\x14\n\x0cRopeFreqBase\x18% \x01(\x02\x12\x15\n\rRopeFreqScale\x18& \x01(\x02\x12\x1b\n\x13NegativePromptScale\x18\' \x01(\x02\x12\x16\n\x0eNegativePrompt\x18( \x01(\t\x12\x0e\n\x06NDraft\x18) \x01(\x05\x12\x0e\n\x06Images\x18* \x03(\t\"\x18\n\x05Reply\x12\x0f\n\x07message\x18\x01 \x01(\x0c\"\xb0\x08\n\x0cModelOptions\x12\r\n\x05Model\x18\x01 \x01(\t\x12\x13\n\x0b\x43ontextSize\x18\x02 \x01(\x05\x12\x0c\n\x04Seed\x18\x03 \x01(\x05\x12\x0e\n\x06NBatch\x18\x04 \x01(\x05\x12\x11\n\tF16Memory\x18\x05 \x01(\x08\x12\r\n\x05MLock\x18\x06 \x01(\x08\x12\x0c\n\x04MMap\x18\x07 \x01(\x08\x12\x11\n\tVocabOnly\x18\x08 \x01(\x08\x12\x0f\n\x07LowVRAM\x18\t \x01(\x08\x12\x12\n\nEmbeddings\x18\n \x01(\x08\x12\x0c\n\x04NUMA\x18\x0b \x01(\x08\x12\x12\n\nNGPULayers\x18\x0c \x01(\x05\x12\x0f\n\x07MainGPU\x18\r \x01(\t\x12\x13\n\x0bTensorSplit\x18\x0e \x01(\t\x12\x0f\n\x07Threads\x18\x0f \x01(\x05\x12\x19\n\x11LibrarySearchPath\x18\x10 \x01(\t\x12\x14\n\x0cRopeFreqBase\x18\x11 \x01(\x02\x12\x15\n\rRopeFreqScale\x18\x12 \x01(\x02\x12\x12\n\nRMSNormEps\x18\x13 \x01(\x02\x12\x0c\n\x04NGQA\x18\x14 \x01(\x05\x12\x11\n\tModelFile\x18\x15 \x01(\t\x12\x0e\n\x06\x44\x65vice\x18\x16 \x01(\t\x12\x11\n\tUseTriton\x18\x17 \x01(\x08\x12\x15\n\rModelBaseName\x18\x18 \x01(\t\x12\x18\n\x10UseFastTokenizer\x18\x19 \x01(\x08\x12\x14\n\x0cPipelineType\x18\x1a \x01(\t\x12\x15\n\rSchedulerType\x18\x1b \x01(\t\x12\x0c\n\x04\x43UDA\x18\x1c \x01(\x08\x12\x10\n\x08\x43\x46GScale\x18\x1d \x01(\x02\x12\x0f\n\x07IMG2IMG\x18\x1e \x01(\x08\x12\x11\n\tCLIPModel\x18\x1f \x01(\t\x12\x15\n\rCLIPSubfolder\x18  \x01(\t\x12\x10\n\x08\x43LIPSkip\x18! \x01(\x05\x12\x12\n\nControlNet\x18\x30 \x01(\t\x12\x11\n\tTokenizer\x18\" \x01(\t\x12\x10\n\x08LoraBase\x18# \x01(\t\x12\x13\n\x0bLoraAdapter\x18$ \x01(\t\x12\x11\n\tLoraScale\x18* \x01(\x02\x12\x11\n\tNoMulMatQ\x18% \x01(\x08\x12\x12\n\nDraftModel\x18\' \x01(\t\x12\x11\n\tAudioPath\x18& \x01(\t\x12\x14\n\x0cQuantization\x18( \x01(\t\x12\x1c\n\x14GPUMemoryUtilization\x18\x32 \x01(\x02\x12\x17\n\x0fTrustRemoteCode\x18\x33 \x01(\x08\x12\x14\n\x0c\x45nforceEager\x18\x34 \x01(\x08\x12\x11\n\tSwapSpace\x18\x35 \x01(\x05\x12\x13\n\x0bMaxModelLen\x18\x36 \x01(\x05\x12\x0e\n\x06MMProj\x18) \x01(\t\x12\x13\n\x0bRopeScaling\x18+ \x01(\t\x12\x15\n\rYarnExtFactor\x18, \x01(\x02\x12\x16\n\x0eYarnAttnFactor\x18- \x01(\x02\x12\x14\n\x0cYarnBetaFast\x18. \x01(\x02\x12\x14\n\x0cYarnBetaSlow\x18/ \x01(\x02\x12\x0c\n\x04Type\x18\x31 \x01(\t\"*\n\x06Result\x12\x0f\n\x07message\x18\x01 \x01(\t\x12\x0f\n\x07success\x18\x02 \x01(\x08\"%\n\x0f\x45mbeddingResult\x12\x12\n\nembeddings\x18\x01 \x03(\x02\"C\n\x11TranscriptRequest\x12\x0b\n\x03\x64st\x18\x02 \x01(\t\x12\x10\n\x08language\x18\x03 \x01(\t\x12\x0f\n\x07threads\x18\x04 \x01(\r\"N\n\x10TranscriptResult\x12,\n\x08segments\x18\x01 \x03(\x0b\x32\x1a.backend.TranscriptSegment\x12\x0c\n\x04text\x18\x02 \x01(\t\"Y\n\x11TranscriptSegment\x12\n\n\x02id\x18\x01 \x01(\x05\x12\r\n\x05start\x18\x02 \x01(\x03\x12\x0b\n\x03\x65nd\x18\x03 \x01(\x03\x12\x0c\n\x04text\x18\x04 \x01(\t\x12\x0e\n\x06tokens\x18\x05 \x03(\x05\"\xd7\x01\n\x14GenerateImageRequest\x12\x0e\n\x06height\x18\x01 \x01(\x05\x12\r\n\x05width\x18\x02 \x01(\x05\x12\x0c\n\x04mode\x18\x03 \x01(\x05\x12\x0c\n\x04step\x18\x04 \x01(\x05\x12\x0c\n\x04seed\x18\x05 \x01(\x05\x12\x17\n\x0fpositive_prompt\x18\x06 \x01(\t\x12\x17\n\x0fnegative_prompt\x18\x07 \x01(\t\x12\x0b\n\x03\x64st\x18\x08 \x01(\t\x12\x0b\n\x03src\x18\t \x01(\t\x12\x18\n\x10\x45nableParameters\x18\n \x01(\t\x12\x10\n\x08\x43LIPSkip\x18\x0b \x01(\x05\"E\n\nTTSRequest\x12\x0c\n\x04text\x18\x01 \x01(\t\x12\r\n\x05model\x18\x02 \x01(\t\x12\x0b\n\x03\x64st\x18\x03 \x01(\t\x12\r\n\x05voice\x18\x04 \x01(\t\"6\n\x14TokenizationResponse\x12\x0e\n\x06length\x18\x01 \x01(\x05\x12\x0e\n\x06tokens\x18\x02 \x03(\x05\"\x8e\x01\n\x0fMemoryUsageData\x12\r\n\x05total\x18\x01 \x01(\x04\x12:\n\tbreakdown\x18\x02 \x03(\x0b\x32\'.backend.MemoryUsageData.BreakdownEntry\x1a\x30\n\x0e\x42reakdownEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\x04:\x02\x38\x01\"\xad\x01\n\x0eStatusResponse\x12,\n\x05state\x18\x01 \x01(\x0e\x32\x1d.backend.StatusResponse.State\x12(\n\x06memory\x18\x02 \x01(\x0b\x32\x18.backend.MemoryUsageData\"C\n\x05State\x12\x11\n\rUNINITIALIZED\x10\x00\x12\x08\n\x04\x42USY\x10\x01\x12\t\n\x05READY\x10\x02\x12\x12\n\x05\x45RROR\x10\xff\xff\xff\xff\xff\xff\xff\xff\xff\x01\x32\xf4\x04\n\x07\x42\x61\x63kend\x12\x32\n\x06Health\x12\x16.backend.HealthMessage\x1a\x0e.backend.Reply\"\x00\x12\x34\n\x07Predict\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x12\x35\n\tLoadModel\x12\x15.backend.ModelOptions\x1a\x0f.backend.Result\"\x00\x12<\n\rPredictStream\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x30\x01\x12@\n\tEmbedding\x12\x17.backend.PredictOptions\x1a\x18.backend.EmbeddingResult\"\x00\x12\x41\n\rGenerateImage\x12\x1d.backend.GenerateImageRequest\x1a\x0f.backend.Result\"\x00\x12M\n\x12\x41udioTranscription\x12\x1a.backend.TranscriptRequest\x1a\x19.backend.TranscriptResult\"\x00\x12-\n\x03TTS\x12\x13.backend.TTSRequest\x1a\x0f.backend.Result\"\x00\x12J\n\x0eTokenizeString\x12\x17.backend.PredictOptions\x1a\x1d.backend.TokenizationResponse\"\x00\x12;\n\x06Status\x12\x16.backend.HealthMessage\x1a\x17.backend.StatusResponse\"\x00\x42Z\n\x19io.skynet.localai.backendB\x0eLocalAIBackendP\x01Z+github.com/go-skynet/LocalAI/pkg/grpc/protob\x06proto3')
+DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\rbackend.proto\x12\x07\x62\x61\x63kend\x1a\x19google/protobuf/any.proto\"\x1b\n\tStoresKey\x12\x0e\n\x06\x46loats\x18\x01 \x03(\x02\"\x1c\n\x0bStoresValue\x12\r\n\x05\x42ytes\x18\x01 \x01(\x0c\"Z\n\x10StoresSetOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\"7\n\x13StoresDeleteOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\"4\n\x10StoresGetOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\"Y\n\x0fStoresGetResult\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\"B\n\x11StoresFindOptions\x12\x1f\n\x03Key\x18\x01 \x01(\x0b\x32\x12.backend.StoresKey\x12\x0c\n\x04TopK\x18\x02 \x01(\x05\"p\n\x10StoresFindResult\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\x12\x14\n\x0cSimilarities\x18\x03 \x03(\x02\"\x0f\n\rHealthMessage\"\xe8\x06\n\x0ePredictOptions\x12\x0e\n\x06Prompt\x18\x01 \x01(\t\x12\x0c\n\x04Seed\x18\x02 \x01(\x05\x12\x0f\n\x07Threads\x18\x03 \x01(\x05\x12\x0e\n\x06Tokens\x18\x04 \x01(\x05\x12\x0c\n\x04TopK\x18\x05 \x01(\x05\x12\x0e\n\x06Repeat\x18\x06 \x01(\x05\x12\r\n\x05\x42\x61tch\x18\x07 \x01(\x05\x12\r\n\x05NKeep\x18\x08 \x01(\x05\x12\x13\n\x0bTemperature\x18\t \x01(\x02\x12\x0f\n\x07Penalty\x18\n \x01(\x02\x12\r\n\x05\x46\x31\x36KV\x18\x0b \x01(\x08\x12\x11\n\tDebugMode\x18\x0c \x01(\x08\x12\x13\n\x0bStopPrompts\x18\r \x03(\t\x12\x11\n\tIgnoreEOS\x18\x0e \x01(\x08\x12\x19\n\x11TailFreeSamplingZ\x18\x0f \x01(\x02\x12\x10\n\x08TypicalP\x18\x10 \x01(\x02\x12\x18\n\x10\x46requencyPenalty\x18\x11 \x01(\x02\x12\x17\n\x0fPresencePenalty\x18\x12 \x01(\x02\x12\x10\n\x08Mirostat\x18\x13 \x01(\x05\x12\x13\n\x0bMirostatETA\x18\x14 \x01(\x02\x12\x13\n\x0bMirostatTAU\x18\x15 \x01(\x02\x12\x12\n\nPenalizeNL\x18\x16 \x01(\x08\x12\x11\n\tLogitBias\x18\x17 \x01(\t\x12\r\n\x05MLock\x18\x19 \x01(\x08\x12\x0c\n\x04MMap\x18\x1a \x01(\x08\x12\x16\n\x0ePromptCacheAll\x18\x1b \x01(\x08\x12\x15\n\rPromptCacheRO\x18\x1c \x01(\x08\x12\x0f\n\x07Grammar\x18\x1d \x01(\t\x12\x0f\n\x07MainGPU\x18\x1e \x01(\t\x12\x13\n\x0bTensorSplit\x18\x1f \x01(\t\x12\x0c\n\x04TopP\x18  \x01(\x02\x12\x17\n\x0fPromptCachePath\x18! \x01(\t\x12\r\n\x05\x44\x65\x62ug\x18\" \x01(\x08\x12\x17\n\x0f\x45mbeddingTokens\x18# \x03(\x05\x12\x12\n\nEmbeddings\x18$ \x01(\t\x12\x14\n\x0cRopeFreqBase\x18% \x01(\x02\x12\x15\n\rRopeFreqScale\x18& \x01(\x02\x12\x1b\n\x13NegativePromptScale\x18\' \x01(\x02\x12\x16\n\x0eNegativePrompt\x18( \x01(\t\x12\x0e\n\x06NDraft\x18) \x01(\x05\x12\x0e\n\x06Images\x18* \x03(\t\x12\x1c\n\x14UseTokenizerTemplate\x18+ \x01(\x08\x12\"\n\x08Messages\x18, \x03(\x0b\x32\x10.backend.Message\"\x18\n\x05Reply\x12\x0f\n\x07message\x18\x01 \x01(\x0c\"\xb0\x08\n\x0cModelOptions\x12\r\n\x05Model\x18\x01 \x01(\t\x12\x13\n\x0b\x43ontextSize\x18\x02 \x01(\x05\x12\x0c\n\x04Seed\x18\x03 \x01(\x05\x12\x0e\n\x06NBatch\x18\x04 \x01(\x05\x12\x11\n\tF16Memory\x18\x05 \x01(\x08\x12\r\n\x05MLock\x18\x06 \x01(\x08\x12\x0c\n\x04MMap\x18\x07 \x01(\x08\x12\x11\n\tVocabOnly\x18\x08 \x01(\x08\x12\x0f\n\x07LowVRAM\x18\t \x01(\x08\x12\x12\n\nEmbeddings\x18\n \x01(\x08\x12\x0c\n\x04NUMA\x18\x0b \x01(\x08\x12\x12\n\nNGPULayers\x18\x0c \x01(\x05\x12\x0f\n\x07MainGPU\x18\r \x01(\t\x12\x13\n\x0bTensorSplit\x18\x0e \x01(\t\x12\x0f\n\x07Threads\x18\x0f \x01(\x05\x12\x19\n\x11LibrarySearchPath\x18\x10 \x01(\t\x12\x14\n\x0cRopeFreqBase\x18\x11 \x01(\x02\x12\x15\n\rRopeFreqScale\x18\x12 \x01(\x02\x12\x12\n\nRMSNormEps\x18\x13 \x01(\x02\x12\x0c\n\x04NGQA\x18\x14 \x01(\x05\x12\x11\n\tModelFile\x18\x15 \x01(\t\x12\x0e\n\x06\x44\x65vice\x18\x16 \x01(\t\x12\x11\n\tUseTriton\x18\x17 \x01(\x08\x12\x15\n\rModelBaseName\x18\x18 \x01(\t\x12\x18\n\x10UseFastTokenizer\x18\x19 \x01(\x08\x12\x14\n\x0cPipelineType\x18\x1a \x01(\t\x12\x15\n\rSchedulerType\x18\x1b \x01(\t\x12\x0c\n\x04\x43UDA\x18\x1c \x01(\x08\x12\x10\n\x08\x43\x46GScale\x18\x1d \x01(\x02\x12\x0f\n\x07IMG2IMG\x18\x1e \x01(\x08\x12\x11\n\tCLIPModel\x18\x1f \x01(\t\x12\x15\n\rCLIPSubfolder\x18  \x01(\t\x12\x10\n\x08\x43LIPSkip\x18! \x01(\x05\x12\x12\n\nControlNet\x18\x30 \x01(\t\x12\x11\n\tTokenizer\x18\" \x01(\t\x12\x10\n\x08LoraBase\x18# \x01(\t\x12\x13\n\x0bLoraAdapter\x18$ \x01(\t\x12\x11\n\tLoraScale\x18* \x01(\x02\x12\x11\n\tNoMulMatQ\x18% \x01(\x08\x12\x12\n\nDraftModel\x18\' \x01(\t\x12\x11\n\tAudioPath\x18& \x01(\t\x12\x14\n\x0cQuantization\x18( \x01(\t\x12\x1c\n\x14GPUMemoryUtilization\x18\x32 \x01(\x02\x12\x17\n\x0fTrustRemoteCode\x18\x33 \x01(\x08\x12\x14\n\x0c\x45nforceEager\x18\x34 \x01(\x08\x12\x11\n\tSwapSpace\x18\x35 \x01(\x05\x12\x13\n\x0bMaxModelLen\x18\x36 \x01(\x05\x12\x0e\n\x06MMProj\x18) \x01(\t\x12\x13\n\x0bRopeScaling\x18+ \x01(\t\x12\x15\n\rYarnExtFactor\x18, \x01(\x02\x12\x16\n\x0eYarnAttnFactor\x18- \x01(\x02\x12\x14\n\x0cYarnBetaFast\x18. \x01(\x02\x12\x14\n\x0cYarnBetaSlow\x18/ \x01(\x02\x12\x0c\n\x04Type\x18\x31 \x01(\t\"*\n\x06Result\x12\x0f\n\x07message\x18\x01 \x01(\t\x12\x0f\n\x07success\x18\x02 \x01(\x08\"%\n\x0f\x45mbeddingResult\x12\x12\n\nembeddings\x18\x01 \x03(\x02\"C\n\x11TranscriptRequest\x12\x0b\n\x03\x64st\x18\x02 \x01(\t\x12\x10\n\x08language\x18\x03 \x01(\t\x12\x0f\n\x07threads\x18\x04 \x01(\r\"N\n\x10TranscriptResult\x12,\n\x08segments\x18\x01 \x03(\x0b\x32\x1a.backend.TranscriptSegment\x12\x0c\n\x04text\x18\x02 \x01(\t\"Y\n\x11TranscriptSegment\x12\n\n\x02id\x18\x01 \x01(\x05\x12\r\n\x05start\x18\x02 \x01(\x03\x12\x0b\n\x03\x65nd\x18\x03 \x01(\x03\x12\x0c\n\x04text\x18\x04 \x01(\t\x12\x0e\n\x06tokens\x18\x05 \x03(\x05\"\xd7\x01\n\x14GenerateImageRequest\x12\x0e\n\x06height\x18\x01 \x01(\x05\x12\r\n\x05width\x18\x02 \x01(\x05\x12\x0c\n\x04mode\x18\x03 \x01(\x05\x12\x0c\n\x04step\x18\x04 \x01(\x05\x12\x0c\n\x04seed\x18\x05 \x01(\x05\x12\x17\n\x0fpositive_prompt\x18\x06 \x01(\t\x12\x17\n\x0fnegative_prompt\x18\x07 \x01(\t\x12\x0b\n\x03\x64st\x18\x08 \x01(\t\x12\x0b\n\x03src\x18\t \x01(\t\x12\x18\n\x10\x45nableParameters\x18\n \x01(\t\x12\x10\n\x08\x43LIPSkip\x18\x0b \x01(\x05\"E\n\nTTSRequest\x12\x0c\n\x04text\x18\x01 \x01(\t\x12\r\n\x05model\x18\x02 \x01(\t\x12\x0b\n\x03\x64st\x18\x03 \x01(\t\x12\r\n\x05voice\x18\x04 \x01(\t\"6\n\x14TokenizationResponse\x12\x0e\n\x06length\x18\x01 \x01(\x05\x12\x0e\n\x06tokens\x18\x02 \x03(\x05\"\x8e\x01\n\x0fMemoryUsageData\x12\r\n\x05total\x18\x01 \x01(\x04\x12:\n\tbreakdown\x18\x02 \x03(\x0b\x32\'.backend.MemoryUsageData.BreakdownEntry\x1a\x30\n\x0e\x42reakdownEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\x04:\x02\x38\x01\"\xad\x01\n\x0eStatusResponse\x12,\n\x05state\x18\x01 \x01(\x0e\x32\x1d.backend.StatusResponse.State\x12(\n\x06memory\x18\x02 \x01(\x0b\x32\x18.backend.MemoryUsageData\"C\n\x05State\x12\x11\n\rUNINITIALIZED\x10\x00\x12\x08\n\x04\x42USY\x10\x01\x12\t\n\x05READY\x10\x02\x12\x12\n\x05\x45RROR\x10\xff\xff\xff\xff\xff\xff\xff\xff\xff\x01\">\n\x07Message\x12\x0c\n\x04Role\x18\x01 \x01(\t\x12%\n\x07\x43ontent\x18\x02 \x01(\x0b\x32\x14.google.protobuf.Any2\xfb\x06\n\x07\x42\x61\x63kend\x12\x32\n\x06Health\x12\x16.backend.HealthMessage\x1a\x0e.backend.Reply\"\x00\x12\x34\n\x07Predict\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x12\x35\n\tLoadModel\x12\x15.backend.ModelOptions\x1a\x0f.backend.Result\"\x00\x12<\n\rPredictStream\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x30\x01\x12@\n\tEmbedding\x12\x17.backend.PredictOptions\x1a\x18.backend.EmbeddingResult\"\x00\x12\x41\n\rGenerateImage\x12\x1d.backend.GenerateImageRequest\x1a\x0f.backend.Result\"\x00\x12M\n\x12\x41udioTranscription\x12\x1a.backend.TranscriptRequest\x1a\x19.backend.TranscriptResult\"\x00\x12-\n\x03TTS\x12\x13.backend.TTSRequest\x1a\x0f.backend.Result\"\x00\x12J\n\x0eTokenizeString\x12\x17.backend.PredictOptions\x1a\x1d.backend.TokenizationResponse\"\x00\x12;\n\x06Status\x12\x16.backend.HealthMessage\x1a\x17.backend.StatusResponse\"\x00\x12\x39\n\tStoresSet\x12\x19.backend.StoresSetOptions\x1a\x0f.backend.Result\"\x00\x12?\n\x0cStoresDelete\x12\x1c.backend.StoresDeleteOptions\x1a\x0f.backend.Result\"\x00\x12\x42\n\tStoresGet\x12\x19.backend.StoresGetOptions\x1a\x18.backend.StoresGetResult\"\x00\x12\x45\n\nStoresFind\x12\x1a.backend.StoresFindOptions\x1a\x19.backend.StoresFindResult\"\x00\x42Z\n\x19io.skynet.localai.backendB\x0eLocalAIBackendP\x01Z+github.com/go-skynet/LocalAI/pkg/grpc/protob\x06proto3')
 
 _globals = globals()
 _builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, _globals)
 _builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, 'backend_pb2', _globals)
 if _descriptor._USE_C_DESCRIPTORS == False:
-
-  DESCRIPTOR._options = None
-  DESCRIPTOR._serialized_options = b'\n\031io.skynet.localai.backendB\016LocalAIBackendP\001Z+github.com/go-skynet/LocalAI/pkg/grpc/proto'
-  _MEMORYUSAGEDATA_BREAKDOWNENTRY._options = None
-  _MEMORYUSAGEDATA_BREAKDOWNENTRY._serialized_options = b'8\001'
-  _globals['_HEALTHMESSAGE']._serialized_start=26
-  _globals['_HEALTHMESSAGE']._serialized_end=41
-  _globals['_PREDICTOPTIONS']._serialized_start=44
-  _globals['_PREDICTOPTIONS']._serialized_end=850
-  _globals['_REPLY']._serialized_start=852
-  _globals['_REPLY']._serialized_end=876
-  _globals['_MODELOPTIONS']._serialized_start=879
-  _globals['_MODELOPTIONS']._serialized_end=1951
-  _globals['_RESULT']._serialized_start=1953
-  _globals['_RESULT']._serialized_end=1995
-  _globals['_EMBEDDINGRESULT']._serialized_start=1997
-  _globals['_EMBEDDINGRESULT']._serialized_end=2034
-  _globals['_TRANSCRIPTREQUEST']._serialized_start=2036
-  _globals['_TRANSCRIPTREQUEST']._serialized_end=2103
-  _globals['_TRANSCRIPTRESULT']._serialized_start=2105
-  _globals['_TRANSCRIPTRESULT']._serialized_end=2183
-  _globals['_TRANSCRIPTSEGMENT']._serialized_start=2185
-  _globals['_TRANSCRIPTSEGMENT']._serialized_end=2274
-  _globals['_GENERATEIMAGEREQUEST']._serialized_start=2277
-  _globals['_GENERATEIMAGEREQUEST']._serialized_end=2492
-  _globals['_TTSREQUEST']._serialized_start=2494
-  _globals['_TTSREQUEST']._serialized_end=2563
-  _globals['_TOKENIZATIONRESPONSE']._serialized_start=2565
-  _globals['_TOKENIZATIONRESPONSE']._serialized_end=2619
-  _globals['_MEMORYUSAGEDATA']._serialized_start=2622
-  _globals['_MEMORYUSAGEDATA']._serialized_end=2764
-  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_start=2716
-  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_end=2764
-  _globals['_STATUSRESPONSE']._serialized_start=2767
-  _globals['_STATUSRESPONSE']._serialized_end=2940
-  _globals['_STATUSRESPONSE_STATE']._serialized_start=2873
-  _globals['_STATUSRESPONSE_STATE']._serialized_end=2940
-  _globals['_BACKEND']._serialized_start=2943
-  _globals['_BACKEND']._serialized_end=3571
+  _globals['DESCRIPTOR']._options = None
+  _globals['DESCRIPTOR']._serialized_options = b'\n\031io.skynet.localai.backendB\016LocalAIBackendP\001Z+github.com/go-skynet/LocalAI/pkg/grpc/proto'
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._options = None
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_options = b'8\001'
+  _globals['_STORESKEY']._serialized_start=53
+  _globals['_STORESKEY']._serialized_end=80
+  _globals['_STORESVALUE']._serialized_start=82
+  _globals['_STORESVALUE']._serialized_end=110
+  _globals['_STORESSETOPTIONS']._serialized_start=112
+  _globals['_STORESSETOPTIONS']._serialized_end=202
+  _globals['_STORESDELETEOPTIONS']._serialized_start=204
+  _globals['_STORESDELETEOPTIONS']._serialized_end=259
+  _globals['_STORESGETOPTIONS']._serialized_start=261
+  _globals['_STORESGETOPTIONS']._serialized_end=313
+  _globals['_STORESGETRESULT']._serialized_start=315
+  _globals['_STORESGETRESULT']._serialized_end=404
+  _globals['_STORESFINDOPTIONS']._serialized_start=406
+  _globals['_STORESFINDOPTIONS']._serialized_end=472
+  _globals['_STORESFINDRESULT']._serialized_start=474
+  _globals['_STORESFINDRESULT']._serialized_end=586
+  _globals['_HEALTHMESSAGE']._serialized_start=588
+  _globals['_HEALTHMESSAGE']._serialized_end=603
+  _globals['_PREDICTOPTIONS']._serialized_start=606
+  _globals['_PREDICTOPTIONS']._serialized_end=1478
+  _globals['_REPLY']._serialized_start=1480
+  _globals['_REPLY']._serialized_end=1504
+  _globals['_MODELOPTIONS']._serialized_start=1507
+  _globals['_MODELOPTIONS']._serialized_end=2579
+  _globals['_RESULT']._serialized_start=2581
+  _globals['_RESULT']._serialized_end=2623
+  _globals['_EMBEDDINGRESULT']._serialized_start=2625
+  _globals['_EMBEDDINGRESULT']._serialized_end=2662
+  _globals['_TRANSCRIPTREQUEST']._serialized_start=2664
+  _globals['_TRANSCRIPTREQUEST']._serialized_end=2731
+  _globals['_TRANSCRIPTRESULT']._serialized_start=2733
+  _globals['_TRANSCRIPTRESULT']._serialized_end=2811
+  _globals['_TRANSCRIPTSEGMENT']._serialized_start=2813
+  _globals['_TRANSCRIPTSEGMENT']._serialized_end=2902
+  _globals['_GENERATEIMAGEREQUEST']._serialized_start=2905
+  _globals['_GENERATEIMAGEREQUEST']._serialized_end=3120
+  _globals['_TTSREQUEST']._serialized_start=3122
+  _globals['_TTSREQUEST']._serialized_end=3191
+  _globals['_TOKENIZATIONRESPONSE']._serialized_start=3193
+  _globals['_TOKENIZATIONRESPONSE']._serialized_end=3247
+  _globals['_MEMORYUSAGEDATA']._serialized_start=3250
+  _globals['_MEMORYUSAGEDATA']._serialized_end=3392
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_start=3344
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_end=3392
+  _globals['_STATUSRESPONSE']._serialized_start=3395
+  _globals['_STATUSRESPONSE']._serialized_end=3568
+  _globals['_STATUSRESPONSE_STATE']._serialized_start=3501
+  _globals['_STATUSRESPONSE_STATE']._serialized_end=3568
+  _globals['_MESSAGE']._serialized_start=3570
+  _globals['_MESSAGE']._serialized_end=3632
+  _globals['_BACKEND']._serialized_start=3635
+  _globals['_BACKEND']._serialized_end=4526
 # @@protoc_insertion_point(module_scope)
diff --git a/backend/python/mamba/backend_pb2_grpc.py b/backend/python/mamba/backend_pb2_grpc.py
index 79a7677fb27f..e06fccf3d451 100644
--- a/backend/python/mamba/backend_pb2_grpc.py
+++ b/backend/python/mamba/backend_pb2_grpc.py
@@ -64,6 +64,26 @@ def __init__(self, channel):
                 request_serializer=backend__pb2.HealthMessage.SerializeToString,
                 response_deserializer=backend__pb2.StatusResponse.FromString,
                 )
+        self.StoresSet = channel.unary_unary(
+                '/backend.Backend/StoresSet',
+                request_serializer=backend__pb2.StoresSetOptions.SerializeToString,
+                response_deserializer=backend__pb2.Result.FromString,
+                )
+        self.StoresDelete = channel.unary_unary(
+                '/backend.Backend/StoresDelete',
+                request_serializer=backend__pb2.StoresDeleteOptions.SerializeToString,
+                response_deserializer=backend__pb2.Result.FromString,
+                )
+        self.StoresGet = channel.unary_unary(
+                '/backend.Backend/StoresGet',
+                request_serializer=backend__pb2.StoresGetOptions.SerializeToString,
+                response_deserializer=backend__pb2.StoresGetResult.FromString,
+                )
+        self.StoresFind = channel.unary_unary(
+                '/backend.Backend/StoresFind',
+                request_serializer=backend__pb2.StoresFindOptions.SerializeToString,
+                response_deserializer=backend__pb2.StoresFindResult.FromString,
+                )
 
 
 class BackendServicer(object):
@@ -129,6 +149,30 @@ def Status(self, request, context):
         context.set_details('Method not implemented!')
         raise NotImplementedError('Method not implemented!')
 
+    def StoresSet(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresDelete(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresGet(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresFind(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
 
 def add_BackendServicer_to_server(servicer, server):
     rpc_method_handlers = {
@@ -182,6 +226,26 @@ def add_BackendServicer_to_server(servicer, server):
                     request_deserializer=backend__pb2.HealthMessage.FromString,
                     response_serializer=backend__pb2.StatusResponse.SerializeToString,
             ),
+            'StoresSet': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresSet,
+                    request_deserializer=backend__pb2.StoresSetOptions.FromString,
+                    response_serializer=backend__pb2.Result.SerializeToString,
+            ),
+            'StoresDelete': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresDelete,
+                    request_deserializer=backend__pb2.StoresDeleteOptions.FromString,
+                    response_serializer=backend__pb2.Result.SerializeToString,
+            ),
+            'StoresGet': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresGet,
+                    request_deserializer=backend__pb2.StoresGetOptions.FromString,
+                    response_serializer=backend__pb2.StoresGetResult.SerializeToString,
+            ),
+            'StoresFind': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresFind,
+                    request_deserializer=backend__pb2.StoresFindOptions.FromString,
+                    response_serializer=backend__pb2.StoresFindResult.SerializeToString,
+            ),
     }
     generic_handler = grpc.method_handlers_generic_handler(
             'backend.Backend', rpc_method_handlers)
@@ -361,3 +425,71 @@ def Status(request,
             backend__pb2.StatusResponse.FromString,
             options, channel_credentials,
             insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresSet(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresSet',
+            backend__pb2.StoresSetOptions.SerializeToString,
+            backend__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresDelete(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresDelete',
+            backend__pb2.StoresDeleteOptions.SerializeToString,
+            backend__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresGet(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresGet',
+            backend__pb2.StoresGetOptions.SerializeToString,
+            backend__pb2.StoresGetResult.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresFind(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresFind',
+            backend__pb2.StoresFindOptions.SerializeToString,
+            backend__pb2.StoresFindResult.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
diff --git a/backend/python/petals/backend_pb2.py b/backend/python/petals/backend_pb2.py
index 08b896c7cad5..8d366c16d63b 100644
--- a/backend/python/petals/backend_pb2.py
+++ b/backend/python/petals/backend_pb2.py
@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 # Generated by the protocol buffer compiler.  DO NOT EDIT!
 # source: backend.proto
+# Protobuf Python Version: 4.25.1
 """Generated protocol buffer code."""
 from google.protobuf import descriptor as _descriptor
 from google.protobuf import descriptor_pool as _descriptor_pool
@@ -11,51 +12,69 @@
 _sym_db = _symbol_database.Default()
 
 
+from google.protobuf import any_pb2 as google_dot_protobuf_dot_any__pb2
 
 
-DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\rbackend.proto\x12\x07\x62\x61\x63kend\"\x0f\n\rHealthMessage\"\xa6\x06\n\x0ePredictOptions\x12\x0e\n\x06Prompt\x18\x01 \x01(\t\x12\x0c\n\x04Seed\x18\x02 \x01(\x05\x12\x0f\n\x07Threads\x18\x03 \x01(\x05\x12\x0e\n\x06Tokens\x18\x04 \x01(\x05\x12\x0c\n\x04TopK\x18\x05 \x01(\x05\x12\x0e\n\x06Repeat\x18\x06 \x01(\x05\x12\r\n\x05\x42\x61tch\x18\x07 \x01(\x05\x12\r\n\x05NKeep\x18\x08 \x01(\x05\x12\x13\n\x0bTemperature\x18\t \x01(\x02\x12\x0f\n\x07Penalty\x18\n \x01(\x02\x12\r\n\x05\x46\x31\x36KV\x18\x0b \x01(\x08\x12\x11\n\tDebugMode\x18\x0c \x01(\x08\x12\x13\n\x0bStopPrompts\x18\r \x03(\t\x12\x11\n\tIgnoreEOS\x18\x0e \x01(\x08\x12\x19\n\x11TailFreeSamplingZ\x18\x0f \x01(\x02\x12\x10\n\x08TypicalP\x18\x10 \x01(\x02\x12\x18\n\x10\x46requencyPenalty\x18\x11 \x01(\x02\x12\x17\n\x0fPresencePenalty\x18\x12 \x01(\x02\x12\x10\n\x08Mirostat\x18\x13 \x01(\x05\x12\x13\n\x0bMirostatETA\x18\x14 \x01(\x02\x12\x13\n\x0bMirostatTAU\x18\x15 \x01(\x02\x12\x12\n\nPenalizeNL\x18\x16 \x01(\x08\x12\x11\n\tLogitBias\x18\x17 \x01(\t\x12\r\n\x05MLock\x18\x19 \x01(\x08\x12\x0c\n\x04MMap\x18\x1a \x01(\x08\x12\x16\n\x0ePromptCacheAll\x18\x1b \x01(\x08\x12\x15\n\rPromptCacheRO\x18\x1c \x01(\x08\x12\x0f\n\x07Grammar\x18\x1d \x01(\t\x12\x0f\n\x07MainGPU\x18\x1e \x01(\t\x12\x13\n\x0bTensorSplit\x18\x1f \x01(\t\x12\x0c\n\x04TopP\x18  \x01(\x02\x12\x17\n\x0fPromptCachePath\x18! \x01(\t\x12\r\n\x05\x44\x65\x62ug\x18\" \x01(\x08\x12\x17\n\x0f\x45mbeddingTokens\x18# \x03(\x05\x12\x12\n\nEmbeddings\x18$ \x01(\t\x12\x14\n\x0cRopeFreqBase\x18% \x01(\x02\x12\x15\n\rRopeFreqScale\x18& \x01(\x02\x12\x1b\n\x13NegativePromptScale\x18\' \x01(\x02\x12\x16\n\x0eNegativePrompt\x18( \x01(\t\x12\x0e\n\x06NDraft\x18) \x01(\x05\x12\x0e\n\x06Images\x18* \x03(\t\"\x18\n\x05Reply\x12\x0f\n\x07message\x18\x01 \x01(\x0c\"\xb0\x08\n\x0cModelOptions\x12\r\n\x05Model\x18\x01 \x01(\t\x12\x13\n\x0b\x43ontextSize\x18\x02 \x01(\x05\x12\x0c\n\x04Seed\x18\x03 \x01(\x05\x12\x0e\n\x06NBatch\x18\x04 \x01(\x05\x12\x11\n\tF16Memory\x18\x05 \x01(\x08\x12\r\n\x05MLock\x18\x06 \x01(\x08\x12\x0c\n\x04MMap\x18\x07 \x01(\x08\x12\x11\n\tVocabOnly\x18\x08 \x01(\x08\x12\x0f\n\x07LowVRAM\x18\t \x01(\x08\x12\x12\n\nEmbeddings\x18\n \x01(\x08\x12\x0c\n\x04NUMA\x18\x0b \x01(\x08\x12\x12\n\nNGPULayers\x18\x0c \x01(\x05\x12\x0f\n\x07MainGPU\x18\r \x01(\t\x12\x13\n\x0bTensorSplit\x18\x0e \x01(\t\x12\x0f\n\x07Threads\x18\x0f \x01(\x05\x12\x19\n\x11LibrarySearchPath\x18\x10 \x01(\t\x12\x14\n\x0cRopeFreqBase\x18\x11 \x01(\x02\x12\x15\n\rRopeFreqScale\x18\x12 \x01(\x02\x12\x12\n\nRMSNormEps\x18\x13 \x01(\x02\x12\x0c\n\x04NGQA\x18\x14 \x01(\x05\x12\x11\n\tModelFile\x18\x15 \x01(\t\x12\x0e\n\x06\x44\x65vice\x18\x16 \x01(\t\x12\x11\n\tUseTriton\x18\x17 \x01(\x08\x12\x15\n\rModelBaseName\x18\x18 \x01(\t\x12\x18\n\x10UseFastTokenizer\x18\x19 \x01(\x08\x12\x14\n\x0cPipelineType\x18\x1a \x01(\t\x12\x15\n\rSchedulerType\x18\x1b \x01(\t\x12\x0c\n\x04\x43UDA\x18\x1c \x01(\x08\x12\x10\n\x08\x43\x46GScale\x18\x1d \x01(\x02\x12\x0f\n\x07IMG2IMG\x18\x1e \x01(\x08\x12\x11\n\tCLIPModel\x18\x1f \x01(\t\x12\x15\n\rCLIPSubfolder\x18  \x01(\t\x12\x10\n\x08\x43LIPSkip\x18! \x01(\x05\x12\x12\n\nControlNet\x18\x30 \x01(\t\x12\x11\n\tTokenizer\x18\" \x01(\t\x12\x10\n\x08LoraBase\x18# \x01(\t\x12\x13\n\x0bLoraAdapter\x18$ \x01(\t\x12\x11\n\tLoraScale\x18* \x01(\x02\x12\x11\n\tNoMulMatQ\x18% \x01(\x08\x12\x12\n\nDraftModel\x18\' \x01(\t\x12\x11\n\tAudioPath\x18& \x01(\t\x12\x14\n\x0cQuantization\x18( \x01(\t\x12\x1c\n\x14GPUMemoryUtilization\x18\x32 \x01(\x02\x12\x17\n\x0fTrustRemoteCode\x18\x33 \x01(\x08\x12\x14\n\x0c\x45nforceEager\x18\x34 \x01(\x08\x12\x11\n\tSwapSpace\x18\x35 \x01(\x05\x12\x13\n\x0bMaxModelLen\x18\x36 \x01(\x05\x12\x0e\n\x06MMProj\x18) \x01(\t\x12\x13\n\x0bRopeScaling\x18+ \x01(\t\x12\x15\n\rYarnExtFactor\x18, \x01(\x02\x12\x16\n\x0eYarnAttnFactor\x18- \x01(\x02\x12\x14\n\x0cYarnBetaFast\x18. \x01(\x02\x12\x14\n\x0cYarnBetaSlow\x18/ \x01(\x02\x12\x0c\n\x04Type\x18\x31 \x01(\t\"*\n\x06Result\x12\x0f\n\x07message\x18\x01 \x01(\t\x12\x0f\n\x07success\x18\x02 \x01(\x08\"%\n\x0f\x45mbeddingResult\x12\x12\n\nembeddings\x18\x01 \x03(\x02\"C\n\x11TranscriptRequest\x12\x0b\n\x03\x64st\x18\x02 \x01(\t\x12\x10\n\x08language\x18\x03 \x01(\t\x12\x0f\n\x07threads\x18\x04 \x01(\r\"N\n\x10TranscriptResult\x12,\n\x08segments\x18\x01 \x03(\x0b\x32\x1a.backend.TranscriptSegment\x12\x0c\n\x04text\x18\x02 \x01(\t\"Y\n\x11TranscriptSegment\x12\n\n\x02id\x18\x01 \x01(\x05\x12\r\n\x05start\x18\x02 \x01(\x03\x12\x0b\n\x03\x65nd\x18\x03 \x01(\x03\x12\x0c\n\x04text\x18\x04 \x01(\t\x12\x0e\n\x06tokens\x18\x05 \x03(\x05\"\xd7\x01\n\x14GenerateImageRequest\x12\x0e\n\x06height\x18\x01 \x01(\x05\x12\r\n\x05width\x18\x02 \x01(\x05\x12\x0c\n\x04mode\x18\x03 \x01(\x05\x12\x0c\n\x04step\x18\x04 \x01(\x05\x12\x0c\n\x04seed\x18\x05 \x01(\x05\x12\x17\n\x0fpositive_prompt\x18\x06 \x01(\t\x12\x17\n\x0fnegative_prompt\x18\x07 \x01(\t\x12\x0b\n\x03\x64st\x18\x08 \x01(\t\x12\x0b\n\x03src\x18\t \x01(\t\x12\x18\n\x10\x45nableParameters\x18\n \x01(\t\x12\x10\n\x08\x43LIPSkip\x18\x0b \x01(\x05\"E\n\nTTSRequest\x12\x0c\n\x04text\x18\x01 \x01(\t\x12\r\n\x05model\x18\x02 \x01(\t\x12\x0b\n\x03\x64st\x18\x03 \x01(\t\x12\r\n\x05voice\x18\x04 \x01(\t\"6\n\x14TokenizationResponse\x12\x0e\n\x06length\x18\x01 \x01(\x05\x12\x0e\n\x06tokens\x18\x02 \x03(\x05\"\x8e\x01\n\x0fMemoryUsageData\x12\r\n\x05total\x18\x01 \x01(\x04\x12:\n\tbreakdown\x18\x02 \x03(\x0b\x32\'.backend.MemoryUsageData.BreakdownEntry\x1a\x30\n\x0e\x42reakdownEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\x04:\x02\x38\x01\"\xad\x01\n\x0eStatusResponse\x12,\n\x05state\x18\x01 \x01(\x0e\x32\x1d.backend.StatusResponse.State\x12(\n\x06memory\x18\x02 \x01(\x0b\x32\x18.backend.MemoryUsageData\"C\n\x05State\x12\x11\n\rUNINITIALIZED\x10\x00\x12\x08\n\x04\x42USY\x10\x01\x12\t\n\x05READY\x10\x02\x12\x12\n\x05\x45RROR\x10\xff\xff\xff\xff\xff\xff\xff\xff\xff\x01\x32\xf4\x04\n\x07\x42\x61\x63kend\x12\x32\n\x06Health\x12\x16.backend.HealthMessage\x1a\x0e.backend.Reply\"\x00\x12\x34\n\x07Predict\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x12\x35\n\tLoadModel\x12\x15.backend.ModelOptions\x1a\x0f.backend.Result\"\x00\x12<\n\rPredictStream\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x30\x01\x12@\n\tEmbedding\x12\x17.backend.PredictOptions\x1a\x18.backend.EmbeddingResult\"\x00\x12\x41\n\rGenerateImage\x12\x1d.backend.GenerateImageRequest\x1a\x0f.backend.Result\"\x00\x12M\n\x12\x41udioTranscription\x12\x1a.backend.TranscriptRequest\x1a\x19.backend.TranscriptResult\"\x00\x12-\n\x03TTS\x12\x13.backend.TTSRequest\x1a\x0f.backend.Result\"\x00\x12J\n\x0eTokenizeString\x12\x17.backend.PredictOptions\x1a\x1d.backend.TokenizationResponse\"\x00\x12;\n\x06Status\x12\x16.backend.HealthMessage\x1a\x17.backend.StatusResponse\"\x00\x42Z\n\x19io.skynet.localai.backendB\x0eLocalAIBackendP\x01Z+github.com/go-skynet/LocalAI/pkg/grpc/protob\x06proto3')
+DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\rbackend.proto\x12\x07\x62\x61\x63kend\x1a\x19google/protobuf/any.proto\"\x1b\n\tStoresKey\x12\x0e\n\x06\x46loats\x18\x01 \x03(\x02\"\x1c\n\x0bStoresValue\x12\r\n\x05\x42ytes\x18\x01 \x01(\x0c\"Z\n\x10StoresSetOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\"7\n\x13StoresDeleteOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\"4\n\x10StoresGetOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\"Y\n\x0fStoresGetResult\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\"B\n\x11StoresFindOptions\x12\x1f\n\x03Key\x18\x01 \x01(\x0b\x32\x12.backend.StoresKey\x12\x0c\n\x04TopK\x18\x02 \x01(\x05\"p\n\x10StoresFindResult\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\x12\x14\n\x0cSimilarities\x18\x03 \x03(\x02\"\x0f\n\rHealthMessage\"\xe8\x06\n\x0ePredictOptions\x12\x0e\n\x06Prompt\x18\x01 \x01(\t\x12\x0c\n\x04Seed\x18\x02 \x01(\x05\x12\x0f\n\x07Threads\x18\x03 \x01(\x05\x12\x0e\n\x06Tokens\x18\x04 \x01(\x05\x12\x0c\n\x04TopK\x18\x05 \x01(\x05\x12\x0e\n\x06Repeat\x18\x06 \x01(\x05\x12\r\n\x05\x42\x61tch\x18\x07 \x01(\x05\x12\r\n\x05NKeep\x18\x08 \x01(\x05\x12\x13\n\x0bTemperature\x18\t \x01(\x02\x12\x0f\n\x07Penalty\x18\n \x01(\x02\x12\r\n\x05\x46\x31\x36KV\x18\x0b \x01(\x08\x12\x11\n\tDebugMode\x18\x0c \x01(\x08\x12\x13\n\x0bStopPrompts\x18\r \x03(\t\x12\x11\n\tIgnoreEOS\x18\x0e \x01(\x08\x12\x19\n\x11TailFreeSamplingZ\x18\x0f \x01(\x02\x12\x10\n\x08TypicalP\x18\x10 \x01(\x02\x12\x18\n\x10\x46requencyPenalty\x18\x11 \x01(\x02\x12\x17\n\x0fPresencePenalty\x18\x12 \x01(\x02\x12\x10\n\x08Mirostat\x18\x13 \x01(\x05\x12\x13\n\x0bMirostatETA\x18\x14 \x01(\x02\x12\x13\n\x0bMirostatTAU\x18\x15 \x01(\x02\x12\x12\n\nPenalizeNL\x18\x16 \x01(\x08\x12\x11\n\tLogitBias\x18\x17 \x01(\t\x12\r\n\x05MLock\x18\x19 \x01(\x08\x12\x0c\n\x04MMap\x18\x1a \x01(\x08\x12\x16\n\x0ePromptCacheAll\x18\x1b \x01(\x08\x12\x15\n\rPromptCacheRO\x18\x1c \x01(\x08\x12\x0f\n\x07Grammar\x18\x1d \x01(\t\x12\x0f\n\x07MainGPU\x18\x1e \x01(\t\x12\x13\n\x0bTensorSplit\x18\x1f \x01(\t\x12\x0c\n\x04TopP\x18  \x01(\x02\x12\x17\n\x0fPromptCachePath\x18! \x01(\t\x12\r\n\x05\x44\x65\x62ug\x18\" \x01(\x08\x12\x17\n\x0f\x45mbeddingTokens\x18# \x03(\x05\x12\x12\n\nEmbeddings\x18$ \x01(\t\x12\x14\n\x0cRopeFreqBase\x18% \x01(\x02\x12\x15\n\rRopeFreqScale\x18& \x01(\x02\x12\x1b\n\x13NegativePromptScale\x18\' \x01(\x02\x12\x16\n\x0eNegativePrompt\x18( \x01(\t\x12\x0e\n\x06NDraft\x18) \x01(\x05\x12\x0e\n\x06Images\x18* \x03(\t\x12\x1c\n\x14UseTokenizerTemplate\x18+ \x01(\x08\x12\"\n\x08Messages\x18, \x03(\x0b\x32\x10.backend.Message\"\x18\n\x05Reply\x12\x0f\n\x07message\x18\x01 \x01(\x0c\"\xb0\x08\n\x0cModelOptions\x12\r\n\x05Model\x18\x01 \x01(\t\x12\x13\n\x0b\x43ontextSize\x18\x02 \x01(\x05\x12\x0c\n\x04Seed\x18\x03 \x01(\x05\x12\x0e\n\x06NBatch\x18\x04 \x01(\x05\x12\x11\n\tF16Memory\x18\x05 \x01(\x08\x12\r\n\x05MLock\x18\x06 \x01(\x08\x12\x0c\n\x04MMap\x18\x07 \x01(\x08\x12\x11\n\tVocabOnly\x18\x08 \x01(\x08\x12\x0f\n\x07LowVRAM\x18\t \x01(\x08\x12\x12\n\nEmbeddings\x18\n \x01(\x08\x12\x0c\n\x04NUMA\x18\x0b \x01(\x08\x12\x12\n\nNGPULayers\x18\x0c \x01(\x05\x12\x0f\n\x07MainGPU\x18\r \x01(\t\x12\x13\n\x0bTensorSplit\x18\x0e \x01(\t\x12\x0f\n\x07Threads\x18\x0f \x01(\x05\x12\x19\n\x11LibrarySearchPath\x18\x10 \x01(\t\x12\x14\n\x0cRopeFreqBase\x18\x11 \x01(\x02\x12\x15\n\rRopeFreqScale\x18\x12 \x01(\x02\x12\x12\n\nRMSNormEps\x18\x13 \x01(\x02\x12\x0c\n\x04NGQA\x18\x14 \x01(\x05\x12\x11\n\tModelFile\x18\x15 \x01(\t\x12\x0e\n\x06\x44\x65vice\x18\x16 \x01(\t\x12\x11\n\tUseTriton\x18\x17 \x01(\x08\x12\x15\n\rModelBaseName\x18\x18 \x01(\t\x12\x18\n\x10UseFastTokenizer\x18\x19 \x01(\x08\x12\x14\n\x0cPipelineType\x18\x1a \x01(\t\x12\x15\n\rSchedulerType\x18\x1b \x01(\t\x12\x0c\n\x04\x43UDA\x18\x1c \x01(\x08\x12\x10\n\x08\x43\x46GScale\x18\x1d \x01(\x02\x12\x0f\n\x07IMG2IMG\x18\x1e \x01(\x08\x12\x11\n\tCLIPModel\x18\x1f \x01(\t\x12\x15\n\rCLIPSubfolder\x18  \x01(\t\x12\x10\n\x08\x43LIPSkip\x18! \x01(\x05\x12\x12\n\nControlNet\x18\x30 \x01(\t\x12\x11\n\tTokenizer\x18\" \x01(\t\x12\x10\n\x08LoraBase\x18# \x01(\t\x12\x13\n\x0bLoraAdapter\x18$ \x01(\t\x12\x11\n\tLoraScale\x18* \x01(\x02\x12\x11\n\tNoMulMatQ\x18% \x01(\x08\x12\x12\n\nDraftModel\x18\' \x01(\t\x12\x11\n\tAudioPath\x18& \x01(\t\x12\x14\n\x0cQuantization\x18( \x01(\t\x12\x1c\n\x14GPUMemoryUtilization\x18\x32 \x01(\x02\x12\x17\n\x0fTrustRemoteCode\x18\x33 \x01(\x08\x12\x14\n\x0c\x45nforceEager\x18\x34 \x01(\x08\x12\x11\n\tSwapSpace\x18\x35 \x01(\x05\x12\x13\n\x0bMaxModelLen\x18\x36 \x01(\x05\x12\x0e\n\x06MMProj\x18) \x01(\t\x12\x13\n\x0bRopeScaling\x18+ \x01(\t\x12\x15\n\rYarnExtFactor\x18, \x01(\x02\x12\x16\n\x0eYarnAttnFactor\x18- \x01(\x02\x12\x14\n\x0cYarnBetaFast\x18. \x01(\x02\x12\x14\n\x0cYarnBetaSlow\x18/ \x01(\x02\x12\x0c\n\x04Type\x18\x31 \x01(\t\"*\n\x06Result\x12\x0f\n\x07message\x18\x01 \x01(\t\x12\x0f\n\x07success\x18\x02 \x01(\x08\"%\n\x0f\x45mbeddingResult\x12\x12\n\nembeddings\x18\x01 \x03(\x02\"C\n\x11TranscriptRequest\x12\x0b\n\x03\x64st\x18\x02 \x01(\t\x12\x10\n\x08language\x18\x03 \x01(\t\x12\x0f\n\x07threads\x18\x04 \x01(\r\"N\n\x10TranscriptResult\x12,\n\x08segments\x18\x01 \x03(\x0b\x32\x1a.backend.TranscriptSegment\x12\x0c\n\x04text\x18\x02 \x01(\t\"Y\n\x11TranscriptSegment\x12\n\n\x02id\x18\x01 \x01(\x05\x12\r\n\x05start\x18\x02 \x01(\x03\x12\x0b\n\x03\x65nd\x18\x03 \x01(\x03\x12\x0c\n\x04text\x18\x04 \x01(\t\x12\x0e\n\x06tokens\x18\x05 \x03(\x05\"\xd7\x01\n\x14GenerateImageRequest\x12\x0e\n\x06height\x18\x01 \x01(\x05\x12\r\n\x05width\x18\x02 \x01(\x05\x12\x0c\n\x04mode\x18\x03 \x01(\x05\x12\x0c\n\x04step\x18\x04 \x01(\x05\x12\x0c\n\x04seed\x18\x05 \x01(\x05\x12\x17\n\x0fpositive_prompt\x18\x06 \x01(\t\x12\x17\n\x0fnegative_prompt\x18\x07 \x01(\t\x12\x0b\n\x03\x64st\x18\x08 \x01(\t\x12\x0b\n\x03src\x18\t \x01(\t\x12\x18\n\x10\x45nableParameters\x18\n \x01(\t\x12\x10\n\x08\x43LIPSkip\x18\x0b \x01(\x05\"E\n\nTTSRequest\x12\x0c\n\x04text\x18\x01 \x01(\t\x12\r\n\x05model\x18\x02 \x01(\t\x12\x0b\n\x03\x64st\x18\x03 \x01(\t\x12\r\n\x05voice\x18\x04 \x01(\t\"6\n\x14TokenizationResponse\x12\x0e\n\x06length\x18\x01 \x01(\x05\x12\x0e\n\x06tokens\x18\x02 \x03(\x05\"\x8e\x01\n\x0fMemoryUsageData\x12\r\n\x05total\x18\x01 \x01(\x04\x12:\n\tbreakdown\x18\x02 \x03(\x0b\x32\'.backend.MemoryUsageData.BreakdownEntry\x1a\x30\n\x0e\x42reakdownEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\x04:\x02\x38\x01\"\xad\x01\n\x0eStatusResponse\x12,\n\x05state\x18\x01 \x01(\x0e\x32\x1d.backend.StatusResponse.State\x12(\n\x06memory\x18\x02 \x01(\x0b\x32\x18.backend.MemoryUsageData\"C\n\x05State\x12\x11\n\rUNINITIALIZED\x10\x00\x12\x08\n\x04\x42USY\x10\x01\x12\t\n\x05READY\x10\x02\x12\x12\n\x05\x45RROR\x10\xff\xff\xff\xff\xff\xff\xff\xff\xff\x01\">\n\x07Message\x12\x0c\n\x04Role\x18\x01 \x01(\t\x12%\n\x07\x43ontent\x18\x02 \x01(\x0b\x32\x14.google.protobuf.Any2\xfb\x06\n\x07\x42\x61\x63kend\x12\x32\n\x06Health\x12\x16.backend.HealthMessage\x1a\x0e.backend.Reply\"\x00\x12\x34\n\x07Predict\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x12\x35\n\tLoadModel\x12\x15.backend.ModelOptions\x1a\x0f.backend.Result\"\x00\x12<\n\rPredictStream\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x30\x01\x12@\n\tEmbedding\x12\x17.backend.PredictOptions\x1a\x18.backend.EmbeddingResult\"\x00\x12\x41\n\rGenerateImage\x12\x1d.backend.GenerateImageRequest\x1a\x0f.backend.Result\"\x00\x12M\n\x12\x41udioTranscription\x12\x1a.backend.TranscriptRequest\x1a\x19.backend.TranscriptResult\"\x00\x12-\n\x03TTS\x12\x13.backend.TTSRequest\x1a\x0f.backend.Result\"\x00\x12J\n\x0eTokenizeString\x12\x17.backend.PredictOptions\x1a\x1d.backend.TokenizationResponse\"\x00\x12;\n\x06Status\x12\x16.backend.HealthMessage\x1a\x17.backend.StatusResponse\"\x00\x12\x39\n\tStoresSet\x12\x19.backend.StoresSetOptions\x1a\x0f.backend.Result\"\x00\x12?\n\x0cStoresDelete\x12\x1c.backend.StoresDeleteOptions\x1a\x0f.backend.Result\"\x00\x12\x42\n\tStoresGet\x12\x19.backend.StoresGetOptions\x1a\x18.backend.StoresGetResult\"\x00\x12\x45\n\nStoresFind\x12\x1a.backend.StoresFindOptions\x1a\x19.backend.StoresFindResult\"\x00\x42Z\n\x19io.skynet.localai.backendB\x0eLocalAIBackendP\x01Z+github.com/go-skynet/LocalAI/pkg/grpc/protob\x06proto3')
 
 _globals = globals()
 _builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, _globals)
 _builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, 'backend_pb2', _globals)
 if _descriptor._USE_C_DESCRIPTORS == False:
-
-  DESCRIPTOR._options = None
-  DESCRIPTOR._serialized_options = b'\n\031io.skynet.localai.backendB\016LocalAIBackendP\001Z+github.com/go-skynet/LocalAI/pkg/grpc/proto'
-  _MEMORYUSAGEDATA_BREAKDOWNENTRY._options = None
-  _MEMORYUSAGEDATA_BREAKDOWNENTRY._serialized_options = b'8\001'
-  _globals['_HEALTHMESSAGE']._serialized_start=26
-  _globals['_HEALTHMESSAGE']._serialized_end=41
-  _globals['_PREDICTOPTIONS']._serialized_start=44
-  _globals['_PREDICTOPTIONS']._serialized_end=850
-  _globals['_REPLY']._serialized_start=852
-  _globals['_REPLY']._serialized_end=876
-  _globals['_MODELOPTIONS']._serialized_start=879
-  _globals['_MODELOPTIONS']._serialized_end=1951
-  _globals['_RESULT']._serialized_start=1953
-  _globals['_RESULT']._serialized_end=1995
-  _globals['_EMBEDDINGRESULT']._serialized_start=1997
-  _globals['_EMBEDDINGRESULT']._serialized_end=2034
-  _globals['_TRANSCRIPTREQUEST']._serialized_start=2036
-  _globals['_TRANSCRIPTREQUEST']._serialized_end=2103
-  _globals['_TRANSCRIPTRESULT']._serialized_start=2105
-  _globals['_TRANSCRIPTRESULT']._serialized_end=2183
-  _globals['_TRANSCRIPTSEGMENT']._serialized_start=2185
-  _globals['_TRANSCRIPTSEGMENT']._serialized_end=2274
-  _globals['_GENERATEIMAGEREQUEST']._serialized_start=2277
-  _globals['_GENERATEIMAGEREQUEST']._serialized_end=2492
-  _globals['_TTSREQUEST']._serialized_start=2494
-  _globals['_TTSREQUEST']._serialized_end=2563
-  _globals['_TOKENIZATIONRESPONSE']._serialized_start=2565
-  _globals['_TOKENIZATIONRESPONSE']._serialized_end=2619
-  _globals['_MEMORYUSAGEDATA']._serialized_start=2622
-  _globals['_MEMORYUSAGEDATA']._serialized_end=2764
-  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_start=2716
-  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_end=2764
-  _globals['_STATUSRESPONSE']._serialized_start=2767
-  _globals['_STATUSRESPONSE']._serialized_end=2940
-  _globals['_STATUSRESPONSE_STATE']._serialized_start=2873
-  _globals['_STATUSRESPONSE_STATE']._serialized_end=2940
-  _globals['_BACKEND']._serialized_start=2943
-  _globals['_BACKEND']._serialized_end=3571
+  _globals['DESCRIPTOR']._options = None
+  _globals['DESCRIPTOR']._serialized_options = b'\n\031io.skynet.localai.backendB\016LocalAIBackendP\001Z+github.com/go-skynet/LocalAI/pkg/grpc/proto'
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._options = None
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_options = b'8\001'
+  _globals['_STORESKEY']._serialized_start=53
+  _globals['_STORESKEY']._serialized_end=80
+  _globals['_STORESVALUE']._serialized_start=82
+  _globals['_STORESVALUE']._serialized_end=110
+  _globals['_STORESSETOPTIONS']._serialized_start=112
+  _globals['_STORESSETOPTIONS']._serialized_end=202
+  _globals['_STORESDELETEOPTIONS']._serialized_start=204
+  _globals['_STORESDELETEOPTIONS']._serialized_end=259
+  _globals['_STORESGETOPTIONS']._serialized_start=261
+  _globals['_STORESGETOPTIONS']._serialized_end=313
+  _globals['_STORESGETRESULT']._serialized_start=315
+  _globals['_STORESGETRESULT']._serialized_end=404
+  _globals['_STORESFINDOPTIONS']._serialized_start=406
+  _globals['_STORESFINDOPTIONS']._serialized_end=472
+  _globals['_STORESFINDRESULT']._serialized_start=474
+  _globals['_STORESFINDRESULT']._serialized_end=586
+  _globals['_HEALTHMESSAGE']._serialized_start=588
+  _globals['_HEALTHMESSAGE']._serialized_end=603
+  _globals['_PREDICTOPTIONS']._serialized_start=606
+  _globals['_PREDICTOPTIONS']._serialized_end=1478
+  _globals['_REPLY']._serialized_start=1480
+  _globals['_REPLY']._serialized_end=1504
+  _globals['_MODELOPTIONS']._serialized_start=1507
+  _globals['_MODELOPTIONS']._serialized_end=2579
+  _globals['_RESULT']._serialized_start=2581
+  _globals['_RESULT']._serialized_end=2623
+  _globals['_EMBEDDINGRESULT']._serialized_start=2625
+  _globals['_EMBEDDINGRESULT']._serialized_end=2662
+  _globals['_TRANSCRIPTREQUEST']._serialized_start=2664
+  _globals['_TRANSCRIPTREQUEST']._serialized_end=2731
+  _globals['_TRANSCRIPTRESULT']._serialized_start=2733
+  _globals['_TRANSCRIPTRESULT']._serialized_end=2811
+  _globals['_TRANSCRIPTSEGMENT']._serialized_start=2813
+  _globals['_TRANSCRIPTSEGMENT']._serialized_end=2902
+  _globals['_GENERATEIMAGEREQUEST']._serialized_start=2905
+  _globals['_GENERATEIMAGEREQUEST']._serialized_end=3120
+  _globals['_TTSREQUEST']._serialized_start=3122
+  _globals['_TTSREQUEST']._serialized_end=3191
+  _globals['_TOKENIZATIONRESPONSE']._serialized_start=3193
+  _globals['_TOKENIZATIONRESPONSE']._serialized_end=3247
+  _globals['_MEMORYUSAGEDATA']._serialized_start=3250
+  _globals['_MEMORYUSAGEDATA']._serialized_end=3392
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_start=3344
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_end=3392
+  _globals['_STATUSRESPONSE']._serialized_start=3395
+  _globals['_STATUSRESPONSE']._serialized_end=3568
+  _globals['_STATUSRESPONSE_STATE']._serialized_start=3501
+  _globals['_STATUSRESPONSE_STATE']._serialized_end=3568
+  _globals['_MESSAGE']._serialized_start=3570
+  _globals['_MESSAGE']._serialized_end=3632
+  _globals['_BACKEND']._serialized_start=3635
+  _globals['_BACKEND']._serialized_end=4526
 # @@protoc_insertion_point(module_scope)
diff --git a/backend/python/petals/backend_pb2_grpc.py b/backend/python/petals/backend_pb2_grpc.py
index 79a7677fb27f..e06fccf3d451 100644
--- a/backend/python/petals/backend_pb2_grpc.py
+++ b/backend/python/petals/backend_pb2_grpc.py
@@ -64,6 +64,26 @@ def __init__(self, channel):
                 request_serializer=backend__pb2.HealthMessage.SerializeToString,
                 response_deserializer=backend__pb2.StatusResponse.FromString,
                 )
+        self.StoresSet = channel.unary_unary(
+                '/backend.Backend/StoresSet',
+                request_serializer=backend__pb2.StoresSetOptions.SerializeToString,
+                response_deserializer=backend__pb2.Result.FromString,
+                )
+        self.StoresDelete = channel.unary_unary(
+                '/backend.Backend/StoresDelete',
+                request_serializer=backend__pb2.StoresDeleteOptions.SerializeToString,
+                response_deserializer=backend__pb2.Result.FromString,
+                )
+        self.StoresGet = channel.unary_unary(
+                '/backend.Backend/StoresGet',
+                request_serializer=backend__pb2.StoresGetOptions.SerializeToString,
+                response_deserializer=backend__pb2.StoresGetResult.FromString,
+                )
+        self.StoresFind = channel.unary_unary(
+                '/backend.Backend/StoresFind',
+                request_serializer=backend__pb2.StoresFindOptions.SerializeToString,
+                response_deserializer=backend__pb2.StoresFindResult.FromString,
+                )
 
 
 class BackendServicer(object):
@@ -129,6 +149,30 @@ def Status(self, request, context):
         context.set_details('Method not implemented!')
         raise NotImplementedError('Method not implemented!')
 
+    def StoresSet(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresDelete(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresGet(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresFind(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
 
 def add_BackendServicer_to_server(servicer, server):
     rpc_method_handlers = {
@@ -182,6 +226,26 @@ def add_BackendServicer_to_server(servicer, server):
                     request_deserializer=backend__pb2.HealthMessage.FromString,
                     response_serializer=backend__pb2.StatusResponse.SerializeToString,
             ),
+            'StoresSet': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresSet,
+                    request_deserializer=backend__pb2.StoresSetOptions.FromString,
+                    response_serializer=backend__pb2.Result.SerializeToString,
+            ),
+            'StoresDelete': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresDelete,
+                    request_deserializer=backend__pb2.StoresDeleteOptions.FromString,
+                    response_serializer=backend__pb2.Result.SerializeToString,
+            ),
+            'StoresGet': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresGet,
+                    request_deserializer=backend__pb2.StoresGetOptions.FromString,
+                    response_serializer=backend__pb2.StoresGetResult.SerializeToString,
+            ),
+            'StoresFind': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresFind,
+                    request_deserializer=backend__pb2.StoresFindOptions.FromString,
+                    response_serializer=backend__pb2.StoresFindResult.SerializeToString,
+            ),
     }
     generic_handler = grpc.method_handlers_generic_handler(
             'backend.Backend', rpc_method_handlers)
@@ -361,3 +425,71 @@ def Status(request,
             backend__pb2.StatusResponse.FromString,
             options, channel_credentials,
             insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresSet(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresSet',
+            backend__pb2.StoresSetOptions.SerializeToString,
+            backend__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresDelete(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresDelete',
+            backend__pb2.StoresDeleteOptions.SerializeToString,
+            backend__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresGet(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresGet',
+            backend__pb2.StoresGetOptions.SerializeToString,
+            backend__pb2.StoresGetResult.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresFind(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresFind',
+            backend__pb2.StoresFindOptions.SerializeToString,
+            backend__pb2.StoresFindResult.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
diff --git a/backend/python/sentencetransformers/backend_pb2.py b/backend/python/sentencetransformers/backend_pb2.py
index 08b896c7cad5..8d366c16d63b 100644
--- a/backend/python/sentencetransformers/backend_pb2.py
+++ b/backend/python/sentencetransformers/backend_pb2.py
@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 # Generated by the protocol buffer compiler.  DO NOT EDIT!
 # source: backend.proto
+# Protobuf Python Version: 4.25.1
 """Generated protocol buffer code."""
 from google.protobuf import descriptor as _descriptor
 from google.protobuf import descriptor_pool as _descriptor_pool
@@ -11,51 +12,69 @@
 _sym_db = _symbol_database.Default()
 
 
+from google.protobuf import any_pb2 as google_dot_protobuf_dot_any__pb2
 
 
-DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\rbackend.proto\x12\x07\x62\x61\x63kend\"\x0f\n\rHealthMessage\"\xa6\x06\n\x0ePredictOptions\x12\x0e\n\x06Prompt\x18\x01 \x01(\t\x12\x0c\n\x04Seed\x18\x02 \x01(\x05\x12\x0f\n\x07Threads\x18\x03 \x01(\x05\x12\x0e\n\x06Tokens\x18\x04 \x01(\x05\x12\x0c\n\x04TopK\x18\x05 \x01(\x05\x12\x0e\n\x06Repeat\x18\x06 \x01(\x05\x12\r\n\x05\x42\x61tch\x18\x07 \x01(\x05\x12\r\n\x05NKeep\x18\x08 \x01(\x05\x12\x13\n\x0bTemperature\x18\t \x01(\x02\x12\x0f\n\x07Penalty\x18\n \x01(\x02\x12\r\n\x05\x46\x31\x36KV\x18\x0b \x01(\x08\x12\x11\n\tDebugMode\x18\x0c \x01(\x08\x12\x13\n\x0bStopPrompts\x18\r \x03(\t\x12\x11\n\tIgnoreEOS\x18\x0e \x01(\x08\x12\x19\n\x11TailFreeSamplingZ\x18\x0f \x01(\x02\x12\x10\n\x08TypicalP\x18\x10 \x01(\x02\x12\x18\n\x10\x46requencyPenalty\x18\x11 \x01(\x02\x12\x17\n\x0fPresencePenalty\x18\x12 \x01(\x02\x12\x10\n\x08Mirostat\x18\x13 \x01(\x05\x12\x13\n\x0bMirostatETA\x18\x14 \x01(\x02\x12\x13\n\x0bMirostatTAU\x18\x15 \x01(\x02\x12\x12\n\nPenalizeNL\x18\x16 \x01(\x08\x12\x11\n\tLogitBias\x18\x17 \x01(\t\x12\r\n\x05MLock\x18\x19 \x01(\x08\x12\x0c\n\x04MMap\x18\x1a \x01(\x08\x12\x16\n\x0ePromptCacheAll\x18\x1b \x01(\x08\x12\x15\n\rPromptCacheRO\x18\x1c \x01(\x08\x12\x0f\n\x07Grammar\x18\x1d \x01(\t\x12\x0f\n\x07MainGPU\x18\x1e \x01(\t\x12\x13\n\x0bTensorSplit\x18\x1f \x01(\t\x12\x0c\n\x04TopP\x18  \x01(\x02\x12\x17\n\x0fPromptCachePath\x18! \x01(\t\x12\r\n\x05\x44\x65\x62ug\x18\" \x01(\x08\x12\x17\n\x0f\x45mbeddingTokens\x18# \x03(\x05\x12\x12\n\nEmbeddings\x18$ \x01(\t\x12\x14\n\x0cRopeFreqBase\x18% \x01(\x02\x12\x15\n\rRopeFreqScale\x18& \x01(\x02\x12\x1b\n\x13NegativePromptScale\x18\' \x01(\x02\x12\x16\n\x0eNegativePrompt\x18( \x01(\t\x12\x0e\n\x06NDraft\x18) \x01(\x05\x12\x0e\n\x06Images\x18* \x03(\t\"\x18\n\x05Reply\x12\x0f\n\x07message\x18\x01 \x01(\x0c\"\xb0\x08\n\x0cModelOptions\x12\r\n\x05Model\x18\x01 \x01(\t\x12\x13\n\x0b\x43ontextSize\x18\x02 \x01(\x05\x12\x0c\n\x04Seed\x18\x03 \x01(\x05\x12\x0e\n\x06NBatch\x18\x04 \x01(\x05\x12\x11\n\tF16Memory\x18\x05 \x01(\x08\x12\r\n\x05MLock\x18\x06 \x01(\x08\x12\x0c\n\x04MMap\x18\x07 \x01(\x08\x12\x11\n\tVocabOnly\x18\x08 \x01(\x08\x12\x0f\n\x07LowVRAM\x18\t \x01(\x08\x12\x12\n\nEmbeddings\x18\n \x01(\x08\x12\x0c\n\x04NUMA\x18\x0b \x01(\x08\x12\x12\n\nNGPULayers\x18\x0c \x01(\x05\x12\x0f\n\x07MainGPU\x18\r \x01(\t\x12\x13\n\x0bTensorSplit\x18\x0e \x01(\t\x12\x0f\n\x07Threads\x18\x0f \x01(\x05\x12\x19\n\x11LibrarySearchPath\x18\x10 \x01(\t\x12\x14\n\x0cRopeFreqBase\x18\x11 \x01(\x02\x12\x15\n\rRopeFreqScale\x18\x12 \x01(\x02\x12\x12\n\nRMSNormEps\x18\x13 \x01(\x02\x12\x0c\n\x04NGQA\x18\x14 \x01(\x05\x12\x11\n\tModelFile\x18\x15 \x01(\t\x12\x0e\n\x06\x44\x65vice\x18\x16 \x01(\t\x12\x11\n\tUseTriton\x18\x17 \x01(\x08\x12\x15\n\rModelBaseName\x18\x18 \x01(\t\x12\x18\n\x10UseFastTokenizer\x18\x19 \x01(\x08\x12\x14\n\x0cPipelineType\x18\x1a \x01(\t\x12\x15\n\rSchedulerType\x18\x1b \x01(\t\x12\x0c\n\x04\x43UDA\x18\x1c \x01(\x08\x12\x10\n\x08\x43\x46GScale\x18\x1d \x01(\x02\x12\x0f\n\x07IMG2IMG\x18\x1e \x01(\x08\x12\x11\n\tCLIPModel\x18\x1f \x01(\t\x12\x15\n\rCLIPSubfolder\x18  \x01(\t\x12\x10\n\x08\x43LIPSkip\x18! \x01(\x05\x12\x12\n\nControlNet\x18\x30 \x01(\t\x12\x11\n\tTokenizer\x18\" \x01(\t\x12\x10\n\x08LoraBase\x18# \x01(\t\x12\x13\n\x0bLoraAdapter\x18$ \x01(\t\x12\x11\n\tLoraScale\x18* \x01(\x02\x12\x11\n\tNoMulMatQ\x18% \x01(\x08\x12\x12\n\nDraftModel\x18\' \x01(\t\x12\x11\n\tAudioPath\x18& \x01(\t\x12\x14\n\x0cQuantization\x18( \x01(\t\x12\x1c\n\x14GPUMemoryUtilization\x18\x32 \x01(\x02\x12\x17\n\x0fTrustRemoteCode\x18\x33 \x01(\x08\x12\x14\n\x0c\x45nforceEager\x18\x34 \x01(\x08\x12\x11\n\tSwapSpace\x18\x35 \x01(\x05\x12\x13\n\x0bMaxModelLen\x18\x36 \x01(\x05\x12\x0e\n\x06MMProj\x18) \x01(\t\x12\x13\n\x0bRopeScaling\x18+ \x01(\t\x12\x15\n\rYarnExtFactor\x18, \x01(\x02\x12\x16\n\x0eYarnAttnFactor\x18- \x01(\x02\x12\x14\n\x0cYarnBetaFast\x18. \x01(\x02\x12\x14\n\x0cYarnBetaSlow\x18/ \x01(\x02\x12\x0c\n\x04Type\x18\x31 \x01(\t\"*\n\x06Result\x12\x0f\n\x07message\x18\x01 \x01(\t\x12\x0f\n\x07success\x18\x02 \x01(\x08\"%\n\x0f\x45mbeddingResult\x12\x12\n\nembeddings\x18\x01 \x03(\x02\"C\n\x11TranscriptRequest\x12\x0b\n\x03\x64st\x18\x02 \x01(\t\x12\x10\n\x08language\x18\x03 \x01(\t\x12\x0f\n\x07threads\x18\x04 \x01(\r\"N\n\x10TranscriptResult\x12,\n\x08segments\x18\x01 \x03(\x0b\x32\x1a.backend.TranscriptSegment\x12\x0c\n\x04text\x18\x02 \x01(\t\"Y\n\x11TranscriptSegment\x12\n\n\x02id\x18\x01 \x01(\x05\x12\r\n\x05start\x18\x02 \x01(\x03\x12\x0b\n\x03\x65nd\x18\x03 \x01(\x03\x12\x0c\n\x04text\x18\x04 \x01(\t\x12\x0e\n\x06tokens\x18\x05 \x03(\x05\"\xd7\x01\n\x14GenerateImageRequest\x12\x0e\n\x06height\x18\x01 \x01(\x05\x12\r\n\x05width\x18\x02 \x01(\x05\x12\x0c\n\x04mode\x18\x03 \x01(\x05\x12\x0c\n\x04step\x18\x04 \x01(\x05\x12\x0c\n\x04seed\x18\x05 \x01(\x05\x12\x17\n\x0fpositive_prompt\x18\x06 \x01(\t\x12\x17\n\x0fnegative_prompt\x18\x07 \x01(\t\x12\x0b\n\x03\x64st\x18\x08 \x01(\t\x12\x0b\n\x03src\x18\t \x01(\t\x12\x18\n\x10\x45nableParameters\x18\n \x01(\t\x12\x10\n\x08\x43LIPSkip\x18\x0b \x01(\x05\"E\n\nTTSRequest\x12\x0c\n\x04text\x18\x01 \x01(\t\x12\r\n\x05model\x18\x02 \x01(\t\x12\x0b\n\x03\x64st\x18\x03 \x01(\t\x12\r\n\x05voice\x18\x04 \x01(\t\"6\n\x14TokenizationResponse\x12\x0e\n\x06length\x18\x01 \x01(\x05\x12\x0e\n\x06tokens\x18\x02 \x03(\x05\"\x8e\x01\n\x0fMemoryUsageData\x12\r\n\x05total\x18\x01 \x01(\x04\x12:\n\tbreakdown\x18\x02 \x03(\x0b\x32\'.backend.MemoryUsageData.BreakdownEntry\x1a\x30\n\x0e\x42reakdownEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\x04:\x02\x38\x01\"\xad\x01\n\x0eStatusResponse\x12,\n\x05state\x18\x01 \x01(\x0e\x32\x1d.backend.StatusResponse.State\x12(\n\x06memory\x18\x02 \x01(\x0b\x32\x18.backend.MemoryUsageData\"C\n\x05State\x12\x11\n\rUNINITIALIZED\x10\x00\x12\x08\n\x04\x42USY\x10\x01\x12\t\n\x05READY\x10\x02\x12\x12\n\x05\x45RROR\x10\xff\xff\xff\xff\xff\xff\xff\xff\xff\x01\x32\xf4\x04\n\x07\x42\x61\x63kend\x12\x32\n\x06Health\x12\x16.backend.HealthMessage\x1a\x0e.backend.Reply\"\x00\x12\x34\n\x07Predict\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x12\x35\n\tLoadModel\x12\x15.backend.ModelOptions\x1a\x0f.backend.Result\"\x00\x12<\n\rPredictStream\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x30\x01\x12@\n\tEmbedding\x12\x17.backend.PredictOptions\x1a\x18.backend.EmbeddingResult\"\x00\x12\x41\n\rGenerateImage\x12\x1d.backend.GenerateImageRequest\x1a\x0f.backend.Result\"\x00\x12M\n\x12\x41udioTranscription\x12\x1a.backend.TranscriptRequest\x1a\x19.backend.TranscriptResult\"\x00\x12-\n\x03TTS\x12\x13.backend.TTSRequest\x1a\x0f.backend.Result\"\x00\x12J\n\x0eTokenizeString\x12\x17.backend.PredictOptions\x1a\x1d.backend.TokenizationResponse\"\x00\x12;\n\x06Status\x12\x16.backend.HealthMessage\x1a\x17.backend.StatusResponse\"\x00\x42Z\n\x19io.skynet.localai.backendB\x0eLocalAIBackendP\x01Z+github.com/go-skynet/LocalAI/pkg/grpc/protob\x06proto3')
+DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\rbackend.proto\x12\x07\x62\x61\x63kend\x1a\x19google/protobuf/any.proto\"\x1b\n\tStoresKey\x12\x0e\n\x06\x46loats\x18\x01 \x03(\x02\"\x1c\n\x0bStoresValue\x12\r\n\x05\x42ytes\x18\x01 \x01(\x0c\"Z\n\x10StoresSetOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\"7\n\x13StoresDeleteOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\"4\n\x10StoresGetOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\"Y\n\x0fStoresGetResult\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\"B\n\x11StoresFindOptions\x12\x1f\n\x03Key\x18\x01 \x01(\x0b\x32\x12.backend.StoresKey\x12\x0c\n\x04TopK\x18\x02 \x01(\x05\"p\n\x10StoresFindResult\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\x12\x14\n\x0cSimilarities\x18\x03 \x03(\x02\"\x0f\n\rHealthMessage\"\xe8\x06\n\x0ePredictOptions\x12\x0e\n\x06Prompt\x18\x01 \x01(\t\x12\x0c\n\x04Seed\x18\x02 \x01(\x05\x12\x0f\n\x07Threads\x18\x03 \x01(\x05\x12\x0e\n\x06Tokens\x18\x04 \x01(\x05\x12\x0c\n\x04TopK\x18\x05 \x01(\x05\x12\x0e\n\x06Repeat\x18\x06 \x01(\x05\x12\r\n\x05\x42\x61tch\x18\x07 \x01(\x05\x12\r\n\x05NKeep\x18\x08 \x01(\x05\x12\x13\n\x0bTemperature\x18\t \x01(\x02\x12\x0f\n\x07Penalty\x18\n \x01(\x02\x12\r\n\x05\x46\x31\x36KV\x18\x0b \x01(\x08\x12\x11\n\tDebugMode\x18\x0c \x01(\x08\x12\x13\n\x0bStopPrompts\x18\r \x03(\t\x12\x11\n\tIgnoreEOS\x18\x0e \x01(\x08\x12\x19\n\x11TailFreeSamplingZ\x18\x0f \x01(\x02\x12\x10\n\x08TypicalP\x18\x10 \x01(\x02\x12\x18\n\x10\x46requencyPenalty\x18\x11 \x01(\x02\x12\x17\n\x0fPresencePenalty\x18\x12 \x01(\x02\x12\x10\n\x08Mirostat\x18\x13 \x01(\x05\x12\x13\n\x0bMirostatETA\x18\x14 \x01(\x02\x12\x13\n\x0bMirostatTAU\x18\x15 \x01(\x02\x12\x12\n\nPenalizeNL\x18\x16 \x01(\x08\x12\x11\n\tLogitBias\x18\x17 \x01(\t\x12\r\n\x05MLock\x18\x19 \x01(\x08\x12\x0c\n\x04MMap\x18\x1a \x01(\x08\x12\x16\n\x0ePromptCacheAll\x18\x1b \x01(\x08\x12\x15\n\rPromptCacheRO\x18\x1c \x01(\x08\x12\x0f\n\x07Grammar\x18\x1d \x01(\t\x12\x0f\n\x07MainGPU\x18\x1e \x01(\t\x12\x13\n\x0bTensorSplit\x18\x1f \x01(\t\x12\x0c\n\x04TopP\x18  \x01(\x02\x12\x17\n\x0fPromptCachePath\x18! \x01(\t\x12\r\n\x05\x44\x65\x62ug\x18\" \x01(\x08\x12\x17\n\x0f\x45mbeddingTokens\x18# \x03(\x05\x12\x12\n\nEmbeddings\x18$ \x01(\t\x12\x14\n\x0cRopeFreqBase\x18% \x01(\x02\x12\x15\n\rRopeFreqScale\x18& \x01(\x02\x12\x1b\n\x13NegativePromptScale\x18\' \x01(\x02\x12\x16\n\x0eNegativePrompt\x18( \x01(\t\x12\x0e\n\x06NDraft\x18) \x01(\x05\x12\x0e\n\x06Images\x18* \x03(\t\x12\x1c\n\x14UseTokenizerTemplate\x18+ \x01(\x08\x12\"\n\x08Messages\x18, \x03(\x0b\x32\x10.backend.Message\"\x18\n\x05Reply\x12\x0f\n\x07message\x18\x01 \x01(\x0c\"\xb0\x08\n\x0cModelOptions\x12\r\n\x05Model\x18\x01 \x01(\t\x12\x13\n\x0b\x43ontextSize\x18\x02 \x01(\x05\x12\x0c\n\x04Seed\x18\x03 \x01(\x05\x12\x0e\n\x06NBatch\x18\x04 \x01(\x05\x12\x11\n\tF16Memory\x18\x05 \x01(\x08\x12\r\n\x05MLock\x18\x06 \x01(\x08\x12\x0c\n\x04MMap\x18\x07 \x01(\x08\x12\x11\n\tVocabOnly\x18\x08 \x01(\x08\x12\x0f\n\x07LowVRAM\x18\t \x01(\x08\x12\x12\n\nEmbeddings\x18\n \x01(\x08\x12\x0c\n\x04NUMA\x18\x0b \x01(\x08\x12\x12\n\nNGPULayers\x18\x0c \x01(\x05\x12\x0f\n\x07MainGPU\x18\r \x01(\t\x12\x13\n\x0bTensorSplit\x18\x0e \x01(\t\x12\x0f\n\x07Threads\x18\x0f \x01(\x05\x12\x19\n\x11LibrarySearchPath\x18\x10 \x01(\t\x12\x14\n\x0cRopeFreqBase\x18\x11 \x01(\x02\x12\x15\n\rRopeFreqScale\x18\x12 \x01(\x02\x12\x12\n\nRMSNormEps\x18\x13 \x01(\x02\x12\x0c\n\x04NGQA\x18\x14 \x01(\x05\x12\x11\n\tModelFile\x18\x15 \x01(\t\x12\x0e\n\x06\x44\x65vice\x18\x16 \x01(\t\x12\x11\n\tUseTriton\x18\x17 \x01(\x08\x12\x15\n\rModelBaseName\x18\x18 \x01(\t\x12\x18\n\x10UseFastTokenizer\x18\x19 \x01(\x08\x12\x14\n\x0cPipelineType\x18\x1a \x01(\t\x12\x15\n\rSchedulerType\x18\x1b \x01(\t\x12\x0c\n\x04\x43UDA\x18\x1c \x01(\x08\x12\x10\n\x08\x43\x46GScale\x18\x1d \x01(\x02\x12\x0f\n\x07IMG2IMG\x18\x1e \x01(\x08\x12\x11\n\tCLIPModel\x18\x1f \x01(\t\x12\x15\n\rCLIPSubfolder\x18  \x01(\t\x12\x10\n\x08\x43LIPSkip\x18! \x01(\x05\x12\x12\n\nControlNet\x18\x30 \x01(\t\x12\x11\n\tTokenizer\x18\" \x01(\t\x12\x10\n\x08LoraBase\x18# \x01(\t\x12\x13\n\x0bLoraAdapter\x18$ \x01(\t\x12\x11\n\tLoraScale\x18* \x01(\x02\x12\x11\n\tNoMulMatQ\x18% \x01(\x08\x12\x12\n\nDraftModel\x18\' \x01(\t\x12\x11\n\tAudioPath\x18& \x01(\t\x12\x14\n\x0cQuantization\x18( \x01(\t\x12\x1c\n\x14GPUMemoryUtilization\x18\x32 \x01(\x02\x12\x17\n\x0fTrustRemoteCode\x18\x33 \x01(\x08\x12\x14\n\x0c\x45nforceEager\x18\x34 \x01(\x08\x12\x11\n\tSwapSpace\x18\x35 \x01(\x05\x12\x13\n\x0bMaxModelLen\x18\x36 \x01(\x05\x12\x0e\n\x06MMProj\x18) \x01(\t\x12\x13\n\x0bRopeScaling\x18+ \x01(\t\x12\x15\n\rYarnExtFactor\x18, \x01(\x02\x12\x16\n\x0eYarnAttnFactor\x18- \x01(\x02\x12\x14\n\x0cYarnBetaFast\x18. \x01(\x02\x12\x14\n\x0cYarnBetaSlow\x18/ \x01(\x02\x12\x0c\n\x04Type\x18\x31 \x01(\t\"*\n\x06Result\x12\x0f\n\x07message\x18\x01 \x01(\t\x12\x0f\n\x07success\x18\x02 \x01(\x08\"%\n\x0f\x45mbeddingResult\x12\x12\n\nembeddings\x18\x01 \x03(\x02\"C\n\x11TranscriptRequest\x12\x0b\n\x03\x64st\x18\x02 \x01(\t\x12\x10\n\x08language\x18\x03 \x01(\t\x12\x0f\n\x07threads\x18\x04 \x01(\r\"N\n\x10TranscriptResult\x12,\n\x08segments\x18\x01 \x03(\x0b\x32\x1a.backend.TranscriptSegment\x12\x0c\n\x04text\x18\x02 \x01(\t\"Y\n\x11TranscriptSegment\x12\n\n\x02id\x18\x01 \x01(\x05\x12\r\n\x05start\x18\x02 \x01(\x03\x12\x0b\n\x03\x65nd\x18\x03 \x01(\x03\x12\x0c\n\x04text\x18\x04 \x01(\t\x12\x0e\n\x06tokens\x18\x05 \x03(\x05\"\xd7\x01\n\x14GenerateImageRequest\x12\x0e\n\x06height\x18\x01 \x01(\x05\x12\r\n\x05width\x18\x02 \x01(\x05\x12\x0c\n\x04mode\x18\x03 \x01(\x05\x12\x0c\n\x04step\x18\x04 \x01(\x05\x12\x0c\n\x04seed\x18\x05 \x01(\x05\x12\x17\n\x0fpositive_prompt\x18\x06 \x01(\t\x12\x17\n\x0fnegative_prompt\x18\x07 \x01(\t\x12\x0b\n\x03\x64st\x18\x08 \x01(\t\x12\x0b\n\x03src\x18\t \x01(\t\x12\x18\n\x10\x45nableParameters\x18\n \x01(\t\x12\x10\n\x08\x43LIPSkip\x18\x0b \x01(\x05\"E\n\nTTSRequest\x12\x0c\n\x04text\x18\x01 \x01(\t\x12\r\n\x05model\x18\x02 \x01(\t\x12\x0b\n\x03\x64st\x18\x03 \x01(\t\x12\r\n\x05voice\x18\x04 \x01(\t\"6\n\x14TokenizationResponse\x12\x0e\n\x06length\x18\x01 \x01(\x05\x12\x0e\n\x06tokens\x18\x02 \x03(\x05\"\x8e\x01\n\x0fMemoryUsageData\x12\r\n\x05total\x18\x01 \x01(\x04\x12:\n\tbreakdown\x18\x02 \x03(\x0b\x32\'.backend.MemoryUsageData.BreakdownEntry\x1a\x30\n\x0e\x42reakdownEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\x04:\x02\x38\x01\"\xad\x01\n\x0eStatusResponse\x12,\n\x05state\x18\x01 \x01(\x0e\x32\x1d.backend.StatusResponse.State\x12(\n\x06memory\x18\x02 \x01(\x0b\x32\x18.backend.MemoryUsageData\"C\n\x05State\x12\x11\n\rUNINITIALIZED\x10\x00\x12\x08\n\x04\x42USY\x10\x01\x12\t\n\x05READY\x10\x02\x12\x12\n\x05\x45RROR\x10\xff\xff\xff\xff\xff\xff\xff\xff\xff\x01\">\n\x07Message\x12\x0c\n\x04Role\x18\x01 \x01(\t\x12%\n\x07\x43ontent\x18\x02 \x01(\x0b\x32\x14.google.protobuf.Any2\xfb\x06\n\x07\x42\x61\x63kend\x12\x32\n\x06Health\x12\x16.backend.HealthMessage\x1a\x0e.backend.Reply\"\x00\x12\x34\n\x07Predict\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x12\x35\n\tLoadModel\x12\x15.backend.ModelOptions\x1a\x0f.backend.Result\"\x00\x12<\n\rPredictStream\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x30\x01\x12@\n\tEmbedding\x12\x17.backend.PredictOptions\x1a\x18.backend.EmbeddingResult\"\x00\x12\x41\n\rGenerateImage\x12\x1d.backend.GenerateImageRequest\x1a\x0f.backend.Result\"\x00\x12M\n\x12\x41udioTranscription\x12\x1a.backend.TranscriptRequest\x1a\x19.backend.TranscriptResult\"\x00\x12-\n\x03TTS\x12\x13.backend.TTSRequest\x1a\x0f.backend.Result\"\x00\x12J\n\x0eTokenizeString\x12\x17.backend.PredictOptions\x1a\x1d.backend.TokenizationResponse\"\x00\x12;\n\x06Status\x12\x16.backend.HealthMessage\x1a\x17.backend.StatusResponse\"\x00\x12\x39\n\tStoresSet\x12\x19.backend.StoresSetOptions\x1a\x0f.backend.Result\"\x00\x12?\n\x0cStoresDelete\x12\x1c.backend.StoresDeleteOptions\x1a\x0f.backend.Result\"\x00\x12\x42\n\tStoresGet\x12\x19.backend.StoresGetOptions\x1a\x18.backend.StoresGetResult\"\x00\x12\x45\n\nStoresFind\x12\x1a.backend.StoresFindOptions\x1a\x19.backend.StoresFindResult\"\x00\x42Z\n\x19io.skynet.localai.backendB\x0eLocalAIBackendP\x01Z+github.com/go-skynet/LocalAI/pkg/grpc/protob\x06proto3')
 
 _globals = globals()
 _builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, _globals)
 _builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, 'backend_pb2', _globals)
 if _descriptor._USE_C_DESCRIPTORS == False:
-
-  DESCRIPTOR._options = None
-  DESCRIPTOR._serialized_options = b'\n\031io.skynet.localai.backendB\016LocalAIBackendP\001Z+github.com/go-skynet/LocalAI/pkg/grpc/proto'
-  _MEMORYUSAGEDATA_BREAKDOWNENTRY._options = None
-  _MEMORYUSAGEDATA_BREAKDOWNENTRY._serialized_options = b'8\001'
-  _globals['_HEALTHMESSAGE']._serialized_start=26
-  _globals['_HEALTHMESSAGE']._serialized_end=41
-  _globals['_PREDICTOPTIONS']._serialized_start=44
-  _globals['_PREDICTOPTIONS']._serialized_end=850
-  _globals['_REPLY']._serialized_start=852
-  _globals['_REPLY']._serialized_end=876
-  _globals['_MODELOPTIONS']._serialized_start=879
-  _globals['_MODELOPTIONS']._serialized_end=1951
-  _globals['_RESULT']._serialized_start=1953
-  _globals['_RESULT']._serialized_end=1995
-  _globals['_EMBEDDINGRESULT']._serialized_start=1997
-  _globals['_EMBEDDINGRESULT']._serialized_end=2034
-  _globals['_TRANSCRIPTREQUEST']._serialized_start=2036
-  _globals['_TRANSCRIPTREQUEST']._serialized_end=2103
-  _globals['_TRANSCRIPTRESULT']._serialized_start=2105
-  _globals['_TRANSCRIPTRESULT']._serialized_end=2183
-  _globals['_TRANSCRIPTSEGMENT']._serialized_start=2185
-  _globals['_TRANSCRIPTSEGMENT']._serialized_end=2274
-  _globals['_GENERATEIMAGEREQUEST']._serialized_start=2277
-  _globals['_GENERATEIMAGEREQUEST']._serialized_end=2492
-  _globals['_TTSREQUEST']._serialized_start=2494
-  _globals['_TTSREQUEST']._serialized_end=2563
-  _globals['_TOKENIZATIONRESPONSE']._serialized_start=2565
-  _globals['_TOKENIZATIONRESPONSE']._serialized_end=2619
-  _globals['_MEMORYUSAGEDATA']._serialized_start=2622
-  _globals['_MEMORYUSAGEDATA']._serialized_end=2764
-  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_start=2716
-  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_end=2764
-  _globals['_STATUSRESPONSE']._serialized_start=2767
-  _globals['_STATUSRESPONSE']._serialized_end=2940
-  _globals['_STATUSRESPONSE_STATE']._serialized_start=2873
-  _globals['_STATUSRESPONSE_STATE']._serialized_end=2940
-  _globals['_BACKEND']._serialized_start=2943
-  _globals['_BACKEND']._serialized_end=3571
+  _globals['DESCRIPTOR']._options = None
+  _globals['DESCRIPTOR']._serialized_options = b'\n\031io.skynet.localai.backendB\016LocalAIBackendP\001Z+github.com/go-skynet/LocalAI/pkg/grpc/proto'
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._options = None
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_options = b'8\001'
+  _globals['_STORESKEY']._serialized_start=53
+  _globals['_STORESKEY']._serialized_end=80
+  _globals['_STORESVALUE']._serialized_start=82
+  _globals['_STORESVALUE']._serialized_end=110
+  _globals['_STORESSETOPTIONS']._serialized_start=112
+  _globals['_STORESSETOPTIONS']._serialized_end=202
+  _globals['_STORESDELETEOPTIONS']._serialized_start=204
+  _globals['_STORESDELETEOPTIONS']._serialized_end=259
+  _globals['_STORESGETOPTIONS']._serialized_start=261
+  _globals['_STORESGETOPTIONS']._serialized_end=313
+  _globals['_STORESGETRESULT']._serialized_start=315
+  _globals['_STORESGETRESULT']._serialized_end=404
+  _globals['_STORESFINDOPTIONS']._serialized_start=406
+  _globals['_STORESFINDOPTIONS']._serialized_end=472
+  _globals['_STORESFINDRESULT']._serialized_start=474
+  _globals['_STORESFINDRESULT']._serialized_end=586
+  _globals['_HEALTHMESSAGE']._serialized_start=588
+  _globals['_HEALTHMESSAGE']._serialized_end=603
+  _globals['_PREDICTOPTIONS']._serialized_start=606
+  _globals['_PREDICTOPTIONS']._serialized_end=1478
+  _globals['_REPLY']._serialized_start=1480
+  _globals['_REPLY']._serialized_end=1504
+  _globals['_MODELOPTIONS']._serialized_start=1507
+  _globals['_MODELOPTIONS']._serialized_end=2579
+  _globals['_RESULT']._serialized_start=2581
+  _globals['_RESULT']._serialized_end=2623
+  _globals['_EMBEDDINGRESULT']._serialized_start=2625
+  _globals['_EMBEDDINGRESULT']._serialized_end=2662
+  _globals['_TRANSCRIPTREQUEST']._serialized_start=2664
+  _globals['_TRANSCRIPTREQUEST']._serialized_end=2731
+  _globals['_TRANSCRIPTRESULT']._serialized_start=2733
+  _globals['_TRANSCRIPTRESULT']._serialized_end=2811
+  _globals['_TRANSCRIPTSEGMENT']._serialized_start=2813
+  _globals['_TRANSCRIPTSEGMENT']._serialized_end=2902
+  _globals['_GENERATEIMAGEREQUEST']._serialized_start=2905
+  _globals['_GENERATEIMAGEREQUEST']._serialized_end=3120
+  _globals['_TTSREQUEST']._serialized_start=3122
+  _globals['_TTSREQUEST']._serialized_end=3191
+  _globals['_TOKENIZATIONRESPONSE']._serialized_start=3193
+  _globals['_TOKENIZATIONRESPONSE']._serialized_end=3247
+  _globals['_MEMORYUSAGEDATA']._serialized_start=3250
+  _globals['_MEMORYUSAGEDATA']._serialized_end=3392
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_start=3344
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_end=3392
+  _globals['_STATUSRESPONSE']._serialized_start=3395
+  _globals['_STATUSRESPONSE']._serialized_end=3568
+  _globals['_STATUSRESPONSE_STATE']._serialized_start=3501
+  _globals['_STATUSRESPONSE_STATE']._serialized_end=3568
+  _globals['_MESSAGE']._serialized_start=3570
+  _globals['_MESSAGE']._serialized_end=3632
+  _globals['_BACKEND']._serialized_start=3635
+  _globals['_BACKEND']._serialized_end=4526
 # @@protoc_insertion_point(module_scope)
diff --git a/backend/python/sentencetransformers/backend_pb2_grpc.py b/backend/python/sentencetransformers/backend_pb2_grpc.py
index 79a7677fb27f..e06fccf3d451 100644
--- a/backend/python/sentencetransformers/backend_pb2_grpc.py
+++ b/backend/python/sentencetransformers/backend_pb2_grpc.py
@@ -64,6 +64,26 @@ def __init__(self, channel):
                 request_serializer=backend__pb2.HealthMessage.SerializeToString,
                 response_deserializer=backend__pb2.StatusResponse.FromString,
                 )
+        self.StoresSet = channel.unary_unary(
+                '/backend.Backend/StoresSet',
+                request_serializer=backend__pb2.StoresSetOptions.SerializeToString,
+                response_deserializer=backend__pb2.Result.FromString,
+                )
+        self.StoresDelete = channel.unary_unary(
+                '/backend.Backend/StoresDelete',
+                request_serializer=backend__pb2.StoresDeleteOptions.SerializeToString,
+                response_deserializer=backend__pb2.Result.FromString,
+                )
+        self.StoresGet = channel.unary_unary(
+                '/backend.Backend/StoresGet',
+                request_serializer=backend__pb2.StoresGetOptions.SerializeToString,
+                response_deserializer=backend__pb2.StoresGetResult.FromString,
+                )
+        self.StoresFind = channel.unary_unary(
+                '/backend.Backend/StoresFind',
+                request_serializer=backend__pb2.StoresFindOptions.SerializeToString,
+                response_deserializer=backend__pb2.StoresFindResult.FromString,
+                )
 
 
 class BackendServicer(object):
@@ -129,6 +149,30 @@ def Status(self, request, context):
         context.set_details('Method not implemented!')
         raise NotImplementedError('Method not implemented!')
 
+    def StoresSet(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresDelete(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresGet(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresFind(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
 
 def add_BackendServicer_to_server(servicer, server):
     rpc_method_handlers = {
@@ -182,6 +226,26 @@ def add_BackendServicer_to_server(servicer, server):
                     request_deserializer=backend__pb2.HealthMessage.FromString,
                     response_serializer=backend__pb2.StatusResponse.SerializeToString,
             ),
+            'StoresSet': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresSet,
+                    request_deserializer=backend__pb2.StoresSetOptions.FromString,
+                    response_serializer=backend__pb2.Result.SerializeToString,
+            ),
+            'StoresDelete': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresDelete,
+                    request_deserializer=backend__pb2.StoresDeleteOptions.FromString,
+                    response_serializer=backend__pb2.Result.SerializeToString,
+            ),
+            'StoresGet': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresGet,
+                    request_deserializer=backend__pb2.StoresGetOptions.FromString,
+                    response_serializer=backend__pb2.StoresGetResult.SerializeToString,
+            ),
+            'StoresFind': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresFind,
+                    request_deserializer=backend__pb2.StoresFindOptions.FromString,
+                    response_serializer=backend__pb2.StoresFindResult.SerializeToString,
+            ),
     }
     generic_handler = grpc.method_handlers_generic_handler(
             'backend.Backend', rpc_method_handlers)
@@ -361,3 +425,71 @@ def Status(request,
             backend__pb2.StatusResponse.FromString,
             options, channel_credentials,
             insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresSet(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresSet',
+            backend__pb2.StoresSetOptions.SerializeToString,
+            backend__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresDelete(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresDelete',
+            backend__pb2.StoresDeleteOptions.SerializeToString,
+            backend__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresGet(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresGet',
+            backend__pb2.StoresGetOptions.SerializeToString,
+            backend__pb2.StoresGetResult.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresFind(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresFind',
+            backend__pb2.StoresFindOptions.SerializeToString,
+            backend__pb2.StoresFindResult.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
diff --git a/backend/python/transformers-musicgen/backend_pb2.py b/backend/python/transformers-musicgen/backend_pb2.py
index 08b896c7cad5..8d366c16d63b 100644
--- a/backend/python/transformers-musicgen/backend_pb2.py
+++ b/backend/python/transformers-musicgen/backend_pb2.py
@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 # Generated by the protocol buffer compiler.  DO NOT EDIT!
 # source: backend.proto
+# Protobuf Python Version: 4.25.1
 """Generated protocol buffer code."""
 from google.protobuf import descriptor as _descriptor
 from google.protobuf import descriptor_pool as _descriptor_pool
@@ -11,51 +12,69 @@
 _sym_db = _symbol_database.Default()
 
 
+from google.protobuf import any_pb2 as google_dot_protobuf_dot_any__pb2
 
 
-DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\rbackend.proto\x12\x07\x62\x61\x63kend\"\x0f\n\rHealthMessage\"\xa6\x06\n\x0ePredictOptions\x12\x0e\n\x06Prompt\x18\x01 \x01(\t\x12\x0c\n\x04Seed\x18\x02 \x01(\x05\x12\x0f\n\x07Threads\x18\x03 \x01(\x05\x12\x0e\n\x06Tokens\x18\x04 \x01(\x05\x12\x0c\n\x04TopK\x18\x05 \x01(\x05\x12\x0e\n\x06Repeat\x18\x06 \x01(\x05\x12\r\n\x05\x42\x61tch\x18\x07 \x01(\x05\x12\r\n\x05NKeep\x18\x08 \x01(\x05\x12\x13\n\x0bTemperature\x18\t \x01(\x02\x12\x0f\n\x07Penalty\x18\n \x01(\x02\x12\r\n\x05\x46\x31\x36KV\x18\x0b \x01(\x08\x12\x11\n\tDebugMode\x18\x0c \x01(\x08\x12\x13\n\x0bStopPrompts\x18\r \x03(\t\x12\x11\n\tIgnoreEOS\x18\x0e \x01(\x08\x12\x19\n\x11TailFreeSamplingZ\x18\x0f \x01(\x02\x12\x10\n\x08TypicalP\x18\x10 \x01(\x02\x12\x18\n\x10\x46requencyPenalty\x18\x11 \x01(\x02\x12\x17\n\x0fPresencePenalty\x18\x12 \x01(\x02\x12\x10\n\x08Mirostat\x18\x13 \x01(\x05\x12\x13\n\x0bMirostatETA\x18\x14 \x01(\x02\x12\x13\n\x0bMirostatTAU\x18\x15 \x01(\x02\x12\x12\n\nPenalizeNL\x18\x16 \x01(\x08\x12\x11\n\tLogitBias\x18\x17 \x01(\t\x12\r\n\x05MLock\x18\x19 \x01(\x08\x12\x0c\n\x04MMap\x18\x1a \x01(\x08\x12\x16\n\x0ePromptCacheAll\x18\x1b \x01(\x08\x12\x15\n\rPromptCacheRO\x18\x1c \x01(\x08\x12\x0f\n\x07Grammar\x18\x1d \x01(\t\x12\x0f\n\x07MainGPU\x18\x1e \x01(\t\x12\x13\n\x0bTensorSplit\x18\x1f \x01(\t\x12\x0c\n\x04TopP\x18  \x01(\x02\x12\x17\n\x0fPromptCachePath\x18! \x01(\t\x12\r\n\x05\x44\x65\x62ug\x18\" \x01(\x08\x12\x17\n\x0f\x45mbeddingTokens\x18# \x03(\x05\x12\x12\n\nEmbeddings\x18$ \x01(\t\x12\x14\n\x0cRopeFreqBase\x18% \x01(\x02\x12\x15\n\rRopeFreqScale\x18& \x01(\x02\x12\x1b\n\x13NegativePromptScale\x18\' \x01(\x02\x12\x16\n\x0eNegativePrompt\x18( \x01(\t\x12\x0e\n\x06NDraft\x18) \x01(\x05\x12\x0e\n\x06Images\x18* \x03(\t\"\x18\n\x05Reply\x12\x0f\n\x07message\x18\x01 \x01(\x0c\"\xb0\x08\n\x0cModelOptions\x12\r\n\x05Model\x18\x01 \x01(\t\x12\x13\n\x0b\x43ontextSize\x18\x02 \x01(\x05\x12\x0c\n\x04Seed\x18\x03 \x01(\x05\x12\x0e\n\x06NBatch\x18\x04 \x01(\x05\x12\x11\n\tF16Memory\x18\x05 \x01(\x08\x12\r\n\x05MLock\x18\x06 \x01(\x08\x12\x0c\n\x04MMap\x18\x07 \x01(\x08\x12\x11\n\tVocabOnly\x18\x08 \x01(\x08\x12\x0f\n\x07LowVRAM\x18\t \x01(\x08\x12\x12\n\nEmbeddings\x18\n \x01(\x08\x12\x0c\n\x04NUMA\x18\x0b \x01(\x08\x12\x12\n\nNGPULayers\x18\x0c \x01(\x05\x12\x0f\n\x07MainGPU\x18\r \x01(\t\x12\x13\n\x0bTensorSplit\x18\x0e \x01(\t\x12\x0f\n\x07Threads\x18\x0f \x01(\x05\x12\x19\n\x11LibrarySearchPath\x18\x10 \x01(\t\x12\x14\n\x0cRopeFreqBase\x18\x11 \x01(\x02\x12\x15\n\rRopeFreqScale\x18\x12 \x01(\x02\x12\x12\n\nRMSNormEps\x18\x13 \x01(\x02\x12\x0c\n\x04NGQA\x18\x14 \x01(\x05\x12\x11\n\tModelFile\x18\x15 \x01(\t\x12\x0e\n\x06\x44\x65vice\x18\x16 \x01(\t\x12\x11\n\tUseTriton\x18\x17 \x01(\x08\x12\x15\n\rModelBaseName\x18\x18 \x01(\t\x12\x18\n\x10UseFastTokenizer\x18\x19 \x01(\x08\x12\x14\n\x0cPipelineType\x18\x1a \x01(\t\x12\x15\n\rSchedulerType\x18\x1b \x01(\t\x12\x0c\n\x04\x43UDA\x18\x1c \x01(\x08\x12\x10\n\x08\x43\x46GScale\x18\x1d \x01(\x02\x12\x0f\n\x07IMG2IMG\x18\x1e \x01(\x08\x12\x11\n\tCLIPModel\x18\x1f \x01(\t\x12\x15\n\rCLIPSubfolder\x18  \x01(\t\x12\x10\n\x08\x43LIPSkip\x18! \x01(\x05\x12\x12\n\nControlNet\x18\x30 \x01(\t\x12\x11\n\tTokenizer\x18\" \x01(\t\x12\x10\n\x08LoraBase\x18# \x01(\t\x12\x13\n\x0bLoraAdapter\x18$ \x01(\t\x12\x11\n\tLoraScale\x18* \x01(\x02\x12\x11\n\tNoMulMatQ\x18% \x01(\x08\x12\x12\n\nDraftModel\x18\' \x01(\t\x12\x11\n\tAudioPath\x18& \x01(\t\x12\x14\n\x0cQuantization\x18( \x01(\t\x12\x1c\n\x14GPUMemoryUtilization\x18\x32 \x01(\x02\x12\x17\n\x0fTrustRemoteCode\x18\x33 \x01(\x08\x12\x14\n\x0c\x45nforceEager\x18\x34 \x01(\x08\x12\x11\n\tSwapSpace\x18\x35 \x01(\x05\x12\x13\n\x0bMaxModelLen\x18\x36 \x01(\x05\x12\x0e\n\x06MMProj\x18) \x01(\t\x12\x13\n\x0bRopeScaling\x18+ \x01(\t\x12\x15\n\rYarnExtFactor\x18, \x01(\x02\x12\x16\n\x0eYarnAttnFactor\x18- \x01(\x02\x12\x14\n\x0cYarnBetaFast\x18. \x01(\x02\x12\x14\n\x0cYarnBetaSlow\x18/ \x01(\x02\x12\x0c\n\x04Type\x18\x31 \x01(\t\"*\n\x06Result\x12\x0f\n\x07message\x18\x01 \x01(\t\x12\x0f\n\x07success\x18\x02 \x01(\x08\"%\n\x0f\x45mbeddingResult\x12\x12\n\nembeddings\x18\x01 \x03(\x02\"C\n\x11TranscriptRequest\x12\x0b\n\x03\x64st\x18\x02 \x01(\t\x12\x10\n\x08language\x18\x03 \x01(\t\x12\x0f\n\x07threads\x18\x04 \x01(\r\"N\n\x10TranscriptResult\x12,\n\x08segments\x18\x01 \x03(\x0b\x32\x1a.backend.TranscriptSegment\x12\x0c\n\x04text\x18\x02 \x01(\t\"Y\n\x11TranscriptSegment\x12\n\n\x02id\x18\x01 \x01(\x05\x12\r\n\x05start\x18\x02 \x01(\x03\x12\x0b\n\x03\x65nd\x18\x03 \x01(\x03\x12\x0c\n\x04text\x18\x04 \x01(\t\x12\x0e\n\x06tokens\x18\x05 \x03(\x05\"\xd7\x01\n\x14GenerateImageRequest\x12\x0e\n\x06height\x18\x01 \x01(\x05\x12\r\n\x05width\x18\x02 \x01(\x05\x12\x0c\n\x04mode\x18\x03 \x01(\x05\x12\x0c\n\x04step\x18\x04 \x01(\x05\x12\x0c\n\x04seed\x18\x05 \x01(\x05\x12\x17\n\x0fpositive_prompt\x18\x06 \x01(\t\x12\x17\n\x0fnegative_prompt\x18\x07 \x01(\t\x12\x0b\n\x03\x64st\x18\x08 \x01(\t\x12\x0b\n\x03src\x18\t \x01(\t\x12\x18\n\x10\x45nableParameters\x18\n \x01(\t\x12\x10\n\x08\x43LIPSkip\x18\x0b \x01(\x05\"E\n\nTTSRequest\x12\x0c\n\x04text\x18\x01 \x01(\t\x12\r\n\x05model\x18\x02 \x01(\t\x12\x0b\n\x03\x64st\x18\x03 \x01(\t\x12\r\n\x05voice\x18\x04 \x01(\t\"6\n\x14TokenizationResponse\x12\x0e\n\x06length\x18\x01 \x01(\x05\x12\x0e\n\x06tokens\x18\x02 \x03(\x05\"\x8e\x01\n\x0fMemoryUsageData\x12\r\n\x05total\x18\x01 \x01(\x04\x12:\n\tbreakdown\x18\x02 \x03(\x0b\x32\'.backend.MemoryUsageData.BreakdownEntry\x1a\x30\n\x0e\x42reakdownEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\x04:\x02\x38\x01\"\xad\x01\n\x0eStatusResponse\x12,\n\x05state\x18\x01 \x01(\x0e\x32\x1d.backend.StatusResponse.State\x12(\n\x06memory\x18\x02 \x01(\x0b\x32\x18.backend.MemoryUsageData\"C\n\x05State\x12\x11\n\rUNINITIALIZED\x10\x00\x12\x08\n\x04\x42USY\x10\x01\x12\t\n\x05READY\x10\x02\x12\x12\n\x05\x45RROR\x10\xff\xff\xff\xff\xff\xff\xff\xff\xff\x01\x32\xf4\x04\n\x07\x42\x61\x63kend\x12\x32\n\x06Health\x12\x16.backend.HealthMessage\x1a\x0e.backend.Reply\"\x00\x12\x34\n\x07Predict\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x12\x35\n\tLoadModel\x12\x15.backend.ModelOptions\x1a\x0f.backend.Result\"\x00\x12<\n\rPredictStream\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x30\x01\x12@\n\tEmbedding\x12\x17.backend.PredictOptions\x1a\x18.backend.EmbeddingResult\"\x00\x12\x41\n\rGenerateImage\x12\x1d.backend.GenerateImageRequest\x1a\x0f.backend.Result\"\x00\x12M\n\x12\x41udioTranscription\x12\x1a.backend.TranscriptRequest\x1a\x19.backend.TranscriptResult\"\x00\x12-\n\x03TTS\x12\x13.backend.TTSRequest\x1a\x0f.backend.Result\"\x00\x12J\n\x0eTokenizeString\x12\x17.backend.PredictOptions\x1a\x1d.backend.TokenizationResponse\"\x00\x12;\n\x06Status\x12\x16.backend.HealthMessage\x1a\x17.backend.StatusResponse\"\x00\x42Z\n\x19io.skynet.localai.backendB\x0eLocalAIBackendP\x01Z+github.com/go-skynet/LocalAI/pkg/grpc/protob\x06proto3')
+DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\rbackend.proto\x12\x07\x62\x61\x63kend\x1a\x19google/protobuf/any.proto\"\x1b\n\tStoresKey\x12\x0e\n\x06\x46loats\x18\x01 \x03(\x02\"\x1c\n\x0bStoresValue\x12\r\n\x05\x42ytes\x18\x01 \x01(\x0c\"Z\n\x10StoresSetOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\"7\n\x13StoresDeleteOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\"4\n\x10StoresGetOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\"Y\n\x0fStoresGetResult\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\"B\n\x11StoresFindOptions\x12\x1f\n\x03Key\x18\x01 \x01(\x0b\x32\x12.backend.StoresKey\x12\x0c\n\x04TopK\x18\x02 \x01(\x05\"p\n\x10StoresFindResult\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\x12\x14\n\x0cSimilarities\x18\x03 \x03(\x02\"\x0f\n\rHealthMessage\"\xe8\x06\n\x0ePredictOptions\x12\x0e\n\x06Prompt\x18\x01 \x01(\t\x12\x0c\n\x04Seed\x18\x02 \x01(\x05\x12\x0f\n\x07Threads\x18\x03 \x01(\x05\x12\x0e\n\x06Tokens\x18\x04 \x01(\x05\x12\x0c\n\x04TopK\x18\x05 \x01(\x05\x12\x0e\n\x06Repeat\x18\x06 \x01(\x05\x12\r\n\x05\x42\x61tch\x18\x07 \x01(\x05\x12\r\n\x05NKeep\x18\x08 \x01(\x05\x12\x13\n\x0bTemperature\x18\t \x01(\x02\x12\x0f\n\x07Penalty\x18\n \x01(\x02\x12\r\n\x05\x46\x31\x36KV\x18\x0b \x01(\x08\x12\x11\n\tDebugMode\x18\x0c \x01(\x08\x12\x13\n\x0bStopPrompts\x18\r \x03(\t\x12\x11\n\tIgnoreEOS\x18\x0e \x01(\x08\x12\x19\n\x11TailFreeSamplingZ\x18\x0f \x01(\x02\x12\x10\n\x08TypicalP\x18\x10 \x01(\x02\x12\x18\n\x10\x46requencyPenalty\x18\x11 \x01(\x02\x12\x17\n\x0fPresencePenalty\x18\x12 \x01(\x02\x12\x10\n\x08Mirostat\x18\x13 \x01(\x05\x12\x13\n\x0bMirostatETA\x18\x14 \x01(\x02\x12\x13\n\x0bMirostatTAU\x18\x15 \x01(\x02\x12\x12\n\nPenalizeNL\x18\x16 \x01(\x08\x12\x11\n\tLogitBias\x18\x17 \x01(\t\x12\r\n\x05MLock\x18\x19 \x01(\x08\x12\x0c\n\x04MMap\x18\x1a \x01(\x08\x12\x16\n\x0ePromptCacheAll\x18\x1b \x01(\x08\x12\x15\n\rPromptCacheRO\x18\x1c \x01(\x08\x12\x0f\n\x07Grammar\x18\x1d \x01(\t\x12\x0f\n\x07MainGPU\x18\x1e \x01(\t\x12\x13\n\x0bTensorSplit\x18\x1f \x01(\t\x12\x0c\n\x04TopP\x18  \x01(\x02\x12\x17\n\x0fPromptCachePath\x18! \x01(\t\x12\r\n\x05\x44\x65\x62ug\x18\" \x01(\x08\x12\x17\n\x0f\x45mbeddingTokens\x18# \x03(\x05\x12\x12\n\nEmbeddings\x18$ \x01(\t\x12\x14\n\x0cRopeFreqBase\x18% \x01(\x02\x12\x15\n\rRopeFreqScale\x18& \x01(\x02\x12\x1b\n\x13NegativePromptScale\x18\' \x01(\x02\x12\x16\n\x0eNegativePrompt\x18( \x01(\t\x12\x0e\n\x06NDraft\x18) \x01(\x05\x12\x0e\n\x06Images\x18* \x03(\t\x12\x1c\n\x14UseTokenizerTemplate\x18+ \x01(\x08\x12\"\n\x08Messages\x18, \x03(\x0b\x32\x10.backend.Message\"\x18\n\x05Reply\x12\x0f\n\x07message\x18\x01 \x01(\x0c\"\xb0\x08\n\x0cModelOptions\x12\r\n\x05Model\x18\x01 \x01(\t\x12\x13\n\x0b\x43ontextSize\x18\x02 \x01(\x05\x12\x0c\n\x04Seed\x18\x03 \x01(\x05\x12\x0e\n\x06NBatch\x18\x04 \x01(\x05\x12\x11\n\tF16Memory\x18\x05 \x01(\x08\x12\r\n\x05MLock\x18\x06 \x01(\x08\x12\x0c\n\x04MMap\x18\x07 \x01(\x08\x12\x11\n\tVocabOnly\x18\x08 \x01(\x08\x12\x0f\n\x07LowVRAM\x18\t \x01(\x08\x12\x12\n\nEmbeddings\x18\n \x01(\x08\x12\x0c\n\x04NUMA\x18\x0b \x01(\x08\x12\x12\n\nNGPULayers\x18\x0c \x01(\x05\x12\x0f\n\x07MainGPU\x18\r \x01(\t\x12\x13\n\x0bTensorSplit\x18\x0e \x01(\t\x12\x0f\n\x07Threads\x18\x0f \x01(\x05\x12\x19\n\x11LibrarySearchPath\x18\x10 \x01(\t\x12\x14\n\x0cRopeFreqBase\x18\x11 \x01(\x02\x12\x15\n\rRopeFreqScale\x18\x12 \x01(\x02\x12\x12\n\nRMSNormEps\x18\x13 \x01(\x02\x12\x0c\n\x04NGQA\x18\x14 \x01(\x05\x12\x11\n\tModelFile\x18\x15 \x01(\t\x12\x0e\n\x06\x44\x65vice\x18\x16 \x01(\t\x12\x11\n\tUseTriton\x18\x17 \x01(\x08\x12\x15\n\rModelBaseName\x18\x18 \x01(\t\x12\x18\n\x10UseFastTokenizer\x18\x19 \x01(\x08\x12\x14\n\x0cPipelineType\x18\x1a \x01(\t\x12\x15\n\rSchedulerType\x18\x1b \x01(\t\x12\x0c\n\x04\x43UDA\x18\x1c \x01(\x08\x12\x10\n\x08\x43\x46GScale\x18\x1d \x01(\x02\x12\x0f\n\x07IMG2IMG\x18\x1e \x01(\x08\x12\x11\n\tCLIPModel\x18\x1f \x01(\t\x12\x15\n\rCLIPSubfolder\x18  \x01(\t\x12\x10\n\x08\x43LIPSkip\x18! \x01(\x05\x12\x12\n\nControlNet\x18\x30 \x01(\t\x12\x11\n\tTokenizer\x18\" \x01(\t\x12\x10\n\x08LoraBase\x18# \x01(\t\x12\x13\n\x0bLoraAdapter\x18$ \x01(\t\x12\x11\n\tLoraScale\x18* \x01(\x02\x12\x11\n\tNoMulMatQ\x18% \x01(\x08\x12\x12\n\nDraftModel\x18\' \x01(\t\x12\x11\n\tAudioPath\x18& \x01(\t\x12\x14\n\x0cQuantization\x18( \x01(\t\x12\x1c\n\x14GPUMemoryUtilization\x18\x32 \x01(\x02\x12\x17\n\x0fTrustRemoteCode\x18\x33 \x01(\x08\x12\x14\n\x0c\x45nforceEager\x18\x34 \x01(\x08\x12\x11\n\tSwapSpace\x18\x35 \x01(\x05\x12\x13\n\x0bMaxModelLen\x18\x36 \x01(\x05\x12\x0e\n\x06MMProj\x18) \x01(\t\x12\x13\n\x0bRopeScaling\x18+ \x01(\t\x12\x15\n\rYarnExtFactor\x18, \x01(\x02\x12\x16\n\x0eYarnAttnFactor\x18- \x01(\x02\x12\x14\n\x0cYarnBetaFast\x18. \x01(\x02\x12\x14\n\x0cYarnBetaSlow\x18/ \x01(\x02\x12\x0c\n\x04Type\x18\x31 \x01(\t\"*\n\x06Result\x12\x0f\n\x07message\x18\x01 \x01(\t\x12\x0f\n\x07success\x18\x02 \x01(\x08\"%\n\x0f\x45mbeddingResult\x12\x12\n\nembeddings\x18\x01 \x03(\x02\"C\n\x11TranscriptRequest\x12\x0b\n\x03\x64st\x18\x02 \x01(\t\x12\x10\n\x08language\x18\x03 \x01(\t\x12\x0f\n\x07threads\x18\x04 \x01(\r\"N\n\x10TranscriptResult\x12,\n\x08segments\x18\x01 \x03(\x0b\x32\x1a.backend.TranscriptSegment\x12\x0c\n\x04text\x18\x02 \x01(\t\"Y\n\x11TranscriptSegment\x12\n\n\x02id\x18\x01 \x01(\x05\x12\r\n\x05start\x18\x02 \x01(\x03\x12\x0b\n\x03\x65nd\x18\x03 \x01(\x03\x12\x0c\n\x04text\x18\x04 \x01(\t\x12\x0e\n\x06tokens\x18\x05 \x03(\x05\"\xd7\x01\n\x14GenerateImageRequest\x12\x0e\n\x06height\x18\x01 \x01(\x05\x12\r\n\x05width\x18\x02 \x01(\x05\x12\x0c\n\x04mode\x18\x03 \x01(\x05\x12\x0c\n\x04step\x18\x04 \x01(\x05\x12\x0c\n\x04seed\x18\x05 \x01(\x05\x12\x17\n\x0fpositive_prompt\x18\x06 \x01(\t\x12\x17\n\x0fnegative_prompt\x18\x07 \x01(\t\x12\x0b\n\x03\x64st\x18\x08 \x01(\t\x12\x0b\n\x03src\x18\t \x01(\t\x12\x18\n\x10\x45nableParameters\x18\n \x01(\t\x12\x10\n\x08\x43LIPSkip\x18\x0b \x01(\x05\"E\n\nTTSRequest\x12\x0c\n\x04text\x18\x01 \x01(\t\x12\r\n\x05model\x18\x02 \x01(\t\x12\x0b\n\x03\x64st\x18\x03 \x01(\t\x12\r\n\x05voice\x18\x04 \x01(\t\"6\n\x14TokenizationResponse\x12\x0e\n\x06length\x18\x01 \x01(\x05\x12\x0e\n\x06tokens\x18\x02 \x03(\x05\"\x8e\x01\n\x0fMemoryUsageData\x12\r\n\x05total\x18\x01 \x01(\x04\x12:\n\tbreakdown\x18\x02 \x03(\x0b\x32\'.backend.MemoryUsageData.BreakdownEntry\x1a\x30\n\x0e\x42reakdownEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\x04:\x02\x38\x01\"\xad\x01\n\x0eStatusResponse\x12,\n\x05state\x18\x01 \x01(\x0e\x32\x1d.backend.StatusResponse.State\x12(\n\x06memory\x18\x02 \x01(\x0b\x32\x18.backend.MemoryUsageData\"C\n\x05State\x12\x11\n\rUNINITIALIZED\x10\x00\x12\x08\n\x04\x42USY\x10\x01\x12\t\n\x05READY\x10\x02\x12\x12\n\x05\x45RROR\x10\xff\xff\xff\xff\xff\xff\xff\xff\xff\x01\">\n\x07Message\x12\x0c\n\x04Role\x18\x01 \x01(\t\x12%\n\x07\x43ontent\x18\x02 \x01(\x0b\x32\x14.google.protobuf.Any2\xfb\x06\n\x07\x42\x61\x63kend\x12\x32\n\x06Health\x12\x16.backend.HealthMessage\x1a\x0e.backend.Reply\"\x00\x12\x34\n\x07Predict\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x12\x35\n\tLoadModel\x12\x15.backend.ModelOptions\x1a\x0f.backend.Result\"\x00\x12<\n\rPredictStream\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x30\x01\x12@\n\tEmbedding\x12\x17.backend.PredictOptions\x1a\x18.backend.EmbeddingResult\"\x00\x12\x41\n\rGenerateImage\x12\x1d.backend.GenerateImageRequest\x1a\x0f.backend.Result\"\x00\x12M\n\x12\x41udioTranscription\x12\x1a.backend.TranscriptRequest\x1a\x19.backend.TranscriptResult\"\x00\x12-\n\x03TTS\x12\x13.backend.TTSRequest\x1a\x0f.backend.Result\"\x00\x12J\n\x0eTokenizeString\x12\x17.backend.PredictOptions\x1a\x1d.backend.TokenizationResponse\"\x00\x12;\n\x06Status\x12\x16.backend.HealthMessage\x1a\x17.backend.StatusResponse\"\x00\x12\x39\n\tStoresSet\x12\x19.backend.StoresSetOptions\x1a\x0f.backend.Result\"\x00\x12?\n\x0cStoresDelete\x12\x1c.backend.StoresDeleteOptions\x1a\x0f.backend.Result\"\x00\x12\x42\n\tStoresGet\x12\x19.backend.StoresGetOptions\x1a\x18.backend.StoresGetResult\"\x00\x12\x45\n\nStoresFind\x12\x1a.backend.StoresFindOptions\x1a\x19.backend.StoresFindResult\"\x00\x42Z\n\x19io.skynet.localai.backendB\x0eLocalAIBackendP\x01Z+github.com/go-skynet/LocalAI/pkg/grpc/protob\x06proto3')
 
 _globals = globals()
 _builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, _globals)
 _builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, 'backend_pb2', _globals)
 if _descriptor._USE_C_DESCRIPTORS == False:
-
-  DESCRIPTOR._options = None
-  DESCRIPTOR._serialized_options = b'\n\031io.skynet.localai.backendB\016LocalAIBackendP\001Z+github.com/go-skynet/LocalAI/pkg/grpc/proto'
-  _MEMORYUSAGEDATA_BREAKDOWNENTRY._options = None
-  _MEMORYUSAGEDATA_BREAKDOWNENTRY._serialized_options = b'8\001'
-  _globals['_HEALTHMESSAGE']._serialized_start=26
-  _globals['_HEALTHMESSAGE']._serialized_end=41
-  _globals['_PREDICTOPTIONS']._serialized_start=44
-  _globals['_PREDICTOPTIONS']._serialized_end=850
-  _globals['_REPLY']._serialized_start=852
-  _globals['_REPLY']._serialized_end=876
-  _globals['_MODELOPTIONS']._serialized_start=879
-  _globals['_MODELOPTIONS']._serialized_end=1951
-  _globals['_RESULT']._serialized_start=1953
-  _globals['_RESULT']._serialized_end=1995
-  _globals['_EMBEDDINGRESULT']._serialized_start=1997
-  _globals['_EMBEDDINGRESULT']._serialized_end=2034
-  _globals['_TRANSCRIPTREQUEST']._serialized_start=2036
-  _globals['_TRANSCRIPTREQUEST']._serialized_end=2103
-  _globals['_TRANSCRIPTRESULT']._serialized_start=2105
-  _globals['_TRANSCRIPTRESULT']._serialized_end=2183
-  _globals['_TRANSCRIPTSEGMENT']._serialized_start=2185
-  _globals['_TRANSCRIPTSEGMENT']._serialized_end=2274
-  _globals['_GENERATEIMAGEREQUEST']._serialized_start=2277
-  _globals['_GENERATEIMAGEREQUEST']._serialized_end=2492
-  _globals['_TTSREQUEST']._serialized_start=2494
-  _globals['_TTSREQUEST']._serialized_end=2563
-  _globals['_TOKENIZATIONRESPONSE']._serialized_start=2565
-  _globals['_TOKENIZATIONRESPONSE']._serialized_end=2619
-  _globals['_MEMORYUSAGEDATA']._serialized_start=2622
-  _globals['_MEMORYUSAGEDATA']._serialized_end=2764
-  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_start=2716
-  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_end=2764
-  _globals['_STATUSRESPONSE']._serialized_start=2767
-  _globals['_STATUSRESPONSE']._serialized_end=2940
-  _globals['_STATUSRESPONSE_STATE']._serialized_start=2873
-  _globals['_STATUSRESPONSE_STATE']._serialized_end=2940
-  _globals['_BACKEND']._serialized_start=2943
-  _globals['_BACKEND']._serialized_end=3571
+  _globals['DESCRIPTOR']._options = None
+  _globals['DESCRIPTOR']._serialized_options = b'\n\031io.skynet.localai.backendB\016LocalAIBackendP\001Z+github.com/go-skynet/LocalAI/pkg/grpc/proto'
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._options = None
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_options = b'8\001'
+  _globals['_STORESKEY']._serialized_start=53
+  _globals['_STORESKEY']._serialized_end=80
+  _globals['_STORESVALUE']._serialized_start=82
+  _globals['_STORESVALUE']._serialized_end=110
+  _globals['_STORESSETOPTIONS']._serialized_start=112
+  _globals['_STORESSETOPTIONS']._serialized_end=202
+  _globals['_STORESDELETEOPTIONS']._serialized_start=204
+  _globals['_STORESDELETEOPTIONS']._serialized_end=259
+  _globals['_STORESGETOPTIONS']._serialized_start=261
+  _globals['_STORESGETOPTIONS']._serialized_end=313
+  _globals['_STORESGETRESULT']._serialized_start=315
+  _globals['_STORESGETRESULT']._serialized_end=404
+  _globals['_STORESFINDOPTIONS']._serialized_start=406
+  _globals['_STORESFINDOPTIONS']._serialized_end=472
+  _globals['_STORESFINDRESULT']._serialized_start=474
+  _globals['_STORESFINDRESULT']._serialized_end=586
+  _globals['_HEALTHMESSAGE']._serialized_start=588
+  _globals['_HEALTHMESSAGE']._serialized_end=603
+  _globals['_PREDICTOPTIONS']._serialized_start=606
+  _globals['_PREDICTOPTIONS']._serialized_end=1478
+  _globals['_REPLY']._serialized_start=1480
+  _globals['_REPLY']._serialized_end=1504
+  _globals['_MODELOPTIONS']._serialized_start=1507
+  _globals['_MODELOPTIONS']._serialized_end=2579
+  _globals['_RESULT']._serialized_start=2581
+  _globals['_RESULT']._serialized_end=2623
+  _globals['_EMBEDDINGRESULT']._serialized_start=2625
+  _globals['_EMBEDDINGRESULT']._serialized_end=2662
+  _globals['_TRANSCRIPTREQUEST']._serialized_start=2664
+  _globals['_TRANSCRIPTREQUEST']._serialized_end=2731
+  _globals['_TRANSCRIPTRESULT']._serialized_start=2733
+  _globals['_TRANSCRIPTRESULT']._serialized_end=2811
+  _globals['_TRANSCRIPTSEGMENT']._serialized_start=2813
+  _globals['_TRANSCRIPTSEGMENT']._serialized_end=2902
+  _globals['_GENERATEIMAGEREQUEST']._serialized_start=2905
+  _globals['_GENERATEIMAGEREQUEST']._serialized_end=3120
+  _globals['_TTSREQUEST']._serialized_start=3122
+  _globals['_TTSREQUEST']._serialized_end=3191
+  _globals['_TOKENIZATIONRESPONSE']._serialized_start=3193
+  _globals['_TOKENIZATIONRESPONSE']._serialized_end=3247
+  _globals['_MEMORYUSAGEDATA']._serialized_start=3250
+  _globals['_MEMORYUSAGEDATA']._serialized_end=3392
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_start=3344
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_end=3392
+  _globals['_STATUSRESPONSE']._serialized_start=3395
+  _globals['_STATUSRESPONSE']._serialized_end=3568
+  _globals['_STATUSRESPONSE_STATE']._serialized_start=3501
+  _globals['_STATUSRESPONSE_STATE']._serialized_end=3568
+  _globals['_MESSAGE']._serialized_start=3570
+  _globals['_MESSAGE']._serialized_end=3632
+  _globals['_BACKEND']._serialized_start=3635
+  _globals['_BACKEND']._serialized_end=4526
 # @@protoc_insertion_point(module_scope)
diff --git a/backend/python/transformers-musicgen/backend_pb2_grpc.py b/backend/python/transformers-musicgen/backend_pb2_grpc.py
index 79a7677fb27f..e06fccf3d451 100644
--- a/backend/python/transformers-musicgen/backend_pb2_grpc.py
+++ b/backend/python/transformers-musicgen/backend_pb2_grpc.py
@@ -64,6 +64,26 @@ def __init__(self, channel):
                 request_serializer=backend__pb2.HealthMessage.SerializeToString,
                 response_deserializer=backend__pb2.StatusResponse.FromString,
                 )
+        self.StoresSet = channel.unary_unary(
+                '/backend.Backend/StoresSet',
+                request_serializer=backend__pb2.StoresSetOptions.SerializeToString,
+                response_deserializer=backend__pb2.Result.FromString,
+                )
+        self.StoresDelete = channel.unary_unary(
+                '/backend.Backend/StoresDelete',
+                request_serializer=backend__pb2.StoresDeleteOptions.SerializeToString,
+                response_deserializer=backend__pb2.Result.FromString,
+                )
+        self.StoresGet = channel.unary_unary(
+                '/backend.Backend/StoresGet',
+                request_serializer=backend__pb2.StoresGetOptions.SerializeToString,
+                response_deserializer=backend__pb2.StoresGetResult.FromString,
+                )
+        self.StoresFind = channel.unary_unary(
+                '/backend.Backend/StoresFind',
+                request_serializer=backend__pb2.StoresFindOptions.SerializeToString,
+                response_deserializer=backend__pb2.StoresFindResult.FromString,
+                )
 
 
 class BackendServicer(object):
@@ -129,6 +149,30 @@ def Status(self, request, context):
         context.set_details('Method not implemented!')
         raise NotImplementedError('Method not implemented!')
 
+    def StoresSet(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresDelete(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresGet(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresFind(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
 
 def add_BackendServicer_to_server(servicer, server):
     rpc_method_handlers = {
@@ -182,6 +226,26 @@ def add_BackendServicer_to_server(servicer, server):
                     request_deserializer=backend__pb2.HealthMessage.FromString,
                     response_serializer=backend__pb2.StatusResponse.SerializeToString,
             ),
+            'StoresSet': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresSet,
+                    request_deserializer=backend__pb2.StoresSetOptions.FromString,
+                    response_serializer=backend__pb2.Result.SerializeToString,
+            ),
+            'StoresDelete': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresDelete,
+                    request_deserializer=backend__pb2.StoresDeleteOptions.FromString,
+                    response_serializer=backend__pb2.Result.SerializeToString,
+            ),
+            'StoresGet': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresGet,
+                    request_deserializer=backend__pb2.StoresGetOptions.FromString,
+                    response_serializer=backend__pb2.StoresGetResult.SerializeToString,
+            ),
+            'StoresFind': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresFind,
+                    request_deserializer=backend__pb2.StoresFindOptions.FromString,
+                    response_serializer=backend__pb2.StoresFindResult.SerializeToString,
+            ),
     }
     generic_handler = grpc.method_handlers_generic_handler(
             'backend.Backend', rpc_method_handlers)
@@ -361,3 +425,71 @@ def Status(request,
             backend__pb2.StatusResponse.FromString,
             options, channel_credentials,
             insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresSet(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresSet',
+            backend__pb2.StoresSetOptions.SerializeToString,
+            backend__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresDelete(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresDelete',
+            backend__pb2.StoresDeleteOptions.SerializeToString,
+            backend__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresGet(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresGet',
+            backend__pb2.StoresGetOptions.SerializeToString,
+            backend__pb2.StoresGetResult.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresFind(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresFind',
+            backend__pb2.StoresFindOptions.SerializeToString,
+            backend__pb2.StoresFindResult.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
diff --git a/backend/python/transformers/backend_pb2.py b/backend/python/transformers/backend_pb2.py
index 08b896c7cad5..8d366c16d63b 100644
--- a/backend/python/transformers/backend_pb2.py
+++ b/backend/python/transformers/backend_pb2.py
@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 # Generated by the protocol buffer compiler.  DO NOT EDIT!
 # source: backend.proto
+# Protobuf Python Version: 4.25.1
 """Generated protocol buffer code."""
 from google.protobuf import descriptor as _descriptor
 from google.protobuf import descriptor_pool as _descriptor_pool
@@ -11,51 +12,69 @@
 _sym_db = _symbol_database.Default()
 
 
+from google.protobuf import any_pb2 as google_dot_protobuf_dot_any__pb2
 
 
-DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\rbackend.proto\x12\x07\x62\x61\x63kend\"\x0f\n\rHealthMessage\"\xa6\x06\n\x0ePredictOptions\x12\x0e\n\x06Prompt\x18\x01 \x01(\t\x12\x0c\n\x04Seed\x18\x02 \x01(\x05\x12\x0f\n\x07Threads\x18\x03 \x01(\x05\x12\x0e\n\x06Tokens\x18\x04 \x01(\x05\x12\x0c\n\x04TopK\x18\x05 \x01(\x05\x12\x0e\n\x06Repeat\x18\x06 \x01(\x05\x12\r\n\x05\x42\x61tch\x18\x07 \x01(\x05\x12\r\n\x05NKeep\x18\x08 \x01(\x05\x12\x13\n\x0bTemperature\x18\t \x01(\x02\x12\x0f\n\x07Penalty\x18\n \x01(\x02\x12\r\n\x05\x46\x31\x36KV\x18\x0b \x01(\x08\x12\x11\n\tDebugMode\x18\x0c \x01(\x08\x12\x13\n\x0bStopPrompts\x18\r \x03(\t\x12\x11\n\tIgnoreEOS\x18\x0e \x01(\x08\x12\x19\n\x11TailFreeSamplingZ\x18\x0f \x01(\x02\x12\x10\n\x08TypicalP\x18\x10 \x01(\x02\x12\x18\n\x10\x46requencyPenalty\x18\x11 \x01(\x02\x12\x17\n\x0fPresencePenalty\x18\x12 \x01(\x02\x12\x10\n\x08Mirostat\x18\x13 \x01(\x05\x12\x13\n\x0bMirostatETA\x18\x14 \x01(\x02\x12\x13\n\x0bMirostatTAU\x18\x15 \x01(\x02\x12\x12\n\nPenalizeNL\x18\x16 \x01(\x08\x12\x11\n\tLogitBias\x18\x17 \x01(\t\x12\r\n\x05MLock\x18\x19 \x01(\x08\x12\x0c\n\x04MMap\x18\x1a \x01(\x08\x12\x16\n\x0ePromptCacheAll\x18\x1b \x01(\x08\x12\x15\n\rPromptCacheRO\x18\x1c \x01(\x08\x12\x0f\n\x07Grammar\x18\x1d \x01(\t\x12\x0f\n\x07MainGPU\x18\x1e \x01(\t\x12\x13\n\x0bTensorSplit\x18\x1f \x01(\t\x12\x0c\n\x04TopP\x18  \x01(\x02\x12\x17\n\x0fPromptCachePath\x18! \x01(\t\x12\r\n\x05\x44\x65\x62ug\x18\" \x01(\x08\x12\x17\n\x0f\x45mbeddingTokens\x18# \x03(\x05\x12\x12\n\nEmbeddings\x18$ \x01(\t\x12\x14\n\x0cRopeFreqBase\x18% \x01(\x02\x12\x15\n\rRopeFreqScale\x18& \x01(\x02\x12\x1b\n\x13NegativePromptScale\x18\' \x01(\x02\x12\x16\n\x0eNegativePrompt\x18( \x01(\t\x12\x0e\n\x06NDraft\x18) \x01(\x05\x12\x0e\n\x06Images\x18* \x03(\t\"\x18\n\x05Reply\x12\x0f\n\x07message\x18\x01 \x01(\x0c\"\xb0\x08\n\x0cModelOptions\x12\r\n\x05Model\x18\x01 \x01(\t\x12\x13\n\x0b\x43ontextSize\x18\x02 \x01(\x05\x12\x0c\n\x04Seed\x18\x03 \x01(\x05\x12\x0e\n\x06NBatch\x18\x04 \x01(\x05\x12\x11\n\tF16Memory\x18\x05 \x01(\x08\x12\r\n\x05MLock\x18\x06 \x01(\x08\x12\x0c\n\x04MMap\x18\x07 \x01(\x08\x12\x11\n\tVocabOnly\x18\x08 \x01(\x08\x12\x0f\n\x07LowVRAM\x18\t \x01(\x08\x12\x12\n\nEmbeddings\x18\n \x01(\x08\x12\x0c\n\x04NUMA\x18\x0b \x01(\x08\x12\x12\n\nNGPULayers\x18\x0c \x01(\x05\x12\x0f\n\x07MainGPU\x18\r \x01(\t\x12\x13\n\x0bTensorSplit\x18\x0e \x01(\t\x12\x0f\n\x07Threads\x18\x0f \x01(\x05\x12\x19\n\x11LibrarySearchPath\x18\x10 \x01(\t\x12\x14\n\x0cRopeFreqBase\x18\x11 \x01(\x02\x12\x15\n\rRopeFreqScale\x18\x12 \x01(\x02\x12\x12\n\nRMSNormEps\x18\x13 \x01(\x02\x12\x0c\n\x04NGQA\x18\x14 \x01(\x05\x12\x11\n\tModelFile\x18\x15 \x01(\t\x12\x0e\n\x06\x44\x65vice\x18\x16 \x01(\t\x12\x11\n\tUseTriton\x18\x17 \x01(\x08\x12\x15\n\rModelBaseName\x18\x18 \x01(\t\x12\x18\n\x10UseFastTokenizer\x18\x19 \x01(\x08\x12\x14\n\x0cPipelineType\x18\x1a \x01(\t\x12\x15\n\rSchedulerType\x18\x1b \x01(\t\x12\x0c\n\x04\x43UDA\x18\x1c \x01(\x08\x12\x10\n\x08\x43\x46GScale\x18\x1d \x01(\x02\x12\x0f\n\x07IMG2IMG\x18\x1e \x01(\x08\x12\x11\n\tCLIPModel\x18\x1f \x01(\t\x12\x15\n\rCLIPSubfolder\x18  \x01(\t\x12\x10\n\x08\x43LIPSkip\x18! \x01(\x05\x12\x12\n\nControlNet\x18\x30 \x01(\t\x12\x11\n\tTokenizer\x18\" \x01(\t\x12\x10\n\x08LoraBase\x18# \x01(\t\x12\x13\n\x0bLoraAdapter\x18$ \x01(\t\x12\x11\n\tLoraScale\x18* \x01(\x02\x12\x11\n\tNoMulMatQ\x18% \x01(\x08\x12\x12\n\nDraftModel\x18\' \x01(\t\x12\x11\n\tAudioPath\x18& \x01(\t\x12\x14\n\x0cQuantization\x18( \x01(\t\x12\x1c\n\x14GPUMemoryUtilization\x18\x32 \x01(\x02\x12\x17\n\x0fTrustRemoteCode\x18\x33 \x01(\x08\x12\x14\n\x0c\x45nforceEager\x18\x34 \x01(\x08\x12\x11\n\tSwapSpace\x18\x35 \x01(\x05\x12\x13\n\x0bMaxModelLen\x18\x36 \x01(\x05\x12\x0e\n\x06MMProj\x18) \x01(\t\x12\x13\n\x0bRopeScaling\x18+ \x01(\t\x12\x15\n\rYarnExtFactor\x18, \x01(\x02\x12\x16\n\x0eYarnAttnFactor\x18- \x01(\x02\x12\x14\n\x0cYarnBetaFast\x18. \x01(\x02\x12\x14\n\x0cYarnBetaSlow\x18/ \x01(\x02\x12\x0c\n\x04Type\x18\x31 \x01(\t\"*\n\x06Result\x12\x0f\n\x07message\x18\x01 \x01(\t\x12\x0f\n\x07success\x18\x02 \x01(\x08\"%\n\x0f\x45mbeddingResult\x12\x12\n\nembeddings\x18\x01 \x03(\x02\"C\n\x11TranscriptRequest\x12\x0b\n\x03\x64st\x18\x02 \x01(\t\x12\x10\n\x08language\x18\x03 \x01(\t\x12\x0f\n\x07threads\x18\x04 \x01(\r\"N\n\x10TranscriptResult\x12,\n\x08segments\x18\x01 \x03(\x0b\x32\x1a.backend.TranscriptSegment\x12\x0c\n\x04text\x18\x02 \x01(\t\"Y\n\x11TranscriptSegment\x12\n\n\x02id\x18\x01 \x01(\x05\x12\r\n\x05start\x18\x02 \x01(\x03\x12\x0b\n\x03\x65nd\x18\x03 \x01(\x03\x12\x0c\n\x04text\x18\x04 \x01(\t\x12\x0e\n\x06tokens\x18\x05 \x03(\x05\"\xd7\x01\n\x14GenerateImageRequest\x12\x0e\n\x06height\x18\x01 \x01(\x05\x12\r\n\x05width\x18\x02 \x01(\x05\x12\x0c\n\x04mode\x18\x03 \x01(\x05\x12\x0c\n\x04step\x18\x04 \x01(\x05\x12\x0c\n\x04seed\x18\x05 \x01(\x05\x12\x17\n\x0fpositive_prompt\x18\x06 \x01(\t\x12\x17\n\x0fnegative_prompt\x18\x07 \x01(\t\x12\x0b\n\x03\x64st\x18\x08 \x01(\t\x12\x0b\n\x03src\x18\t \x01(\t\x12\x18\n\x10\x45nableParameters\x18\n \x01(\t\x12\x10\n\x08\x43LIPSkip\x18\x0b \x01(\x05\"E\n\nTTSRequest\x12\x0c\n\x04text\x18\x01 \x01(\t\x12\r\n\x05model\x18\x02 \x01(\t\x12\x0b\n\x03\x64st\x18\x03 \x01(\t\x12\r\n\x05voice\x18\x04 \x01(\t\"6\n\x14TokenizationResponse\x12\x0e\n\x06length\x18\x01 \x01(\x05\x12\x0e\n\x06tokens\x18\x02 \x03(\x05\"\x8e\x01\n\x0fMemoryUsageData\x12\r\n\x05total\x18\x01 \x01(\x04\x12:\n\tbreakdown\x18\x02 \x03(\x0b\x32\'.backend.MemoryUsageData.BreakdownEntry\x1a\x30\n\x0e\x42reakdownEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\x04:\x02\x38\x01\"\xad\x01\n\x0eStatusResponse\x12,\n\x05state\x18\x01 \x01(\x0e\x32\x1d.backend.StatusResponse.State\x12(\n\x06memory\x18\x02 \x01(\x0b\x32\x18.backend.MemoryUsageData\"C\n\x05State\x12\x11\n\rUNINITIALIZED\x10\x00\x12\x08\n\x04\x42USY\x10\x01\x12\t\n\x05READY\x10\x02\x12\x12\n\x05\x45RROR\x10\xff\xff\xff\xff\xff\xff\xff\xff\xff\x01\x32\xf4\x04\n\x07\x42\x61\x63kend\x12\x32\n\x06Health\x12\x16.backend.HealthMessage\x1a\x0e.backend.Reply\"\x00\x12\x34\n\x07Predict\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x12\x35\n\tLoadModel\x12\x15.backend.ModelOptions\x1a\x0f.backend.Result\"\x00\x12<\n\rPredictStream\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x30\x01\x12@\n\tEmbedding\x12\x17.backend.PredictOptions\x1a\x18.backend.EmbeddingResult\"\x00\x12\x41\n\rGenerateImage\x12\x1d.backend.GenerateImageRequest\x1a\x0f.backend.Result\"\x00\x12M\n\x12\x41udioTranscription\x12\x1a.backend.TranscriptRequest\x1a\x19.backend.TranscriptResult\"\x00\x12-\n\x03TTS\x12\x13.backend.TTSRequest\x1a\x0f.backend.Result\"\x00\x12J\n\x0eTokenizeString\x12\x17.backend.PredictOptions\x1a\x1d.backend.TokenizationResponse\"\x00\x12;\n\x06Status\x12\x16.backend.HealthMessage\x1a\x17.backend.StatusResponse\"\x00\x42Z\n\x19io.skynet.localai.backendB\x0eLocalAIBackendP\x01Z+github.com/go-skynet/LocalAI/pkg/grpc/protob\x06proto3')
+DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\rbackend.proto\x12\x07\x62\x61\x63kend\x1a\x19google/protobuf/any.proto\"\x1b\n\tStoresKey\x12\x0e\n\x06\x46loats\x18\x01 \x03(\x02\"\x1c\n\x0bStoresValue\x12\r\n\x05\x42ytes\x18\x01 \x01(\x0c\"Z\n\x10StoresSetOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\"7\n\x13StoresDeleteOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\"4\n\x10StoresGetOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\"Y\n\x0fStoresGetResult\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\"B\n\x11StoresFindOptions\x12\x1f\n\x03Key\x18\x01 \x01(\x0b\x32\x12.backend.StoresKey\x12\x0c\n\x04TopK\x18\x02 \x01(\x05\"p\n\x10StoresFindResult\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\x12\x14\n\x0cSimilarities\x18\x03 \x03(\x02\"\x0f\n\rHealthMessage\"\xe8\x06\n\x0ePredictOptions\x12\x0e\n\x06Prompt\x18\x01 \x01(\t\x12\x0c\n\x04Seed\x18\x02 \x01(\x05\x12\x0f\n\x07Threads\x18\x03 \x01(\x05\x12\x0e\n\x06Tokens\x18\x04 \x01(\x05\x12\x0c\n\x04TopK\x18\x05 \x01(\x05\x12\x0e\n\x06Repeat\x18\x06 \x01(\x05\x12\r\n\x05\x42\x61tch\x18\x07 \x01(\x05\x12\r\n\x05NKeep\x18\x08 \x01(\x05\x12\x13\n\x0bTemperature\x18\t \x01(\x02\x12\x0f\n\x07Penalty\x18\n \x01(\x02\x12\r\n\x05\x46\x31\x36KV\x18\x0b \x01(\x08\x12\x11\n\tDebugMode\x18\x0c \x01(\x08\x12\x13\n\x0bStopPrompts\x18\r \x03(\t\x12\x11\n\tIgnoreEOS\x18\x0e \x01(\x08\x12\x19\n\x11TailFreeSamplingZ\x18\x0f \x01(\x02\x12\x10\n\x08TypicalP\x18\x10 \x01(\x02\x12\x18\n\x10\x46requencyPenalty\x18\x11 \x01(\x02\x12\x17\n\x0fPresencePenalty\x18\x12 \x01(\x02\x12\x10\n\x08Mirostat\x18\x13 \x01(\x05\x12\x13\n\x0bMirostatETA\x18\x14 \x01(\x02\x12\x13\n\x0bMirostatTAU\x18\x15 \x01(\x02\x12\x12\n\nPenalizeNL\x18\x16 \x01(\x08\x12\x11\n\tLogitBias\x18\x17 \x01(\t\x12\r\n\x05MLock\x18\x19 \x01(\x08\x12\x0c\n\x04MMap\x18\x1a \x01(\x08\x12\x16\n\x0ePromptCacheAll\x18\x1b \x01(\x08\x12\x15\n\rPromptCacheRO\x18\x1c \x01(\x08\x12\x0f\n\x07Grammar\x18\x1d \x01(\t\x12\x0f\n\x07MainGPU\x18\x1e \x01(\t\x12\x13\n\x0bTensorSplit\x18\x1f \x01(\t\x12\x0c\n\x04TopP\x18  \x01(\x02\x12\x17\n\x0fPromptCachePath\x18! \x01(\t\x12\r\n\x05\x44\x65\x62ug\x18\" \x01(\x08\x12\x17\n\x0f\x45mbeddingTokens\x18# \x03(\x05\x12\x12\n\nEmbeddings\x18$ \x01(\t\x12\x14\n\x0cRopeFreqBase\x18% \x01(\x02\x12\x15\n\rRopeFreqScale\x18& \x01(\x02\x12\x1b\n\x13NegativePromptScale\x18\' \x01(\x02\x12\x16\n\x0eNegativePrompt\x18( \x01(\t\x12\x0e\n\x06NDraft\x18) \x01(\x05\x12\x0e\n\x06Images\x18* \x03(\t\x12\x1c\n\x14UseTokenizerTemplate\x18+ \x01(\x08\x12\"\n\x08Messages\x18, \x03(\x0b\x32\x10.backend.Message\"\x18\n\x05Reply\x12\x0f\n\x07message\x18\x01 \x01(\x0c\"\xb0\x08\n\x0cModelOptions\x12\r\n\x05Model\x18\x01 \x01(\t\x12\x13\n\x0b\x43ontextSize\x18\x02 \x01(\x05\x12\x0c\n\x04Seed\x18\x03 \x01(\x05\x12\x0e\n\x06NBatch\x18\x04 \x01(\x05\x12\x11\n\tF16Memory\x18\x05 \x01(\x08\x12\r\n\x05MLock\x18\x06 \x01(\x08\x12\x0c\n\x04MMap\x18\x07 \x01(\x08\x12\x11\n\tVocabOnly\x18\x08 \x01(\x08\x12\x0f\n\x07LowVRAM\x18\t \x01(\x08\x12\x12\n\nEmbeddings\x18\n \x01(\x08\x12\x0c\n\x04NUMA\x18\x0b \x01(\x08\x12\x12\n\nNGPULayers\x18\x0c \x01(\x05\x12\x0f\n\x07MainGPU\x18\r \x01(\t\x12\x13\n\x0bTensorSplit\x18\x0e \x01(\t\x12\x0f\n\x07Threads\x18\x0f \x01(\x05\x12\x19\n\x11LibrarySearchPath\x18\x10 \x01(\t\x12\x14\n\x0cRopeFreqBase\x18\x11 \x01(\x02\x12\x15\n\rRopeFreqScale\x18\x12 \x01(\x02\x12\x12\n\nRMSNormEps\x18\x13 \x01(\x02\x12\x0c\n\x04NGQA\x18\x14 \x01(\x05\x12\x11\n\tModelFile\x18\x15 \x01(\t\x12\x0e\n\x06\x44\x65vice\x18\x16 \x01(\t\x12\x11\n\tUseTriton\x18\x17 \x01(\x08\x12\x15\n\rModelBaseName\x18\x18 \x01(\t\x12\x18\n\x10UseFastTokenizer\x18\x19 \x01(\x08\x12\x14\n\x0cPipelineType\x18\x1a \x01(\t\x12\x15\n\rSchedulerType\x18\x1b \x01(\t\x12\x0c\n\x04\x43UDA\x18\x1c \x01(\x08\x12\x10\n\x08\x43\x46GScale\x18\x1d \x01(\x02\x12\x0f\n\x07IMG2IMG\x18\x1e \x01(\x08\x12\x11\n\tCLIPModel\x18\x1f \x01(\t\x12\x15\n\rCLIPSubfolder\x18  \x01(\t\x12\x10\n\x08\x43LIPSkip\x18! \x01(\x05\x12\x12\n\nControlNet\x18\x30 \x01(\t\x12\x11\n\tTokenizer\x18\" \x01(\t\x12\x10\n\x08LoraBase\x18# \x01(\t\x12\x13\n\x0bLoraAdapter\x18$ \x01(\t\x12\x11\n\tLoraScale\x18* \x01(\x02\x12\x11\n\tNoMulMatQ\x18% \x01(\x08\x12\x12\n\nDraftModel\x18\' \x01(\t\x12\x11\n\tAudioPath\x18& \x01(\t\x12\x14\n\x0cQuantization\x18( \x01(\t\x12\x1c\n\x14GPUMemoryUtilization\x18\x32 \x01(\x02\x12\x17\n\x0fTrustRemoteCode\x18\x33 \x01(\x08\x12\x14\n\x0c\x45nforceEager\x18\x34 \x01(\x08\x12\x11\n\tSwapSpace\x18\x35 \x01(\x05\x12\x13\n\x0bMaxModelLen\x18\x36 \x01(\x05\x12\x0e\n\x06MMProj\x18) \x01(\t\x12\x13\n\x0bRopeScaling\x18+ \x01(\t\x12\x15\n\rYarnExtFactor\x18, \x01(\x02\x12\x16\n\x0eYarnAttnFactor\x18- \x01(\x02\x12\x14\n\x0cYarnBetaFast\x18. \x01(\x02\x12\x14\n\x0cYarnBetaSlow\x18/ \x01(\x02\x12\x0c\n\x04Type\x18\x31 \x01(\t\"*\n\x06Result\x12\x0f\n\x07message\x18\x01 \x01(\t\x12\x0f\n\x07success\x18\x02 \x01(\x08\"%\n\x0f\x45mbeddingResult\x12\x12\n\nembeddings\x18\x01 \x03(\x02\"C\n\x11TranscriptRequest\x12\x0b\n\x03\x64st\x18\x02 \x01(\t\x12\x10\n\x08language\x18\x03 \x01(\t\x12\x0f\n\x07threads\x18\x04 \x01(\r\"N\n\x10TranscriptResult\x12,\n\x08segments\x18\x01 \x03(\x0b\x32\x1a.backend.TranscriptSegment\x12\x0c\n\x04text\x18\x02 \x01(\t\"Y\n\x11TranscriptSegment\x12\n\n\x02id\x18\x01 \x01(\x05\x12\r\n\x05start\x18\x02 \x01(\x03\x12\x0b\n\x03\x65nd\x18\x03 \x01(\x03\x12\x0c\n\x04text\x18\x04 \x01(\t\x12\x0e\n\x06tokens\x18\x05 \x03(\x05\"\xd7\x01\n\x14GenerateImageRequest\x12\x0e\n\x06height\x18\x01 \x01(\x05\x12\r\n\x05width\x18\x02 \x01(\x05\x12\x0c\n\x04mode\x18\x03 \x01(\x05\x12\x0c\n\x04step\x18\x04 \x01(\x05\x12\x0c\n\x04seed\x18\x05 \x01(\x05\x12\x17\n\x0fpositive_prompt\x18\x06 \x01(\t\x12\x17\n\x0fnegative_prompt\x18\x07 \x01(\t\x12\x0b\n\x03\x64st\x18\x08 \x01(\t\x12\x0b\n\x03src\x18\t \x01(\t\x12\x18\n\x10\x45nableParameters\x18\n \x01(\t\x12\x10\n\x08\x43LIPSkip\x18\x0b \x01(\x05\"E\n\nTTSRequest\x12\x0c\n\x04text\x18\x01 \x01(\t\x12\r\n\x05model\x18\x02 \x01(\t\x12\x0b\n\x03\x64st\x18\x03 \x01(\t\x12\r\n\x05voice\x18\x04 \x01(\t\"6\n\x14TokenizationResponse\x12\x0e\n\x06length\x18\x01 \x01(\x05\x12\x0e\n\x06tokens\x18\x02 \x03(\x05\"\x8e\x01\n\x0fMemoryUsageData\x12\r\n\x05total\x18\x01 \x01(\x04\x12:\n\tbreakdown\x18\x02 \x03(\x0b\x32\'.backend.MemoryUsageData.BreakdownEntry\x1a\x30\n\x0e\x42reakdownEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\x04:\x02\x38\x01\"\xad\x01\n\x0eStatusResponse\x12,\n\x05state\x18\x01 \x01(\x0e\x32\x1d.backend.StatusResponse.State\x12(\n\x06memory\x18\x02 \x01(\x0b\x32\x18.backend.MemoryUsageData\"C\n\x05State\x12\x11\n\rUNINITIALIZED\x10\x00\x12\x08\n\x04\x42USY\x10\x01\x12\t\n\x05READY\x10\x02\x12\x12\n\x05\x45RROR\x10\xff\xff\xff\xff\xff\xff\xff\xff\xff\x01\">\n\x07Message\x12\x0c\n\x04Role\x18\x01 \x01(\t\x12%\n\x07\x43ontent\x18\x02 \x01(\x0b\x32\x14.google.protobuf.Any2\xfb\x06\n\x07\x42\x61\x63kend\x12\x32\n\x06Health\x12\x16.backend.HealthMessage\x1a\x0e.backend.Reply\"\x00\x12\x34\n\x07Predict\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x12\x35\n\tLoadModel\x12\x15.backend.ModelOptions\x1a\x0f.backend.Result\"\x00\x12<\n\rPredictStream\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x30\x01\x12@\n\tEmbedding\x12\x17.backend.PredictOptions\x1a\x18.backend.EmbeddingResult\"\x00\x12\x41\n\rGenerateImage\x12\x1d.backend.GenerateImageRequest\x1a\x0f.backend.Result\"\x00\x12M\n\x12\x41udioTranscription\x12\x1a.backend.TranscriptRequest\x1a\x19.backend.TranscriptResult\"\x00\x12-\n\x03TTS\x12\x13.backend.TTSRequest\x1a\x0f.backend.Result\"\x00\x12J\n\x0eTokenizeString\x12\x17.backend.PredictOptions\x1a\x1d.backend.TokenizationResponse\"\x00\x12;\n\x06Status\x12\x16.backend.HealthMessage\x1a\x17.backend.StatusResponse\"\x00\x12\x39\n\tStoresSet\x12\x19.backend.StoresSetOptions\x1a\x0f.backend.Result\"\x00\x12?\n\x0cStoresDelete\x12\x1c.backend.StoresDeleteOptions\x1a\x0f.backend.Result\"\x00\x12\x42\n\tStoresGet\x12\x19.backend.StoresGetOptions\x1a\x18.backend.StoresGetResult\"\x00\x12\x45\n\nStoresFind\x12\x1a.backend.StoresFindOptions\x1a\x19.backend.StoresFindResult\"\x00\x42Z\n\x19io.skynet.localai.backendB\x0eLocalAIBackendP\x01Z+github.com/go-skynet/LocalAI/pkg/grpc/protob\x06proto3')
 
 _globals = globals()
 _builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, _globals)
 _builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, 'backend_pb2', _globals)
 if _descriptor._USE_C_DESCRIPTORS == False:
-
-  DESCRIPTOR._options = None
-  DESCRIPTOR._serialized_options = b'\n\031io.skynet.localai.backendB\016LocalAIBackendP\001Z+github.com/go-skynet/LocalAI/pkg/grpc/proto'
-  _MEMORYUSAGEDATA_BREAKDOWNENTRY._options = None
-  _MEMORYUSAGEDATA_BREAKDOWNENTRY._serialized_options = b'8\001'
-  _globals['_HEALTHMESSAGE']._serialized_start=26
-  _globals['_HEALTHMESSAGE']._serialized_end=41
-  _globals['_PREDICTOPTIONS']._serialized_start=44
-  _globals['_PREDICTOPTIONS']._serialized_end=850
-  _globals['_REPLY']._serialized_start=852
-  _globals['_REPLY']._serialized_end=876
-  _globals['_MODELOPTIONS']._serialized_start=879
-  _globals['_MODELOPTIONS']._serialized_end=1951
-  _globals['_RESULT']._serialized_start=1953
-  _globals['_RESULT']._serialized_end=1995
-  _globals['_EMBEDDINGRESULT']._serialized_start=1997
-  _globals['_EMBEDDINGRESULT']._serialized_end=2034
-  _globals['_TRANSCRIPTREQUEST']._serialized_start=2036
-  _globals['_TRANSCRIPTREQUEST']._serialized_end=2103
-  _globals['_TRANSCRIPTRESULT']._serialized_start=2105
-  _globals['_TRANSCRIPTRESULT']._serialized_end=2183
-  _globals['_TRANSCRIPTSEGMENT']._serialized_start=2185
-  _globals['_TRANSCRIPTSEGMENT']._serialized_end=2274
-  _globals['_GENERATEIMAGEREQUEST']._serialized_start=2277
-  _globals['_GENERATEIMAGEREQUEST']._serialized_end=2492
-  _globals['_TTSREQUEST']._serialized_start=2494
-  _globals['_TTSREQUEST']._serialized_end=2563
-  _globals['_TOKENIZATIONRESPONSE']._serialized_start=2565
-  _globals['_TOKENIZATIONRESPONSE']._serialized_end=2619
-  _globals['_MEMORYUSAGEDATA']._serialized_start=2622
-  _globals['_MEMORYUSAGEDATA']._serialized_end=2764
-  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_start=2716
-  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_end=2764
-  _globals['_STATUSRESPONSE']._serialized_start=2767
-  _globals['_STATUSRESPONSE']._serialized_end=2940
-  _globals['_STATUSRESPONSE_STATE']._serialized_start=2873
-  _globals['_STATUSRESPONSE_STATE']._serialized_end=2940
-  _globals['_BACKEND']._serialized_start=2943
-  _globals['_BACKEND']._serialized_end=3571
+  _globals['DESCRIPTOR']._options = None
+  _globals['DESCRIPTOR']._serialized_options = b'\n\031io.skynet.localai.backendB\016LocalAIBackendP\001Z+github.com/go-skynet/LocalAI/pkg/grpc/proto'
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._options = None
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_options = b'8\001'
+  _globals['_STORESKEY']._serialized_start=53
+  _globals['_STORESKEY']._serialized_end=80
+  _globals['_STORESVALUE']._serialized_start=82
+  _globals['_STORESVALUE']._serialized_end=110
+  _globals['_STORESSETOPTIONS']._serialized_start=112
+  _globals['_STORESSETOPTIONS']._serialized_end=202
+  _globals['_STORESDELETEOPTIONS']._serialized_start=204
+  _globals['_STORESDELETEOPTIONS']._serialized_end=259
+  _globals['_STORESGETOPTIONS']._serialized_start=261
+  _globals['_STORESGETOPTIONS']._serialized_end=313
+  _globals['_STORESGETRESULT']._serialized_start=315
+  _globals['_STORESGETRESULT']._serialized_end=404
+  _globals['_STORESFINDOPTIONS']._serialized_start=406
+  _globals['_STORESFINDOPTIONS']._serialized_end=472
+  _globals['_STORESFINDRESULT']._serialized_start=474
+  _globals['_STORESFINDRESULT']._serialized_end=586
+  _globals['_HEALTHMESSAGE']._serialized_start=588
+  _globals['_HEALTHMESSAGE']._serialized_end=603
+  _globals['_PREDICTOPTIONS']._serialized_start=606
+  _globals['_PREDICTOPTIONS']._serialized_end=1478
+  _globals['_REPLY']._serialized_start=1480
+  _globals['_REPLY']._serialized_end=1504
+  _globals['_MODELOPTIONS']._serialized_start=1507
+  _globals['_MODELOPTIONS']._serialized_end=2579
+  _globals['_RESULT']._serialized_start=2581
+  _globals['_RESULT']._serialized_end=2623
+  _globals['_EMBEDDINGRESULT']._serialized_start=2625
+  _globals['_EMBEDDINGRESULT']._serialized_end=2662
+  _globals['_TRANSCRIPTREQUEST']._serialized_start=2664
+  _globals['_TRANSCRIPTREQUEST']._serialized_end=2731
+  _globals['_TRANSCRIPTRESULT']._serialized_start=2733
+  _globals['_TRANSCRIPTRESULT']._serialized_end=2811
+  _globals['_TRANSCRIPTSEGMENT']._serialized_start=2813
+  _globals['_TRANSCRIPTSEGMENT']._serialized_end=2902
+  _globals['_GENERATEIMAGEREQUEST']._serialized_start=2905
+  _globals['_GENERATEIMAGEREQUEST']._serialized_end=3120
+  _globals['_TTSREQUEST']._serialized_start=3122
+  _globals['_TTSREQUEST']._serialized_end=3191
+  _globals['_TOKENIZATIONRESPONSE']._serialized_start=3193
+  _globals['_TOKENIZATIONRESPONSE']._serialized_end=3247
+  _globals['_MEMORYUSAGEDATA']._serialized_start=3250
+  _globals['_MEMORYUSAGEDATA']._serialized_end=3392
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_start=3344
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_end=3392
+  _globals['_STATUSRESPONSE']._serialized_start=3395
+  _globals['_STATUSRESPONSE']._serialized_end=3568
+  _globals['_STATUSRESPONSE_STATE']._serialized_start=3501
+  _globals['_STATUSRESPONSE_STATE']._serialized_end=3568
+  _globals['_MESSAGE']._serialized_start=3570
+  _globals['_MESSAGE']._serialized_end=3632
+  _globals['_BACKEND']._serialized_start=3635
+  _globals['_BACKEND']._serialized_end=4526
 # @@protoc_insertion_point(module_scope)
diff --git a/backend/python/transformers/backend_pb2_grpc.py b/backend/python/transformers/backend_pb2_grpc.py
index 79a7677fb27f..e06fccf3d451 100644
--- a/backend/python/transformers/backend_pb2_grpc.py
+++ b/backend/python/transformers/backend_pb2_grpc.py
@@ -64,6 +64,26 @@ def __init__(self, channel):
                 request_serializer=backend__pb2.HealthMessage.SerializeToString,
                 response_deserializer=backend__pb2.StatusResponse.FromString,
                 )
+        self.StoresSet = channel.unary_unary(
+                '/backend.Backend/StoresSet',
+                request_serializer=backend__pb2.StoresSetOptions.SerializeToString,
+                response_deserializer=backend__pb2.Result.FromString,
+                )
+        self.StoresDelete = channel.unary_unary(
+                '/backend.Backend/StoresDelete',
+                request_serializer=backend__pb2.StoresDeleteOptions.SerializeToString,
+                response_deserializer=backend__pb2.Result.FromString,
+                )
+        self.StoresGet = channel.unary_unary(
+                '/backend.Backend/StoresGet',
+                request_serializer=backend__pb2.StoresGetOptions.SerializeToString,
+                response_deserializer=backend__pb2.StoresGetResult.FromString,
+                )
+        self.StoresFind = channel.unary_unary(
+                '/backend.Backend/StoresFind',
+                request_serializer=backend__pb2.StoresFindOptions.SerializeToString,
+                response_deserializer=backend__pb2.StoresFindResult.FromString,
+                )
 
 
 class BackendServicer(object):
@@ -129,6 +149,30 @@ def Status(self, request, context):
         context.set_details('Method not implemented!')
         raise NotImplementedError('Method not implemented!')
 
+    def StoresSet(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresDelete(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresGet(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresFind(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
 
 def add_BackendServicer_to_server(servicer, server):
     rpc_method_handlers = {
@@ -182,6 +226,26 @@ def add_BackendServicer_to_server(servicer, server):
                     request_deserializer=backend__pb2.HealthMessage.FromString,
                     response_serializer=backend__pb2.StatusResponse.SerializeToString,
             ),
+            'StoresSet': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresSet,
+                    request_deserializer=backend__pb2.StoresSetOptions.FromString,
+                    response_serializer=backend__pb2.Result.SerializeToString,
+            ),
+            'StoresDelete': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresDelete,
+                    request_deserializer=backend__pb2.StoresDeleteOptions.FromString,
+                    response_serializer=backend__pb2.Result.SerializeToString,
+            ),
+            'StoresGet': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresGet,
+                    request_deserializer=backend__pb2.StoresGetOptions.FromString,
+                    response_serializer=backend__pb2.StoresGetResult.SerializeToString,
+            ),
+            'StoresFind': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresFind,
+                    request_deserializer=backend__pb2.StoresFindOptions.FromString,
+                    response_serializer=backend__pb2.StoresFindResult.SerializeToString,
+            ),
     }
     generic_handler = grpc.method_handlers_generic_handler(
             'backend.Backend', rpc_method_handlers)
@@ -361,3 +425,71 @@ def Status(request,
             backend__pb2.StatusResponse.FromString,
             options, channel_credentials,
             insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresSet(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresSet',
+            backend__pb2.StoresSetOptions.SerializeToString,
+            backend__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresDelete(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresDelete',
+            backend__pb2.StoresDeleteOptions.SerializeToString,
+            backend__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresGet(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresGet',
+            backend__pb2.StoresGetOptions.SerializeToString,
+            backend__pb2.StoresGetResult.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresFind(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresFind',
+            backend__pb2.StoresFindOptions.SerializeToString,
+            backend__pb2.StoresFindResult.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
diff --git a/backend/python/vall-e-x/backend_pb2.py b/backend/python/vall-e-x/backend_pb2.py
index 08b896c7cad5..8d366c16d63b 100644
--- a/backend/python/vall-e-x/backend_pb2.py
+++ b/backend/python/vall-e-x/backend_pb2.py
@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 # Generated by the protocol buffer compiler.  DO NOT EDIT!
 # source: backend.proto
+# Protobuf Python Version: 4.25.1
 """Generated protocol buffer code."""
 from google.protobuf import descriptor as _descriptor
 from google.protobuf import descriptor_pool as _descriptor_pool
@@ -11,51 +12,69 @@
 _sym_db = _symbol_database.Default()
 
 
+from google.protobuf import any_pb2 as google_dot_protobuf_dot_any__pb2
 
 
-DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\rbackend.proto\x12\x07\x62\x61\x63kend\"\x0f\n\rHealthMessage\"\xa6\x06\n\x0ePredictOptions\x12\x0e\n\x06Prompt\x18\x01 \x01(\t\x12\x0c\n\x04Seed\x18\x02 \x01(\x05\x12\x0f\n\x07Threads\x18\x03 \x01(\x05\x12\x0e\n\x06Tokens\x18\x04 \x01(\x05\x12\x0c\n\x04TopK\x18\x05 \x01(\x05\x12\x0e\n\x06Repeat\x18\x06 \x01(\x05\x12\r\n\x05\x42\x61tch\x18\x07 \x01(\x05\x12\r\n\x05NKeep\x18\x08 \x01(\x05\x12\x13\n\x0bTemperature\x18\t \x01(\x02\x12\x0f\n\x07Penalty\x18\n \x01(\x02\x12\r\n\x05\x46\x31\x36KV\x18\x0b \x01(\x08\x12\x11\n\tDebugMode\x18\x0c \x01(\x08\x12\x13\n\x0bStopPrompts\x18\r \x03(\t\x12\x11\n\tIgnoreEOS\x18\x0e \x01(\x08\x12\x19\n\x11TailFreeSamplingZ\x18\x0f \x01(\x02\x12\x10\n\x08TypicalP\x18\x10 \x01(\x02\x12\x18\n\x10\x46requencyPenalty\x18\x11 \x01(\x02\x12\x17\n\x0fPresencePenalty\x18\x12 \x01(\x02\x12\x10\n\x08Mirostat\x18\x13 \x01(\x05\x12\x13\n\x0bMirostatETA\x18\x14 \x01(\x02\x12\x13\n\x0bMirostatTAU\x18\x15 \x01(\x02\x12\x12\n\nPenalizeNL\x18\x16 \x01(\x08\x12\x11\n\tLogitBias\x18\x17 \x01(\t\x12\r\n\x05MLock\x18\x19 \x01(\x08\x12\x0c\n\x04MMap\x18\x1a \x01(\x08\x12\x16\n\x0ePromptCacheAll\x18\x1b \x01(\x08\x12\x15\n\rPromptCacheRO\x18\x1c \x01(\x08\x12\x0f\n\x07Grammar\x18\x1d \x01(\t\x12\x0f\n\x07MainGPU\x18\x1e \x01(\t\x12\x13\n\x0bTensorSplit\x18\x1f \x01(\t\x12\x0c\n\x04TopP\x18  \x01(\x02\x12\x17\n\x0fPromptCachePath\x18! \x01(\t\x12\r\n\x05\x44\x65\x62ug\x18\" \x01(\x08\x12\x17\n\x0f\x45mbeddingTokens\x18# \x03(\x05\x12\x12\n\nEmbeddings\x18$ \x01(\t\x12\x14\n\x0cRopeFreqBase\x18% \x01(\x02\x12\x15\n\rRopeFreqScale\x18& \x01(\x02\x12\x1b\n\x13NegativePromptScale\x18\' \x01(\x02\x12\x16\n\x0eNegativePrompt\x18( \x01(\t\x12\x0e\n\x06NDraft\x18) \x01(\x05\x12\x0e\n\x06Images\x18* \x03(\t\"\x18\n\x05Reply\x12\x0f\n\x07message\x18\x01 \x01(\x0c\"\xb0\x08\n\x0cModelOptions\x12\r\n\x05Model\x18\x01 \x01(\t\x12\x13\n\x0b\x43ontextSize\x18\x02 \x01(\x05\x12\x0c\n\x04Seed\x18\x03 \x01(\x05\x12\x0e\n\x06NBatch\x18\x04 \x01(\x05\x12\x11\n\tF16Memory\x18\x05 \x01(\x08\x12\r\n\x05MLock\x18\x06 \x01(\x08\x12\x0c\n\x04MMap\x18\x07 \x01(\x08\x12\x11\n\tVocabOnly\x18\x08 \x01(\x08\x12\x0f\n\x07LowVRAM\x18\t \x01(\x08\x12\x12\n\nEmbeddings\x18\n \x01(\x08\x12\x0c\n\x04NUMA\x18\x0b \x01(\x08\x12\x12\n\nNGPULayers\x18\x0c \x01(\x05\x12\x0f\n\x07MainGPU\x18\r \x01(\t\x12\x13\n\x0bTensorSplit\x18\x0e \x01(\t\x12\x0f\n\x07Threads\x18\x0f \x01(\x05\x12\x19\n\x11LibrarySearchPath\x18\x10 \x01(\t\x12\x14\n\x0cRopeFreqBase\x18\x11 \x01(\x02\x12\x15\n\rRopeFreqScale\x18\x12 \x01(\x02\x12\x12\n\nRMSNormEps\x18\x13 \x01(\x02\x12\x0c\n\x04NGQA\x18\x14 \x01(\x05\x12\x11\n\tModelFile\x18\x15 \x01(\t\x12\x0e\n\x06\x44\x65vice\x18\x16 \x01(\t\x12\x11\n\tUseTriton\x18\x17 \x01(\x08\x12\x15\n\rModelBaseName\x18\x18 \x01(\t\x12\x18\n\x10UseFastTokenizer\x18\x19 \x01(\x08\x12\x14\n\x0cPipelineType\x18\x1a \x01(\t\x12\x15\n\rSchedulerType\x18\x1b \x01(\t\x12\x0c\n\x04\x43UDA\x18\x1c \x01(\x08\x12\x10\n\x08\x43\x46GScale\x18\x1d \x01(\x02\x12\x0f\n\x07IMG2IMG\x18\x1e \x01(\x08\x12\x11\n\tCLIPModel\x18\x1f \x01(\t\x12\x15\n\rCLIPSubfolder\x18  \x01(\t\x12\x10\n\x08\x43LIPSkip\x18! \x01(\x05\x12\x12\n\nControlNet\x18\x30 \x01(\t\x12\x11\n\tTokenizer\x18\" \x01(\t\x12\x10\n\x08LoraBase\x18# \x01(\t\x12\x13\n\x0bLoraAdapter\x18$ \x01(\t\x12\x11\n\tLoraScale\x18* \x01(\x02\x12\x11\n\tNoMulMatQ\x18% \x01(\x08\x12\x12\n\nDraftModel\x18\' \x01(\t\x12\x11\n\tAudioPath\x18& \x01(\t\x12\x14\n\x0cQuantization\x18( \x01(\t\x12\x1c\n\x14GPUMemoryUtilization\x18\x32 \x01(\x02\x12\x17\n\x0fTrustRemoteCode\x18\x33 \x01(\x08\x12\x14\n\x0c\x45nforceEager\x18\x34 \x01(\x08\x12\x11\n\tSwapSpace\x18\x35 \x01(\x05\x12\x13\n\x0bMaxModelLen\x18\x36 \x01(\x05\x12\x0e\n\x06MMProj\x18) \x01(\t\x12\x13\n\x0bRopeScaling\x18+ \x01(\t\x12\x15\n\rYarnExtFactor\x18, \x01(\x02\x12\x16\n\x0eYarnAttnFactor\x18- \x01(\x02\x12\x14\n\x0cYarnBetaFast\x18. \x01(\x02\x12\x14\n\x0cYarnBetaSlow\x18/ \x01(\x02\x12\x0c\n\x04Type\x18\x31 \x01(\t\"*\n\x06Result\x12\x0f\n\x07message\x18\x01 \x01(\t\x12\x0f\n\x07success\x18\x02 \x01(\x08\"%\n\x0f\x45mbeddingResult\x12\x12\n\nembeddings\x18\x01 \x03(\x02\"C\n\x11TranscriptRequest\x12\x0b\n\x03\x64st\x18\x02 \x01(\t\x12\x10\n\x08language\x18\x03 \x01(\t\x12\x0f\n\x07threads\x18\x04 \x01(\r\"N\n\x10TranscriptResult\x12,\n\x08segments\x18\x01 \x03(\x0b\x32\x1a.backend.TranscriptSegment\x12\x0c\n\x04text\x18\x02 \x01(\t\"Y\n\x11TranscriptSegment\x12\n\n\x02id\x18\x01 \x01(\x05\x12\r\n\x05start\x18\x02 \x01(\x03\x12\x0b\n\x03\x65nd\x18\x03 \x01(\x03\x12\x0c\n\x04text\x18\x04 \x01(\t\x12\x0e\n\x06tokens\x18\x05 \x03(\x05\"\xd7\x01\n\x14GenerateImageRequest\x12\x0e\n\x06height\x18\x01 \x01(\x05\x12\r\n\x05width\x18\x02 \x01(\x05\x12\x0c\n\x04mode\x18\x03 \x01(\x05\x12\x0c\n\x04step\x18\x04 \x01(\x05\x12\x0c\n\x04seed\x18\x05 \x01(\x05\x12\x17\n\x0fpositive_prompt\x18\x06 \x01(\t\x12\x17\n\x0fnegative_prompt\x18\x07 \x01(\t\x12\x0b\n\x03\x64st\x18\x08 \x01(\t\x12\x0b\n\x03src\x18\t \x01(\t\x12\x18\n\x10\x45nableParameters\x18\n \x01(\t\x12\x10\n\x08\x43LIPSkip\x18\x0b \x01(\x05\"E\n\nTTSRequest\x12\x0c\n\x04text\x18\x01 \x01(\t\x12\r\n\x05model\x18\x02 \x01(\t\x12\x0b\n\x03\x64st\x18\x03 \x01(\t\x12\r\n\x05voice\x18\x04 \x01(\t\"6\n\x14TokenizationResponse\x12\x0e\n\x06length\x18\x01 \x01(\x05\x12\x0e\n\x06tokens\x18\x02 \x03(\x05\"\x8e\x01\n\x0fMemoryUsageData\x12\r\n\x05total\x18\x01 \x01(\x04\x12:\n\tbreakdown\x18\x02 \x03(\x0b\x32\'.backend.MemoryUsageData.BreakdownEntry\x1a\x30\n\x0e\x42reakdownEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\x04:\x02\x38\x01\"\xad\x01\n\x0eStatusResponse\x12,\n\x05state\x18\x01 \x01(\x0e\x32\x1d.backend.StatusResponse.State\x12(\n\x06memory\x18\x02 \x01(\x0b\x32\x18.backend.MemoryUsageData\"C\n\x05State\x12\x11\n\rUNINITIALIZED\x10\x00\x12\x08\n\x04\x42USY\x10\x01\x12\t\n\x05READY\x10\x02\x12\x12\n\x05\x45RROR\x10\xff\xff\xff\xff\xff\xff\xff\xff\xff\x01\x32\xf4\x04\n\x07\x42\x61\x63kend\x12\x32\n\x06Health\x12\x16.backend.HealthMessage\x1a\x0e.backend.Reply\"\x00\x12\x34\n\x07Predict\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x12\x35\n\tLoadModel\x12\x15.backend.ModelOptions\x1a\x0f.backend.Result\"\x00\x12<\n\rPredictStream\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x30\x01\x12@\n\tEmbedding\x12\x17.backend.PredictOptions\x1a\x18.backend.EmbeddingResult\"\x00\x12\x41\n\rGenerateImage\x12\x1d.backend.GenerateImageRequest\x1a\x0f.backend.Result\"\x00\x12M\n\x12\x41udioTranscription\x12\x1a.backend.TranscriptRequest\x1a\x19.backend.TranscriptResult\"\x00\x12-\n\x03TTS\x12\x13.backend.TTSRequest\x1a\x0f.backend.Result\"\x00\x12J\n\x0eTokenizeString\x12\x17.backend.PredictOptions\x1a\x1d.backend.TokenizationResponse\"\x00\x12;\n\x06Status\x12\x16.backend.HealthMessage\x1a\x17.backend.StatusResponse\"\x00\x42Z\n\x19io.skynet.localai.backendB\x0eLocalAIBackendP\x01Z+github.com/go-skynet/LocalAI/pkg/grpc/protob\x06proto3')
+DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\rbackend.proto\x12\x07\x62\x61\x63kend\x1a\x19google/protobuf/any.proto\"\x1b\n\tStoresKey\x12\x0e\n\x06\x46loats\x18\x01 \x03(\x02\"\x1c\n\x0bStoresValue\x12\r\n\x05\x42ytes\x18\x01 \x01(\x0c\"Z\n\x10StoresSetOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\"7\n\x13StoresDeleteOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\"4\n\x10StoresGetOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\"Y\n\x0fStoresGetResult\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\"B\n\x11StoresFindOptions\x12\x1f\n\x03Key\x18\x01 \x01(\x0b\x32\x12.backend.StoresKey\x12\x0c\n\x04TopK\x18\x02 \x01(\x05\"p\n\x10StoresFindResult\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\x12\x14\n\x0cSimilarities\x18\x03 \x03(\x02\"\x0f\n\rHealthMessage\"\xe8\x06\n\x0ePredictOptions\x12\x0e\n\x06Prompt\x18\x01 \x01(\t\x12\x0c\n\x04Seed\x18\x02 \x01(\x05\x12\x0f\n\x07Threads\x18\x03 \x01(\x05\x12\x0e\n\x06Tokens\x18\x04 \x01(\x05\x12\x0c\n\x04TopK\x18\x05 \x01(\x05\x12\x0e\n\x06Repeat\x18\x06 \x01(\x05\x12\r\n\x05\x42\x61tch\x18\x07 \x01(\x05\x12\r\n\x05NKeep\x18\x08 \x01(\x05\x12\x13\n\x0bTemperature\x18\t \x01(\x02\x12\x0f\n\x07Penalty\x18\n \x01(\x02\x12\r\n\x05\x46\x31\x36KV\x18\x0b \x01(\x08\x12\x11\n\tDebugMode\x18\x0c \x01(\x08\x12\x13\n\x0bStopPrompts\x18\r \x03(\t\x12\x11\n\tIgnoreEOS\x18\x0e \x01(\x08\x12\x19\n\x11TailFreeSamplingZ\x18\x0f \x01(\x02\x12\x10\n\x08TypicalP\x18\x10 \x01(\x02\x12\x18\n\x10\x46requencyPenalty\x18\x11 \x01(\x02\x12\x17\n\x0fPresencePenalty\x18\x12 \x01(\x02\x12\x10\n\x08Mirostat\x18\x13 \x01(\x05\x12\x13\n\x0bMirostatETA\x18\x14 \x01(\x02\x12\x13\n\x0bMirostatTAU\x18\x15 \x01(\x02\x12\x12\n\nPenalizeNL\x18\x16 \x01(\x08\x12\x11\n\tLogitBias\x18\x17 \x01(\t\x12\r\n\x05MLock\x18\x19 \x01(\x08\x12\x0c\n\x04MMap\x18\x1a \x01(\x08\x12\x16\n\x0ePromptCacheAll\x18\x1b \x01(\x08\x12\x15\n\rPromptCacheRO\x18\x1c \x01(\x08\x12\x0f\n\x07Grammar\x18\x1d \x01(\t\x12\x0f\n\x07MainGPU\x18\x1e \x01(\t\x12\x13\n\x0bTensorSplit\x18\x1f \x01(\t\x12\x0c\n\x04TopP\x18  \x01(\x02\x12\x17\n\x0fPromptCachePath\x18! \x01(\t\x12\r\n\x05\x44\x65\x62ug\x18\" \x01(\x08\x12\x17\n\x0f\x45mbeddingTokens\x18# \x03(\x05\x12\x12\n\nEmbeddings\x18$ \x01(\t\x12\x14\n\x0cRopeFreqBase\x18% \x01(\x02\x12\x15\n\rRopeFreqScale\x18& \x01(\x02\x12\x1b\n\x13NegativePromptScale\x18\' \x01(\x02\x12\x16\n\x0eNegativePrompt\x18( \x01(\t\x12\x0e\n\x06NDraft\x18) \x01(\x05\x12\x0e\n\x06Images\x18* \x03(\t\x12\x1c\n\x14UseTokenizerTemplate\x18+ \x01(\x08\x12\"\n\x08Messages\x18, \x03(\x0b\x32\x10.backend.Message\"\x18\n\x05Reply\x12\x0f\n\x07message\x18\x01 \x01(\x0c\"\xb0\x08\n\x0cModelOptions\x12\r\n\x05Model\x18\x01 \x01(\t\x12\x13\n\x0b\x43ontextSize\x18\x02 \x01(\x05\x12\x0c\n\x04Seed\x18\x03 \x01(\x05\x12\x0e\n\x06NBatch\x18\x04 \x01(\x05\x12\x11\n\tF16Memory\x18\x05 \x01(\x08\x12\r\n\x05MLock\x18\x06 \x01(\x08\x12\x0c\n\x04MMap\x18\x07 \x01(\x08\x12\x11\n\tVocabOnly\x18\x08 \x01(\x08\x12\x0f\n\x07LowVRAM\x18\t \x01(\x08\x12\x12\n\nEmbeddings\x18\n \x01(\x08\x12\x0c\n\x04NUMA\x18\x0b \x01(\x08\x12\x12\n\nNGPULayers\x18\x0c \x01(\x05\x12\x0f\n\x07MainGPU\x18\r \x01(\t\x12\x13\n\x0bTensorSplit\x18\x0e \x01(\t\x12\x0f\n\x07Threads\x18\x0f \x01(\x05\x12\x19\n\x11LibrarySearchPath\x18\x10 \x01(\t\x12\x14\n\x0cRopeFreqBase\x18\x11 \x01(\x02\x12\x15\n\rRopeFreqScale\x18\x12 \x01(\x02\x12\x12\n\nRMSNormEps\x18\x13 \x01(\x02\x12\x0c\n\x04NGQA\x18\x14 \x01(\x05\x12\x11\n\tModelFile\x18\x15 \x01(\t\x12\x0e\n\x06\x44\x65vice\x18\x16 \x01(\t\x12\x11\n\tUseTriton\x18\x17 \x01(\x08\x12\x15\n\rModelBaseName\x18\x18 \x01(\t\x12\x18\n\x10UseFastTokenizer\x18\x19 \x01(\x08\x12\x14\n\x0cPipelineType\x18\x1a \x01(\t\x12\x15\n\rSchedulerType\x18\x1b \x01(\t\x12\x0c\n\x04\x43UDA\x18\x1c \x01(\x08\x12\x10\n\x08\x43\x46GScale\x18\x1d \x01(\x02\x12\x0f\n\x07IMG2IMG\x18\x1e \x01(\x08\x12\x11\n\tCLIPModel\x18\x1f \x01(\t\x12\x15\n\rCLIPSubfolder\x18  \x01(\t\x12\x10\n\x08\x43LIPSkip\x18! \x01(\x05\x12\x12\n\nControlNet\x18\x30 \x01(\t\x12\x11\n\tTokenizer\x18\" \x01(\t\x12\x10\n\x08LoraBase\x18# \x01(\t\x12\x13\n\x0bLoraAdapter\x18$ \x01(\t\x12\x11\n\tLoraScale\x18* \x01(\x02\x12\x11\n\tNoMulMatQ\x18% \x01(\x08\x12\x12\n\nDraftModel\x18\' \x01(\t\x12\x11\n\tAudioPath\x18& \x01(\t\x12\x14\n\x0cQuantization\x18( \x01(\t\x12\x1c\n\x14GPUMemoryUtilization\x18\x32 \x01(\x02\x12\x17\n\x0fTrustRemoteCode\x18\x33 \x01(\x08\x12\x14\n\x0c\x45nforceEager\x18\x34 \x01(\x08\x12\x11\n\tSwapSpace\x18\x35 \x01(\x05\x12\x13\n\x0bMaxModelLen\x18\x36 \x01(\x05\x12\x0e\n\x06MMProj\x18) \x01(\t\x12\x13\n\x0bRopeScaling\x18+ \x01(\t\x12\x15\n\rYarnExtFactor\x18, \x01(\x02\x12\x16\n\x0eYarnAttnFactor\x18- \x01(\x02\x12\x14\n\x0cYarnBetaFast\x18. \x01(\x02\x12\x14\n\x0cYarnBetaSlow\x18/ \x01(\x02\x12\x0c\n\x04Type\x18\x31 \x01(\t\"*\n\x06Result\x12\x0f\n\x07message\x18\x01 \x01(\t\x12\x0f\n\x07success\x18\x02 \x01(\x08\"%\n\x0f\x45mbeddingResult\x12\x12\n\nembeddings\x18\x01 \x03(\x02\"C\n\x11TranscriptRequest\x12\x0b\n\x03\x64st\x18\x02 \x01(\t\x12\x10\n\x08language\x18\x03 \x01(\t\x12\x0f\n\x07threads\x18\x04 \x01(\r\"N\n\x10TranscriptResult\x12,\n\x08segments\x18\x01 \x03(\x0b\x32\x1a.backend.TranscriptSegment\x12\x0c\n\x04text\x18\x02 \x01(\t\"Y\n\x11TranscriptSegment\x12\n\n\x02id\x18\x01 \x01(\x05\x12\r\n\x05start\x18\x02 \x01(\x03\x12\x0b\n\x03\x65nd\x18\x03 \x01(\x03\x12\x0c\n\x04text\x18\x04 \x01(\t\x12\x0e\n\x06tokens\x18\x05 \x03(\x05\"\xd7\x01\n\x14GenerateImageRequest\x12\x0e\n\x06height\x18\x01 \x01(\x05\x12\r\n\x05width\x18\x02 \x01(\x05\x12\x0c\n\x04mode\x18\x03 \x01(\x05\x12\x0c\n\x04step\x18\x04 \x01(\x05\x12\x0c\n\x04seed\x18\x05 \x01(\x05\x12\x17\n\x0fpositive_prompt\x18\x06 \x01(\t\x12\x17\n\x0fnegative_prompt\x18\x07 \x01(\t\x12\x0b\n\x03\x64st\x18\x08 \x01(\t\x12\x0b\n\x03src\x18\t \x01(\t\x12\x18\n\x10\x45nableParameters\x18\n \x01(\t\x12\x10\n\x08\x43LIPSkip\x18\x0b \x01(\x05\"E\n\nTTSRequest\x12\x0c\n\x04text\x18\x01 \x01(\t\x12\r\n\x05model\x18\x02 \x01(\t\x12\x0b\n\x03\x64st\x18\x03 \x01(\t\x12\r\n\x05voice\x18\x04 \x01(\t\"6\n\x14TokenizationResponse\x12\x0e\n\x06length\x18\x01 \x01(\x05\x12\x0e\n\x06tokens\x18\x02 \x03(\x05\"\x8e\x01\n\x0fMemoryUsageData\x12\r\n\x05total\x18\x01 \x01(\x04\x12:\n\tbreakdown\x18\x02 \x03(\x0b\x32\'.backend.MemoryUsageData.BreakdownEntry\x1a\x30\n\x0e\x42reakdownEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\x04:\x02\x38\x01\"\xad\x01\n\x0eStatusResponse\x12,\n\x05state\x18\x01 \x01(\x0e\x32\x1d.backend.StatusResponse.State\x12(\n\x06memory\x18\x02 \x01(\x0b\x32\x18.backend.MemoryUsageData\"C\n\x05State\x12\x11\n\rUNINITIALIZED\x10\x00\x12\x08\n\x04\x42USY\x10\x01\x12\t\n\x05READY\x10\x02\x12\x12\n\x05\x45RROR\x10\xff\xff\xff\xff\xff\xff\xff\xff\xff\x01\">\n\x07Message\x12\x0c\n\x04Role\x18\x01 \x01(\t\x12%\n\x07\x43ontent\x18\x02 \x01(\x0b\x32\x14.google.protobuf.Any2\xfb\x06\n\x07\x42\x61\x63kend\x12\x32\n\x06Health\x12\x16.backend.HealthMessage\x1a\x0e.backend.Reply\"\x00\x12\x34\n\x07Predict\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x12\x35\n\tLoadModel\x12\x15.backend.ModelOptions\x1a\x0f.backend.Result\"\x00\x12<\n\rPredictStream\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x30\x01\x12@\n\tEmbedding\x12\x17.backend.PredictOptions\x1a\x18.backend.EmbeddingResult\"\x00\x12\x41\n\rGenerateImage\x12\x1d.backend.GenerateImageRequest\x1a\x0f.backend.Result\"\x00\x12M\n\x12\x41udioTranscription\x12\x1a.backend.TranscriptRequest\x1a\x19.backend.TranscriptResult\"\x00\x12-\n\x03TTS\x12\x13.backend.TTSRequest\x1a\x0f.backend.Result\"\x00\x12J\n\x0eTokenizeString\x12\x17.backend.PredictOptions\x1a\x1d.backend.TokenizationResponse\"\x00\x12;\n\x06Status\x12\x16.backend.HealthMessage\x1a\x17.backend.StatusResponse\"\x00\x12\x39\n\tStoresSet\x12\x19.backend.StoresSetOptions\x1a\x0f.backend.Result\"\x00\x12?\n\x0cStoresDelete\x12\x1c.backend.StoresDeleteOptions\x1a\x0f.backend.Result\"\x00\x12\x42\n\tStoresGet\x12\x19.backend.StoresGetOptions\x1a\x18.backend.StoresGetResult\"\x00\x12\x45\n\nStoresFind\x12\x1a.backend.StoresFindOptions\x1a\x19.backend.StoresFindResult\"\x00\x42Z\n\x19io.skynet.localai.backendB\x0eLocalAIBackendP\x01Z+github.com/go-skynet/LocalAI/pkg/grpc/protob\x06proto3')
 
 _globals = globals()
 _builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, _globals)
 _builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, 'backend_pb2', _globals)
 if _descriptor._USE_C_DESCRIPTORS == False:
-
-  DESCRIPTOR._options = None
-  DESCRIPTOR._serialized_options = b'\n\031io.skynet.localai.backendB\016LocalAIBackendP\001Z+github.com/go-skynet/LocalAI/pkg/grpc/proto'
-  _MEMORYUSAGEDATA_BREAKDOWNENTRY._options = None
-  _MEMORYUSAGEDATA_BREAKDOWNENTRY._serialized_options = b'8\001'
-  _globals['_HEALTHMESSAGE']._serialized_start=26
-  _globals['_HEALTHMESSAGE']._serialized_end=41
-  _globals['_PREDICTOPTIONS']._serialized_start=44
-  _globals['_PREDICTOPTIONS']._serialized_end=850
-  _globals['_REPLY']._serialized_start=852
-  _globals['_REPLY']._serialized_end=876
-  _globals['_MODELOPTIONS']._serialized_start=879
-  _globals['_MODELOPTIONS']._serialized_end=1951
-  _globals['_RESULT']._serialized_start=1953
-  _globals['_RESULT']._serialized_end=1995
-  _globals['_EMBEDDINGRESULT']._serialized_start=1997
-  _globals['_EMBEDDINGRESULT']._serialized_end=2034
-  _globals['_TRANSCRIPTREQUEST']._serialized_start=2036
-  _globals['_TRANSCRIPTREQUEST']._serialized_end=2103
-  _globals['_TRANSCRIPTRESULT']._serialized_start=2105
-  _globals['_TRANSCRIPTRESULT']._serialized_end=2183
-  _globals['_TRANSCRIPTSEGMENT']._serialized_start=2185
-  _globals['_TRANSCRIPTSEGMENT']._serialized_end=2274
-  _globals['_GENERATEIMAGEREQUEST']._serialized_start=2277
-  _globals['_GENERATEIMAGEREQUEST']._serialized_end=2492
-  _globals['_TTSREQUEST']._serialized_start=2494
-  _globals['_TTSREQUEST']._serialized_end=2563
-  _globals['_TOKENIZATIONRESPONSE']._serialized_start=2565
-  _globals['_TOKENIZATIONRESPONSE']._serialized_end=2619
-  _globals['_MEMORYUSAGEDATA']._serialized_start=2622
-  _globals['_MEMORYUSAGEDATA']._serialized_end=2764
-  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_start=2716
-  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_end=2764
-  _globals['_STATUSRESPONSE']._serialized_start=2767
-  _globals['_STATUSRESPONSE']._serialized_end=2940
-  _globals['_STATUSRESPONSE_STATE']._serialized_start=2873
-  _globals['_STATUSRESPONSE_STATE']._serialized_end=2940
-  _globals['_BACKEND']._serialized_start=2943
-  _globals['_BACKEND']._serialized_end=3571
+  _globals['DESCRIPTOR']._options = None
+  _globals['DESCRIPTOR']._serialized_options = b'\n\031io.skynet.localai.backendB\016LocalAIBackendP\001Z+github.com/go-skynet/LocalAI/pkg/grpc/proto'
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._options = None
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_options = b'8\001'
+  _globals['_STORESKEY']._serialized_start=53
+  _globals['_STORESKEY']._serialized_end=80
+  _globals['_STORESVALUE']._serialized_start=82
+  _globals['_STORESVALUE']._serialized_end=110
+  _globals['_STORESSETOPTIONS']._serialized_start=112
+  _globals['_STORESSETOPTIONS']._serialized_end=202
+  _globals['_STORESDELETEOPTIONS']._serialized_start=204
+  _globals['_STORESDELETEOPTIONS']._serialized_end=259
+  _globals['_STORESGETOPTIONS']._serialized_start=261
+  _globals['_STORESGETOPTIONS']._serialized_end=313
+  _globals['_STORESGETRESULT']._serialized_start=315
+  _globals['_STORESGETRESULT']._serialized_end=404
+  _globals['_STORESFINDOPTIONS']._serialized_start=406
+  _globals['_STORESFINDOPTIONS']._serialized_end=472
+  _globals['_STORESFINDRESULT']._serialized_start=474
+  _globals['_STORESFINDRESULT']._serialized_end=586
+  _globals['_HEALTHMESSAGE']._serialized_start=588
+  _globals['_HEALTHMESSAGE']._serialized_end=603
+  _globals['_PREDICTOPTIONS']._serialized_start=606
+  _globals['_PREDICTOPTIONS']._serialized_end=1478
+  _globals['_REPLY']._serialized_start=1480
+  _globals['_REPLY']._serialized_end=1504
+  _globals['_MODELOPTIONS']._serialized_start=1507
+  _globals['_MODELOPTIONS']._serialized_end=2579
+  _globals['_RESULT']._serialized_start=2581
+  _globals['_RESULT']._serialized_end=2623
+  _globals['_EMBEDDINGRESULT']._serialized_start=2625
+  _globals['_EMBEDDINGRESULT']._serialized_end=2662
+  _globals['_TRANSCRIPTREQUEST']._serialized_start=2664
+  _globals['_TRANSCRIPTREQUEST']._serialized_end=2731
+  _globals['_TRANSCRIPTRESULT']._serialized_start=2733
+  _globals['_TRANSCRIPTRESULT']._serialized_end=2811
+  _globals['_TRANSCRIPTSEGMENT']._serialized_start=2813
+  _globals['_TRANSCRIPTSEGMENT']._serialized_end=2902
+  _globals['_GENERATEIMAGEREQUEST']._serialized_start=2905
+  _globals['_GENERATEIMAGEREQUEST']._serialized_end=3120
+  _globals['_TTSREQUEST']._serialized_start=3122
+  _globals['_TTSREQUEST']._serialized_end=3191
+  _globals['_TOKENIZATIONRESPONSE']._serialized_start=3193
+  _globals['_TOKENIZATIONRESPONSE']._serialized_end=3247
+  _globals['_MEMORYUSAGEDATA']._serialized_start=3250
+  _globals['_MEMORYUSAGEDATA']._serialized_end=3392
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_start=3344
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_end=3392
+  _globals['_STATUSRESPONSE']._serialized_start=3395
+  _globals['_STATUSRESPONSE']._serialized_end=3568
+  _globals['_STATUSRESPONSE_STATE']._serialized_start=3501
+  _globals['_STATUSRESPONSE_STATE']._serialized_end=3568
+  _globals['_MESSAGE']._serialized_start=3570
+  _globals['_MESSAGE']._serialized_end=3632
+  _globals['_BACKEND']._serialized_start=3635
+  _globals['_BACKEND']._serialized_end=4526
 # @@protoc_insertion_point(module_scope)
diff --git a/backend/python/vall-e-x/backend_pb2_grpc.py b/backend/python/vall-e-x/backend_pb2_grpc.py
index 79a7677fb27f..e06fccf3d451 100644
--- a/backend/python/vall-e-x/backend_pb2_grpc.py
+++ b/backend/python/vall-e-x/backend_pb2_grpc.py
@@ -64,6 +64,26 @@ def __init__(self, channel):
                 request_serializer=backend__pb2.HealthMessage.SerializeToString,
                 response_deserializer=backend__pb2.StatusResponse.FromString,
                 )
+        self.StoresSet = channel.unary_unary(
+                '/backend.Backend/StoresSet',
+                request_serializer=backend__pb2.StoresSetOptions.SerializeToString,
+                response_deserializer=backend__pb2.Result.FromString,
+                )
+        self.StoresDelete = channel.unary_unary(
+                '/backend.Backend/StoresDelete',
+                request_serializer=backend__pb2.StoresDeleteOptions.SerializeToString,
+                response_deserializer=backend__pb2.Result.FromString,
+                )
+        self.StoresGet = channel.unary_unary(
+                '/backend.Backend/StoresGet',
+                request_serializer=backend__pb2.StoresGetOptions.SerializeToString,
+                response_deserializer=backend__pb2.StoresGetResult.FromString,
+                )
+        self.StoresFind = channel.unary_unary(
+                '/backend.Backend/StoresFind',
+                request_serializer=backend__pb2.StoresFindOptions.SerializeToString,
+                response_deserializer=backend__pb2.StoresFindResult.FromString,
+                )
 
 
 class BackendServicer(object):
@@ -129,6 +149,30 @@ def Status(self, request, context):
         context.set_details('Method not implemented!')
         raise NotImplementedError('Method not implemented!')
 
+    def StoresSet(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresDelete(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresGet(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresFind(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
 
 def add_BackendServicer_to_server(servicer, server):
     rpc_method_handlers = {
@@ -182,6 +226,26 @@ def add_BackendServicer_to_server(servicer, server):
                     request_deserializer=backend__pb2.HealthMessage.FromString,
                     response_serializer=backend__pb2.StatusResponse.SerializeToString,
             ),
+            'StoresSet': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresSet,
+                    request_deserializer=backend__pb2.StoresSetOptions.FromString,
+                    response_serializer=backend__pb2.Result.SerializeToString,
+            ),
+            'StoresDelete': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresDelete,
+                    request_deserializer=backend__pb2.StoresDeleteOptions.FromString,
+                    response_serializer=backend__pb2.Result.SerializeToString,
+            ),
+            'StoresGet': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresGet,
+                    request_deserializer=backend__pb2.StoresGetOptions.FromString,
+                    response_serializer=backend__pb2.StoresGetResult.SerializeToString,
+            ),
+            'StoresFind': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresFind,
+                    request_deserializer=backend__pb2.StoresFindOptions.FromString,
+                    response_serializer=backend__pb2.StoresFindResult.SerializeToString,
+            ),
     }
     generic_handler = grpc.method_handlers_generic_handler(
             'backend.Backend', rpc_method_handlers)
@@ -361,3 +425,71 @@ def Status(request,
             backend__pb2.StatusResponse.FromString,
             options, channel_credentials,
             insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresSet(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresSet',
+            backend__pb2.StoresSetOptions.SerializeToString,
+            backend__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresDelete(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresDelete',
+            backend__pb2.StoresDeleteOptions.SerializeToString,
+            backend__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresGet(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresGet',
+            backend__pb2.StoresGetOptions.SerializeToString,
+            backend__pb2.StoresGetResult.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresFind(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresFind',
+            backend__pb2.StoresFindOptions.SerializeToString,
+            backend__pb2.StoresFindResult.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
diff --git a/backend/python/vllm/backend_pb2.py b/backend/python/vllm/backend_pb2.py
index 08b896c7cad5..8d366c16d63b 100644
--- a/backend/python/vllm/backend_pb2.py
+++ b/backend/python/vllm/backend_pb2.py
@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 # Generated by the protocol buffer compiler.  DO NOT EDIT!
 # source: backend.proto
+# Protobuf Python Version: 4.25.1
 """Generated protocol buffer code."""
 from google.protobuf import descriptor as _descriptor
 from google.protobuf import descriptor_pool as _descriptor_pool
@@ -11,51 +12,69 @@
 _sym_db = _symbol_database.Default()
 
 
+from google.protobuf import any_pb2 as google_dot_protobuf_dot_any__pb2
 
 
-DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\rbackend.proto\x12\x07\x62\x61\x63kend\"\x0f\n\rHealthMessage\"\xa6\x06\n\x0ePredictOptions\x12\x0e\n\x06Prompt\x18\x01 \x01(\t\x12\x0c\n\x04Seed\x18\x02 \x01(\x05\x12\x0f\n\x07Threads\x18\x03 \x01(\x05\x12\x0e\n\x06Tokens\x18\x04 \x01(\x05\x12\x0c\n\x04TopK\x18\x05 \x01(\x05\x12\x0e\n\x06Repeat\x18\x06 \x01(\x05\x12\r\n\x05\x42\x61tch\x18\x07 \x01(\x05\x12\r\n\x05NKeep\x18\x08 \x01(\x05\x12\x13\n\x0bTemperature\x18\t \x01(\x02\x12\x0f\n\x07Penalty\x18\n \x01(\x02\x12\r\n\x05\x46\x31\x36KV\x18\x0b \x01(\x08\x12\x11\n\tDebugMode\x18\x0c \x01(\x08\x12\x13\n\x0bStopPrompts\x18\r \x03(\t\x12\x11\n\tIgnoreEOS\x18\x0e \x01(\x08\x12\x19\n\x11TailFreeSamplingZ\x18\x0f \x01(\x02\x12\x10\n\x08TypicalP\x18\x10 \x01(\x02\x12\x18\n\x10\x46requencyPenalty\x18\x11 \x01(\x02\x12\x17\n\x0fPresencePenalty\x18\x12 \x01(\x02\x12\x10\n\x08Mirostat\x18\x13 \x01(\x05\x12\x13\n\x0bMirostatETA\x18\x14 \x01(\x02\x12\x13\n\x0bMirostatTAU\x18\x15 \x01(\x02\x12\x12\n\nPenalizeNL\x18\x16 \x01(\x08\x12\x11\n\tLogitBias\x18\x17 \x01(\t\x12\r\n\x05MLock\x18\x19 \x01(\x08\x12\x0c\n\x04MMap\x18\x1a \x01(\x08\x12\x16\n\x0ePromptCacheAll\x18\x1b \x01(\x08\x12\x15\n\rPromptCacheRO\x18\x1c \x01(\x08\x12\x0f\n\x07Grammar\x18\x1d \x01(\t\x12\x0f\n\x07MainGPU\x18\x1e \x01(\t\x12\x13\n\x0bTensorSplit\x18\x1f \x01(\t\x12\x0c\n\x04TopP\x18  \x01(\x02\x12\x17\n\x0fPromptCachePath\x18! \x01(\t\x12\r\n\x05\x44\x65\x62ug\x18\" \x01(\x08\x12\x17\n\x0f\x45mbeddingTokens\x18# \x03(\x05\x12\x12\n\nEmbeddings\x18$ \x01(\t\x12\x14\n\x0cRopeFreqBase\x18% \x01(\x02\x12\x15\n\rRopeFreqScale\x18& \x01(\x02\x12\x1b\n\x13NegativePromptScale\x18\' \x01(\x02\x12\x16\n\x0eNegativePrompt\x18( \x01(\t\x12\x0e\n\x06NDraft\x18) \x01(\x05\x12\x0e\n\x06Images\x18* \x03(\t\"\x18\n\x05Reply\x12\x0f\n\x07message\x18\x01 \x01(\x0c\"\xb0\x08\n\x0cModelOptions\x12\r\n\x05Model\x18\x01 \x01(\t\x12\x13\n\x0b\x43ontextSize\x18\x02 \x01(\x05\x12\x0c\n\x04Seed\x18\x03 \x01(\x05\x12\x0e\n\x06NBatch\x18\x04 \x01(\x05\x12\x11\n\tF16Memory\x18\x05 \x01(\x08\x12\r\n\x05MLock\x18\x06 \x01(\x08\x12\x0c\n\x04MMap\x18\x07 \x01(\x08\x12\x11\n\tVocabOnly\x18\x08 \x01(\x08\x12\x0f\n\x07LowVRAM\x18\t \x01(\x08\x12\x12\n\nEmbeddings\x18\n \x01(\x08\x12\x0c\n\x04NUMA\x18\x0b \x01(\x08\x12\x12\n\nNGPULayers\x18\x0c \x01(\x05\x12\x0f\n\x07MainGPU\x18\r \x01(\t\x12\x13\n\x0bTensorSplit\x18\x0e \x01(\t\x12\x0f\n\x07Threads\x18\x0f \x01(\x05\x12\x19\n\x11LibrarySearchPath\x18\x10 \x01(\t\x12\x14\n\x0cRopeFreqBase\x18\x11 \x01(\x02\x12\x15\n\rRopeFreqScale\x18\x12 \x01(\x02\x12\x12\n\nRMSNormEps\x18\x13 \x01(\x02\x12\x0c\n\x04NGQA\x18\x14 \x01(\x05\x12\x11\n\tModelFile\x18\x15 \x01(\t\x12\x0e\n\x06\x44\x65vice\x18\x16 \x01(\t\x12\x11\n\tUseTriton\x18\x17 \x01(\x08\x12\x15\n\rModelBaseName\x18\x18 \x01(\t\x12\x18\n\x10UseFastTokenizer\x18\x19 \x01(\x08\x12\x14\n\x0cPipelineType\x18\x1a \x01(\t\x12\x15\n\rSchedulerType\x18\x1b \x01(\t\x12\x0c\n\x04\x43UDA\x18\x1c \x01(\x08\x12\x10\n\x08\x43\x46GScale\x18\x1d \x01(\x02\x12\x0f\n\x07IMG2IMG\x18\x1e \x01(\x08\x12\x11\n\tCLIPModel\x18\x1f \x01(\t\x12\x15\n\rCLIPSubfolder\x18  \x01(\t\x12\x10\n\x08\x43LIPSkip\x18! \x01(\x05\x12\x12\n\nControlNet\x18\x30 \x01(\t\x12\x11\n\tTokenizer\x18\" \x01(\t\x12\x10\n\x08LoraBase\x18# \x01(\t\x12\x13\n\x0bLoraAdapter\x18$ \x01(\t\x12\x11\n\tLoraScale\x18* \x01(\x02\x12\x11\n\tNoMulMatQ\x18% \x01(\x08\x12\x12\n\nDraftModel\x18\' \x01(\t\x12\x11\n\tAudioPath\x18& \x01(\t\x12\x14\n\x0cQuantization\x18( \x01(\t\x12\x1c\n\x14GPUMemoryUtilization\x18\x32 \x01(\x02\x12\x17\n\x0fTrustRemoteCode\x18\x33 \x01(\x08\x12\x14\n\x0c\x45nforceEager\x18\x34 \x01(\x08\x12\x11\n\tSwapSpace\x18\x35 \x01(\x05\x12\x13\n\x0bMaxModelLen\x18\x36 \x01(\x05\x12\x0e\n\x06MMProj\x18) \x01(\t\x12\x13\n\x0bRopeScaling\x18+ \x01(\t\x12\x15\n\rYarnExtFactor\x18, \x01(\x02\x12\x16\n\x0eYarnAttnFactor\x18- \x01(\x02\x12\x14\n\x0cYarnBetaFast\x18. \x01(\x02\x12\x14\n\x0cYarnBetaSlow\x18/ \x01(\x02\x12\x0c\n\x04Type\x18\x31 \x01(\t\"*\n\x06Result\x12\x0f\n\x07message\x18\x01 \x01(\t\x12\x0f\n\x07success\x18\x02 \x01(\x08\"%\n\x0f\x45mbeddingResult\x12\x12\n\nembeddings\x18\x01 \x03(\x02\"C\n\x11TranscriptRequest\x12\x0b\n\x03\x64st\x18\x02 \x01(\t\x12\x10\n\x08language\x18\x03 \x01(\t\x12\x0f\n\x07threads\x18\x04 \x01(\r\"N\n\x10TranscriptResult\x12,\n\x08segments\x18\x01 \x03(\x0b\x32\x1a.backend.TranscriptSegment\x12\x0c\n\x04text\x18\x02 \x01(\t\"Y\n\x11TranscriptSegment\x12\n\n\x02id\x18\x01 \x01(\x05\x12\r\n\x05start\x18\x02 \x01(\x03\x12\x0b\n\x03\x65nd\x18\x03 \x01(\x03\x12\x0c\n\x04text\x18\x04 \x01(\t\x12\x0e\n\x06tokens\x18\x05 \x03(\x05\"\xd7\x01\n\x14GenerateImageRequest\x12\x0e\n\x06height\x18\x01 \x01(\x05\x12\r\n\x05width\x18\x02 \x01(\x05\x12\x0c\n\x04mode\x18\x03 \x01(\x05\x12\x0c\n\x04step\x18\x04 \x01(\x05\x12\x0c\n\x04seed\x18\x05 \x01(\x05\x12\x17\n\x0fpositive_prompt\x18\x06 \x01(\t\x12\x17\n\x0fnegative_prompt\x18\x07 \x01(\t\x12\x0b\n\x03\x64st\x18\x08 \x01(\t\x12\x0b\n\x03src\x18\t \x01(\t\x12\x18\n\x10\x45nableParameters\x18\n \x01(\t\x12\x10\n\x08\x43LIPSkip\x18\x0b \x01(\x05\"E\n\nTTSRequest\x12\x0c\n\x04text\x18\x01 \x01(\t\x12\r\n\x05model\x18\x02 \x01(\t\x12\x0b\n\x03\x64st\x18\x03 \x01(\t\x12\r\n\x05voice\x18\x04 \x01(\t\"6\n\x14TokenizationResponse\x12\x0e\n\x06length\x18\x01 \x01(\x05\x12\x0e\n\x06tokens\x18\x02 \x03(\x05\"\x8e\x01\n\x0fMemoryUsageData\x12\r\n\x05total\x18\x01 \x01(\x04\x12:\n\tbreakdown\x18\x02 \x03(\x0b\x32\'.backend.MemoryUsageData.BreakdownEntry\x1a\x30\n\x0e\x42reakdownEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\x04:\x02\x38\x01\"\xad\x01\n\x0eStatusResponse\x12,\n\x05state\x18\x01 \x01(\x0e\x32\x1d.backend.StatusResponse.State\x12(\n\x06memory\x18\x02 \x01(\x0b\x32\x18.backend.MemoryUsageData\"C\n\x05State\x12\x11\n\rUNINITIALIZED\x10\x00\x12\x08\n\x04\x42USY\x10\x01\x12\t\n\x05READY\x10\x02\x12\x12\n\x05\x45RROR\x10\xff\xff\xff\xff\xff\xff\xff\xff\xff\x01\x32\xf4\x04\n\x07\x42\x61\x63kend\x12\x32\n\x06Health\x12\x16.backend.HealthMessage\x1a\x0e.backend.Reply\"\x00\x12\x34\n\x07Predict\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x12\x35\n\tLoadModel\x12\x15.backend.ModelOptions\x1a\x0f.backend.Result\"\x00\x12<\n\rPredictStream\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x30\x01\x12@\n\tEmbedding\x12\x17.backend.PredictOptions\x1a\x18.backend.EmbeddingResult\"\x00\x12\x41\n\rGenerateImage\x12\x1d.backend.GenerateImageRequest\x1a\x0f.backend.Result\"\x00\x12M\n\x12\x41udioTranscription\x12\x1a.backend.TranscriptRequest\x1a\x19.backend.TranscriptResult\"\x00\x12-\n\x03TTS\x12\x13.backend.TTSRequest\x1a\x0f.backend.Result\"\x00\x12J\n\x0eTokenizeString\x12\x17.backend.PredictOptions\x1a\x1d.backend.TokenizationResponse\"\x00\x12;\n\x06Status\x12\x16.backend.HealthMessage\x1a\x17.backend.StatusResponse\"\x00\x42Z\n\x19io.skynet.localai.backendB\x0eLocalAIBackendP\x01Z+github.com/go-skynet/LocalAI/pkg/grpc/protob\x06proto3')
+DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\rbackend.proto\x12\x07\x62\x61\x63kend\x1a\x19google/protobuf/any.proto\"\x1b\n\tStoresKey\x12\x0e\n\x06\x46loats\x18\x01 \x03(\x02\"\x1c\n\x0bStoresValue\x12\r\n\x05\x42ytes\x18\x01 \x01(\x0c\"Z\n\x10StoresSetOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\"7\n\x13StoresDeleteOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\"4\n\x10StoresGetOptions\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\"Y\n\x0fStoresGetResult\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\"B\n\x11StoresFindOptions\x12\x1f\n\x03Key\x18\x01 \x01(\x0b\x32\x12.backend.StoresKey\x12\x0c\n\x04TopK\x18\x02 \x01(\x05\"p\n\x10StoresFindResult\x12 \n\x04Keys\x18\x01 \x03(\x0b\x32\x12.backend.StoresKey\x12$\n\x06Values\x18\x02 \x03(\x0b\x32\x14.backend.StoresValue\x12\x14\n\x0cSimilarities\x18\x03 \x03(\x02\"\x0f\n\rHealthMessage\"\xe8\x06\n\x0ePredictOptions\x12\x0e\n\x06Prompt\x18\x01 \x01(\t\x12\x0c\n\x04Seed\x18\x02 \x01(\x05\x12\x0f\n\x07Threads\x18\x03 \x01(\x05\x12\x0e\n\x06Tokens\x18\x04 \x01(\x05\x12\x0c\n\x04TopK\x18\x05 \x01(\x05\x12\x0e\n\x06Repeat\x18\x06 \x01(\x05\x12\r\n\x05\x42\x61tch\x18\x07 \x01(\x05\x12\r\n\x05NKeep\x18\x08 \x01(\x05\x12\x13\n\x0bTemperature\x18\t \x01(\x02\x12\x0f\n\x07Penalty\x18\n \x01(\x02\x12\r\n\x05\x46\x31\x36KV\x18\x0b \x01(\x08\x12\x11\n\tDebugMode\x18\x0c \x01(\x08\x12\x13\n\x0bStopPrompts\x18\r \x03(\t\x12\x11\n\tIgnoreEOS\x18\x0e \x01(\x08\x12\x19\n\x11TailFreeSamplingZ\x18\x0f \x01(\x02\x12\x10\n\x08TypicalP\x18\x10 \x01(\x02\x12\x18\n\x10\x46requencyPenalty\x18\x11 \x01(\x02\x12\x17\n\x0fPresencePenalty\x18\x12 \x01(\x02\x12\x10\n\x08Mirostat\x18\x13 \x01(\x05\x12\x13\n\x0bMirostatETA\x18\x14 \x01(\x02\x12\x13\n\x0bMirostatTAU\x18\x15 \x01(\x02\x12\x12\n\nPenalizeNL\x18\x16 \x01(\x08\x12\x11\n\tLogitBias\x18\x17 \x01(\t\x12\r\n\x05MLock\x18\x19 \x01(\x08\x12\x0c\n\x04MMap\x18\x1a \x01(\x08\x12\x16\n\x0ePromptCacheAll\x18\x1b \x01(\x08\x12\x15\n\rPromptCacheRO\x18\x1c \x01(\x08\x12\x0f\n\x07Grammar\x18\x1d \x01(\t\x12\x0f\n\x07MainGPU\x18\x1e \x01(\t\x12\x13\n\x0bTensorSplit\x18\x1f \x01(\t\x12\x0c\n\x04TopP\x18  \x01(\x02\x12\x17\n\x0fPromptCachePath\x18! \x01(\t\x12\r\n\x05\x44\x65\x62ug\x18\" \x01(\x08\x12\x17\n\x0f\x45mbeddingTokens\x18# \x03(\x05\x12\x12\n\nEmbeddings\x18$ \x01(\t\x12\x14\n\x0cRopeFreqBase\x18% \x01(\x02\x12\x15\n\rRopeFreqScale\x18& \x01(\x02\x12\x1b\n\x13NegativePromptScale\x18\' \x01(\x02\x12\x16\n\x0eNegativePrompt\x18( \x01(\t\x12\x0e\n\x06NDraft\x18) \x01(\x05\x12\x0e\n\x06Images\x18* \x03(\t\x12\x1c\n\x14UseTokenizerTemplate\x18+ \x01(\x08\x12\"\n\x08Messages\x18, \x03(\x0b\x32\x10.backend.Message\"\x18\n\x05Reply\x12\x0f\n\x07message\x18\x01 \x01(\x0c\"\xb0\x08\n\x0cModelOptions\x12\r\n\x05Model\x18\x01 \x01(\t\x12\x13\n\x0b\x43ontextSize\x18\x02 \x01(\x05\x12\x0c\n\x04Seed\x18\x03 \x01(\x05\x12\x0e\n\x06NBatch\x18\x04 \x01(\x05\x12\x11\n\tF16Memory\x18\x05 \x01(\x08\x12\r\n\x05MLock\x18\x06 \x01(\x08\x12\x0c\n\x04MMap\x18\x07 \x01(\x08\x12\x11\n\tVocabOnly\x18\x08 \x01(\x08\x12\x0f\n\x07LowVRAM\x18\t \x01(\x08\x12\x12\n\nEmbeddings\x18\n \x01(\x08\x12\x0c\n\x04NUMA\x18\x0b \x01(\x08\x12\x12\n\nNGPULayers\x18\x0c \x01(\x05\x12\x0f\n\x07MainGPU\x18\r \x01(\t\x12\x13\n\x0bTensorSplit\x18\x0e \x01(\t\x12\x0f\n\x07Threads\x18\x0f \x01(\x05\x12\x19\n\x11LibrarySearchPath\x18\x10 \x01(\t\x12\x14\n\x0cRopeFreqBase\x18\x11 \x01(\x02\x12\x15\n\rRopeFreqScale\x18\x12 \x01(\x02\x12\x12\n\nRMSNormEps\x18\x13 \x01(\x02\x12\x0c\n\x04NGQA\x18\x14 \x01(\x05\x12\x11\n\tModelFile\x18\x15 \x01(\t\x12\x0e\n\x06\x44\x65vice\x18\x16 \x01(\t\x12\x11\n\tUseTriton\x18\x17 \x01(\x08\x12\x15\n\rModelBaseName\x18\x18 \x01(\t\x12\x18\n\x10UseFastTokenizer\x18\x19 \x01(\x08\x12\x14\n\x0cPipelineType\x18\x1a \x01(\t\x12\x15\n\rSchedulerType\x18\x1b \x01(\t\x12\x0c\n\x04\x43UDA\x18\x1c \x01(\x08\x12\x10\n\x08\x43\x46GScale\x18\x1d \x01(\x02\x12\x0f\n\x07IMG2IMG\x18\x1e \x01(\x08\x12\x11\n\tCLIPModel\x18\x1f \x01(\t\x12\x15\n\rCLIPSubfolder\x18  \x01(\t\x12\x10\n\x08\x43LIPSkip\x18! \x01(\x05\x12\x12\n\nControlNet\x18\x30 \x01(\t\x12\x11\n\tTokenizer\x18\" \x01(\t\x12\x10\n\x08LoraBase\x18# \x01(\t\x12\x13\n\x0bLoraAdapter\x18$ \x01(\t\x12\x11\n\tLoraScale\x18* \x01(\x02\x12\x11\n\tNoMulMatQ\x18% \x01(\x08\x12\x12\n\nDraftModel\x18\' \x01(\t\x12\x11\n\tAudioPath\x18& \x01(\t\x12\x14\n\x0cQuantization\x18( \x01(\t\x12\x1c\n\x14GPUMemoryUtilization\x18\x32 \x01(\x02\x12\x17\n\x0fTrustRemoteCode\x18\x33 \x01(\x08\x12\x14\n\x0c\x45nforceEager\x18\x34 \x01(\x08\x12\x11\n\tSwapSpace\x18\x35 \x01(\x05\x12\x13\n\x0bMaxModelLen\x18\x36 \x01(\x05\x12\x0e\n\x06MMProj\x18) \x01(\t\x12\x13\n\x0bRopeScaling\x18+ \x01(\t\x12\x15\n\rYarnExtFactor\x18, \x01(\x02\x12\x16\n\x0eYarnAttnFactor\x18- \x01(\x02\x12\x14\n\x0cYarnBetaFast\x18. \x01(\x02\x12\x14\n\x0cYarnBetaSlow\x18/ \x01(\x02\x12\x0c\n\x04Type\x18\x31 \x01(\t\"*\n\x06Result\x12\x0f\n\x07message\x18\x01 \x01(\t\x12\x0f\n\x07success\x18\x02 \x01(\x08\"%\n\x0f\x45mbeddingResult\x12\x12\n\nembeddings\x18\x01 \x03(\x02\"C\n\x11TranscriptRequest\x12\x0b\n\x03\x64st\x18\x02 \x01(\t\x12\x10\n\x08language\x18\x03 \x01(\t\x12\x0f\n\x07threads\x18\x04 \x01(\r\"N\n\x10TranscriptResult\x12,\n\x08segments\x18\x01 \x03(\x0b\x32\x1a.backend.TranscriptSegment\x12\x0c\n\x04text\x18\x02 \x01(\t\"Y\n\x11TranscriptSegment\x12\n\n\x02id\x18\x01 \x01(\x05\x12\r\n\x05start\x18\x02 \x01(\x03\x12\x0b\n\x03\x65nd\x18\x03 \x01(\x03\x12\x0c\n\x04text\x18\x04 \x01(\t\x12\x0e\n\x06tokens\x18\x05 \x03(\x05\"\xd7\x01\n\x14GenerateImageRequest\x12\x0e\n\x06height\x18\x01 \x01(\x05\x12\r\n\x05width\x18\x02 \x01(\x05\x12\x0c\n\x04mode\x18\x03 \x01(\x05\x12\x0c\n\x04step\x18\x04 \x01(\x05\x12\x0c\n\x04seed\x18\x05 \x01(\x05\x12\x17\n\x0fpositive_prompt\x18\x06 \x01(\t\x12\x17\n\x0fnegative_prompt\x18\x07 \x01(\t\x12\x0b\n\x03\x64st\x18\x08 \x01(\t\x12\x0b\n\x03src\x18\t \x01(\t\x12\x18\n\x10\x45nableParameters\x18\n \x01(\t\x12\x10\n\x08\x43LIPSkip\x18\x0b \x01(\x05\"E\n\nTTSRequest\x12\x0c\n\x04text\x18\x01 \x01(\t\x12\r\n\x05model\x18\x02 \x01(\t\x12\x0b\n\x03\x64st\x18\x03 \x01(\t\x12\r\n\x05voice\x18\x04 \x01(\t\"6\n\x14TokenizationResponse\x12\x0e\n\x06length\x18\x01 \x01(\x05\x12\x0e\n\x06tokens\x18\x02 \x03(\x05\"\x8e\x01\n\x0fMemoryUsageData\x12\r\n\x05total\x18\x01 \x01(\x04\x12:\n\tbreakdown\x18\x02 \x03(\x0b\x32\'.backend.MemoryUsageData.BreakdownEntry\x1a\x30\n\x0e\x42reakdownEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\x04:\x02\x38\x01\"\xad\x01\n\x0eStatusResponse\x12,\n\x05state\x18\x01 \x01(\x0e\x32\x1d.backend.StatusResponse.State\x12(\n\x06memory\x18\x02 \x01(\x0b\x32\x18.backend.MemoryUsageData\"C\n\x05State\x12\x11\n\rUNINITIALIZED\x10\x00\x12\x08\n\x04\x42USY\x10\x01\x12\t\n\x05READY\x10\x02\x12\x12\n\x05\x45RROR\x10\xff\xff\xff\xff\xff\xff\xff\xff\xff\x01\">\n\x07Message\x12\x0c\n\x04Role\x18\x01 \x01(\t\x12%\n\x07\x43ontent\x18\x02 \x01(\x0b\x32\x14.google.protobuf.Any2\xfb\x06\n\x07\x42\x61\x63kend\x12\x32\n\x06Health\x12\x16.backend.HealthMessage\x1a\x0e.backend.Reply\"\x00\x12\x34\n\x07Predict\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x12\x35\n\tLoadModel\x12\x15.backend.ModelOptions\x1a\x0f.backend.Result\"\x00\x12<\n\rPredictStream\x12\x17.backend.PredictOptions\x1a\x0e.backend.Reply\"\x00\x30\x01\x12@\n\tEmbedding\x12\x17.backend.PredictOptions\x1a\x18.backend.EmbeddingResult\"\x00\x12\x41\n\rGenerateImage\x12\x1d.backend.GenerateImageRequest\x1a\x0f.backend.Result\"\x00\x12M\n\x12\x41udioTranscription\x12\x1a.backend.TranscriptRequest\x1a\x19.backend.TranscriptResult\"\x00\x12-\n\x03TTS\x12\x13.backend.TTSRequest\x1a\x0f.backend.Result\"\x00\x12J\n\x0eTokenizeString\x12\x17.backend.PredictOptions\x1a\x1d.backend.TokenizationResponse\"\x00\x12;\n\x06Status\x12\x16.backend.HealthMessage\x1a\x17.backend.StatusResponse\"\x00\x12\x39\n\tStoresSet\x12\x19.backend.StoresSetOptions\x1a\x0f.backend.Result\"\x00\x12?\n\x0cStoresDelete\x12\x1c.backend.StoresDeleteOptions\x1a\x0f.backend.Result\"\x00\x12\x42\n\tStoresGet\x12\x19.backend.StoresGetOptions\x1a\x18.backend.StoresGetResult\"\x00\x12\x45\n\nStoresFind\x12\x1a.backend.StoresFindOptions\x1a\x19.backend.StoresFindResult\"\x00\x42Z\n\x19io.skynet.localai.backendB\x0eLocalAIBackendP\x01Z+github.com/go-skynet/LocalAI/pkg/grpc/protob\x06proto3')
 
 _globals = globals()
 _builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, _globals)
 _builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, 'backend_pb2', _globals)
 if _descriptor._USE_C_DESCRIPTORS == False:
-
-  DESCRIPTOR._options = None
-  DESCRIPTOR._serialized_options = b'\n\031io.skynet.localai.backendB\016LocalAIBackendP\001Z+github.com/go-skynet/LocalAI/pkg/grpc/proto'
-  _MEMORYUSAGEDATA_BREAKDOWNENTRY._options = None
-  _MEMORYUSAGEDATA_BREAKDOWNENTRY._serialized_options = b'8\001'
-  _globals['_HEALTHMESSAGE']._serialized_start=26
-  _globals['_HEALTHMESSAGE']._serialized_end=41
-  _globals['_PREDICTOPTIONS']._serialized_start=44
-  _globals['_PREDICTOPTIONS']._serialized_end=850
-  _globals['_REPLY']._serialized_start=852
-  _globals['_REPLY']._serialized_end=876
-  _globals['_MODELOPTIONS']._serialized_start=879
-  _globals['_MODELOPTIONS']._serialized_end=1951
-  _globals['_RESULT']._serialized_start=1953
-  _globals['_RESULT']._serialized_end=1995
-  _globals['_EMBEDDINGRESULT']._serialized_start=1997
-  _globals['_EMBEDDINGRESULT']._serialized_end=2034
-  _globals['_TRANSCRIPTREQUEST']._serialized_start=2036
-  _globals['_TRANSCRIPTREQUEST']._serialized_end=2103
-  _globals['_TRANSCRIPTRESULT']._serialized_start=2105
-  _globals['_TRANSCRIPTRESULT']._serialized_end=2183
-  _globals['_TRANSCRIPTSEGMENT']._serialized_start=2185
-  _globals['_TRANSCRIPTSEGMENT']._serialized_end=2274
-  _globals['_GENERATEIMAGEREQUEST']._serialized_start=2277
-  _globals['_GENERATEIMAGEREQUEST']._serialized_end=2492
-  _globals['_TTSREQUEST']._serialized_start=2494
-  _globals['_TTSREQUEST']._serialized_end=2563
-  _globals['_TOKENIZATIONRESPONSE']._serialized_start=2565
-  _globals['_TOKENIZATIONRESPONSE']._serialized_end=2619
-  _globals['_MEMORYUSAGEDATA']._serialized_start=2622
-  _globals['_MEMORYUSAGEDATA']._serialized_end=2764
-  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_start=2716
-  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_end=2764
-  _globals['_STATUSRESPONSE']._serialized_start=2767
-  _globals['_STATUSRESPONSE']._serialized_end=2940
-  _globals['_STATUSRESPONSE_STATE']._serialized_start=2873
-  _globals['_STATUSRESPONSE_STATE']._serialized_end=2940
-  _globals['_BACKEND']._serialized_start=2943
-  _globals['_BACKEND']._serialized_end=3571
+  _globals['DESCRIPTOR']._options = None
+  _globals['DESCRIPTOR']._serialized_options = b'\n\031io.skynet.localai.backendB\016LocalAIBackendP\001Z+github.com/go-skynet/LocalAI/pkg/grpc/proto'
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._options = None
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_options = b'8\001'
+  _globals['_STORESKEY']._serialized_start=53
+  _globals['_STORESKEY']._serialized_end=80
+  _globals['_STORESVALUE']._serialized_start=82
+  _globals['_STORESVALUE']._serialized_end=110
+  _globals['_STORESSETOPTIONS']._serialized_start=112
+  _globals['_STORESSETOPTIONS']._serialized_end=202
+  _globals['_STORESDELETEOPTIONS']._serialized_start=204
+  _globals['_STORESDELETEOPTIONS']._serialized_end=259
+  _globals['_STORESGETOPTIONS']._serialized_start=261
+  _globals['_STORESGETOPTIONS']._serialized_end=313
+  _globals['_STORESGETRESULT']._serialized_start=315
+  _globals['_STORESGETRESULT']._serialized_end=404
+  _globals['_STORESFINDOPTIONS']._serialized_start=406
+  _globals['_STORESFINDOPTIONS']._serialized_end=472
+  _globals['_STORESFINDRESULT']._serialized_start=474
+  _globals['_STORESFINDRESULT']._serialized_end=586
+  _globals['_HEALTHMESSAGE']._serialized_start=588
+  _globals['_HEALTHMESSAGE']._serialized_end=603
+  _globals['_PREDICTOPTIONS']._serialized_start=606
+  _globals['_PREDICTOPTIONS']._serialized_end=1478
+  _globals['_REPLY']._serialized_start=1480
+  _globals['_REPLY']._serialized_end=1504
+  _globals['_MODELOPTIONS']._serialized_start=1507
+  _globals['_MODELOPTIONS']._serialized_end=2579
+  _globals['_RESULT']._serialized_start=2581
+  _globals['_RESULT']._serialized_end=2623
+  _globals['_EMBEDDINGRESULT']._serialized_start=2625
+  _globals['_EMBEDDINGRESULT']._serialized_end=2662
+  _globals['_TRANSCRIPTREQUEST']._serialized_start=2664
+  _globals['_TRANSCRIPTREQUEST']._serialized_end=2731
+  _globals['_TRANSCRIPTRESULT']._serialized_start=2733
+  _globals['_TRANSCRIPTRESULT']._serialized_end=2811
+  _globals['_TRANSCRIPTSEGMENT']._serialized_start=2813
+  _globals['_TRANSCRIPTSEGMENT']._serialized_end=2902
+  _globals['_GENERATEIMAGEREQUEST']._serialized_start=2905
+  _globals['_GENERATEIMAGEREQUEST']._serialized_end=3120
+  _globals['_TTSREQUEST']._serialized_start=3122
+  _globals['_TTSREQUEST']._serialized_end=3191
+  _globals['_TOKENIZATIONRESPONSE']._serialized_start=3193
+  _globals['_TOKENIZATIONRESPONSE']._serialized_end=3247
+  _globals['_MEMORYUSAGEDATA']._serialized_start=3250
+  _globals['_MEMORYUSAGEDATA']._serialized_end=3392
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_start=3344
+  _globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_end=3392
+  _globals['_STATUSRESPONSE']._serialized_start=3395
+  _globals['_STATUSRESPONSE']._serialized_end=3568
+  _globals['_STATUSRESPONSE_STATE']._serialized_start=3501
+  _globals['_STATUSRESPONSE_STATE']._serialized_end=3568
+  _globals['_MESSAGE']._serialized_start=3570
+  _globals['_MESSAGE']._serialized_end=3632
+  _globals['_BACKEND']._serialized_start=3635
+  _globals['_BACKEND']._serialized_end=4526
 # @@protoc_insertion_point(module_scope)
diff --git a/backend/python/vllm/backend_pb2_grpc.py b/backend/python/vllm/backend_pb2_grpc.py
index 79a7677fb27f..e06fccf3d451 100644
--- a/backend/python/vllm/backend_pb2_grpc.py
+++ b/backend/python/vllm/backend_pb2_grpc.py
@@ -64,6 +64,26 @@ def __init__(self, channel):
                 request_serializer=backend__pb2.HealthMessage.SerializeToString,
                 response_deserializer=backend__pb2.StatusResponse.FromString,
                 )
+        self.StoresSet = channel.unary_unary(
+                '/backend.Backend/StoresSet',
+                request_serializer=backend__pb2.StoresSetOptions.SerializeToString,
+                response_deserializer=backend__pb2.Result.FromString,
+                )
+        self.StoresDelete = channel.unary_unary(
+                '/backend.Backend/StoresDelete',
+                request_serializer=backend__pb2.StoresDeleteOptions.SerializeToString,
+                response_deserializer=backend__pb2.Result.FromString,
+                )
+        self.StoresGet = channel.unary_unary(
+                '/backend.Backend/StoresGet',
+                request_serializer=backend__pb2.StoresGetOptions.SerializeToString,
+                response_deserializer=backend__pb2.StoresGetResult.FromString,
+                )
+        self.StoresFind = channel.unary_unary(
+                '/backend.Backend/StoresFind',
+                request_serializer=backend__pb2.StoresFindOptions.SerializeToString,
+                response_deserializer=backend__pb2.StoresFindResult.FromString,
+                )
 
 
 class BackendServicer(object):
@@ -129,6 +149,30 @@ def Status(self, request, context):
         context.set_details('Method not implemented!')
         raise NotImplementedError('Method not implemented!')
 
+    def StoresSet(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresDelete(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresGet(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def StoresFind(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
 
 def add_BackendServicer_to_server(servicer, server):
     rpc_method_handlers = {
@@ -182,6 +226,26 @@ def add_BackendServicer_to_server(servicer, server):
                     request_deserializer=backend__pb2.HealthMessage.FromString,
                     response_serializer=backend__pb2.StatusResponse.SerializeToString,
             ),
+            'StoresSet': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresSet,
+                    request_deserializer=backend__pb2.StoresSetOptions.FromString,
+                    response_serializer=backend__pb2.Result.SerializeToString,
+            ),
+            'StoresDelete': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresDelete,
+                    request_deserializer=backend__pb2.StoresDeleteOptions.FromString,
+                    response_serializer=backend__pb2.Result.SerializeToString,
+            ),
+            'StoresGet': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresGet,
+                    request_deserializer=backend__pb2.StoresGetOptions.FromString,
+                    response_serializer=backend__pb2.StoresGetResult.SerializeToString,
+            ),
+            'StoresFind': grpc.unary_unary_rpc_method_handler(
+                    servicer.StoresFind,
+                    request_deserializer=backend__pb2.StoresFindOptions.FromString,
+                    response_serializer=backend__pb2.StoresFindResult.SerializeToString,
+            ),
     }
     generic_handler = grpc.method_handlers_generic_handler(
             'backend.Backend', rpc_method_handlers)
@@ -361,3 +425,71 @@ def Status(request,
             backend__pb2.StatusResponse.FromString,
             options, channel_credentials,
             insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresSet(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresSet',
+            backend__pb2.StoresSetOptions.SerializeToString,
+            backend__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresDelete(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresDelete',
+            backend__pb2.StoresDeleteOptions.SerializeToString,
+            backend__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresGet(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresGet',
+            backend__pb2.StoresGetOptions.SerializeToString,
+            backend__pb2.StoresGetResult.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def StoresFind(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/backend.Backend/StoresFind',
+            backend__pb2.StoresFindOptions.SerializeToString,
+            backend__pb2.StoresFindResult.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
diff --git a/backend/python/vllm/backend_vllm.py b/backend/python/vllm/backend_vllm.py
index ef5134b8fdcc..47d2bbc4e236 100644
--- a/backend/python/vllm/backend_vllm.py
+++ b/backend/python/vllm/backend_vllm.py
@@ -14,6 +14,7 @@
 from vllm.engine.async_llm_engine import AsyncLLMEngine
 from vllm.sampling_params import SamplingParams
 from vllm.utils import random_uuid
+from vllm.transformers_utils.tokenizer import get_tokenizer
 
 _ONE_DAY_IN_SECONDS = 60 * 60 * 24
 
@@ -71,7 +72,7 @@ def Health(self, request, context):
         """
         return backend_pb2.Reply(message=bytes("OK", 'utf-8'))
 
-    def LoadModel(self, request, context):
+    async def LoadModel(self, request, context):
         """
         Loads a language model.
 
@@ -103,6 +104,18 @@ def LoadModel(self, request, context):
             self.llm = AsyncLLMEngine.from_engine_args(engine_args)
         except Exception as err:
             return backend_pb2.Result(success=False, message=f"Unexpected {err=}, {type(err)=}")
+
+        try:
+           engine_model_config = await self.llm.get_model_config()
+           self.tokenizer = get_tokenizer(
+               engine_model_config.tokenizer,
+               tokenizer_mode=engine_model_config.tokenizer_mode,
+               trust_remote_code=engine_model_config.trust_remote_code,
+               truncation_side="left",
+           )
+        except Exception as err:
+            return backend_pb2.Result(success=False, message=f"Unexpected {err=}, {type(err)=}")
+
         return backend_pb2.Result(message="Model loaded successfully", success=True)
 
     async def Predict(self, request, context):
@@ -161,9 +174,13 @@ async def _predict(self, request, context, streaming=False):
         if request.Seed != 0:
             sampling_params.seed = request.Seed
 
+        prompt = request.Prompt
+        if request.UseTokenizerTemplate and request.Messages:
+            prompt = self.tokenizer.apply_chat_template(request.Messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
+
         # Generate text
         request_id = random_uuid()
-        outputs = self.llm.generate(request.Prompt, sampling_params, request_id)
+        outputs = self.llm.generate(prompt, sampling_params, request_id)
 
         # Stream the results
         generated_text = ""
diff --git a/core/backend/llm.go b/core/backend/llm.go
index d5e14df01c19..0b9693523396 100644
--- a/core/backend/llm.go
+++ b/core/backend/llm.go
@@ -2,6 +2,7 @@ package backend
 
 import (
 	"context"
+	"encoding/json"
 	"os"
 	"regexp"
 	"strings"
@@ -9,11 +10,18 @@ import (
 	"unicode/utf8"
 
 	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/schema"
 
 	"github.com/go-skynet/LocalAI/pkg/gallery"
 	"github.com/go-skynet/LocalAI/pkg/grpc"
+	"github.com/go-skynet/LocalAI/pkg/grpc/proto"
 	model "github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/go-skynet/LocalAI/pkg/utils"
+
+	"github.com/golang/protobuf/ptypes/any"
+	"github.com/golang/protobuf/ptypes/wrappers"
+	gproto "google.golang.org/protobuf/proto"
+	"google.golang.org/protobuf/types/known/anypb"
 )
 
 type LLMResponse struct {
@@ -26,7 +34,7 @@ type TokenUsage struct {
 	Completion int
 }
 
-func ModelInference(ctx context.Context, s string, images []string, loader *model.ModelLoader, c config.BackendConfig, o *config.ApplicationConfig, tokenCallback func(string, TokenUsage) bool) (func() (LLMResponse, error), error) {
+func ModelInference(ctx context.Context, s string, messages []schema.Message, images []string, loader *model.ModelLoader, c config.BackendConfig, o *config.ApplicationConfig, tokenCallback func(string, TokenUsage) bool) (func() (LLMResponse, error), error) {
 	modelFile := c.Model
 	threads := c.Threads
 	if *threads == 0 && o.Threads != 0 {
@@ -71,10 +79,27 @@ func ModelInference(ctx context.Context, s string, images []string, loader *mode
 		return nil, err
 	}
 
+	var protoMessages []*proto.Message
+	if c.TemplateConfig.UseTokenizerTemplate {
+		protoMessages = make([]*proto.Message, len(messages), len(messages))
+		for i, message := range messages {
+			content, err := ConvertInterfaceToAny(message.Content)
+			if err != nil {
+				return nil, err
+			}
+			protoMessages[i] = &proto.Message{
+				Role:    message.Role,
+				Content: content,
+			}
+		}
+	}
+
 	// in GRPC, the backend is supposed to answer to 1 single token if stream is not supported
 	fn := func() (LLMResponse, error) {
 		opts := gRPCPredictOpts(c, loader.ModelPath)
 		opts.Prompt = s
+		opts.Messages = protoMessages
+		opts.UseTokenizerTemplate = c.TemplateConfig.UseTokenizerTemplate
 		opts.Images = images
 
 		tokenUsage := TokenUsage{}
@@ -168,3 +193,13 @@ func Finetune(config config.BackendConfig, input, prediction string) string {
 	}
 	return prediction
 }
+
+func ConvertInterfaceToAny(v interface{}) (*any.Any, error) {
+	anyValue := &any.Any{}
+	bytes, _ := json.Marshal(v)
+	bytesValue := &wrappers.BytesValue{
+		Value: bytes,
+	}
+	err := anypb.MarshalFrom(anyValue, bytesValue, gproto.MarshalOptions{})
+	return anyValue, err
+}
diff --git a/core/config/backend_config.go b/core/config/backend_config.go
index a90b1c1bc694..f97cf3d0add5 100644
--- a/core/config/backend_config.go
+++ b/core/config/backend_config.go
@@ -165,11 +165,12 @@ type Functions struct {
 }
 
 type TemplateConfig struct {
-	Chat        string `yaml:"chat"`
-	ChatMessage string `yaml:"chat_message"`
-	Completion  string `yaml:"completion"`
-	Edit        string `yaml:"edit"`
-	Functions   string `yaml:"function"`
+	Chat                 string `yaml:"chat"`
+	ChatMessage          string `yaml:"chat_message"`
+	Completion           string `yaml:"completion"`
+	Edit                 string `yaml:"edit"`
+	Functions            string `yaml:"function"`
+	UseTokenizerTemplate bool   `yaml:"use_tokenizer_templating"`
 }
 
 func (c *BackendConfig) SetFunctionCallString(s string) {
diff --git a/core/http/endpoints/openai/chat.go b/core/http/endpoints/openai/chat.go
index 871ae6c1c6a2..6ebdd004e2db 100644
--- a/core/http/endpoints/openai/chat.go
+++ b/core/http/endpoints/openai/chat.go
@@ -230,112 +230,152 @@ func ChatEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, startup
 
 		var predInput string
 
-		suppressConfigSystemPrompt := false
-		mess := []string{}
-		for messageIndex, i := range input.Messages {
-			var content string
-			role := i.Role
-
-			// if function call, we might want to customize the role so we can display better that the "assistant called a json action"
-			// if an "assistant_function_call" role is defined, we use it, otherwise we use the role that is passed by in the request
-			if (i.FunctionCall != nil || i.ToolCalls != nil) && i.Role == "assistant" {
-				roleFn := "assistant_function_call"
-				r := config.Roles[roleFn]
-				if r != "" {
-					role = roleFn
+		if !processFunctions && !config.TemplateConfig.UseTokenizerTemplate {
+
+			suppressConfigSystemPrompt := false
+			mess := []string{}
+			for messageIndex, i := range input.Messages {
+				var content string
+				role := i.Role
+
+				// if function call, we might want to customize the role so we can display better that the "assistant called a json action"
+				// if an "assistant_function_call" role is defined, we use it, otherwise we use the role that is passed by in the request
+				if (i.FunctionCall != nil || i.ToolCalls != nil) && i.Role == "assistant" {
+					roleFn := "assistant_function_call"
+					r := config.Roles[roleFn]
+					if r != "" {
+						role = roleFn
+					}
 				}
-			}
-			r := config.Roles[role]
-			contentExists := i.Content != nil && i.StringContent != ""
+				r := config.Roles[role]
+				contentExists := i.Content != nil && i.StringContent != ""
 
-			fcall := i.FunctionCall
-			if len(i.ToolCalls) > 0 {
-				fcall = i.ToolCalls
-			}
-
-			// First attempt to populate content via a chat message specific template
-			if config.TemplateConfig.ChatMessage != "" {
-				chatMessageData := model.ChatMessageTemplateData{
-					SystemPrompt: config.SystemPrompt,
-					Role:         r,
-					RoleName:     role,
-					Content:      i.StringContent,
-					FunctionCall: fcall,
-					FunctionName: i.Name,
-					LastMessage:  messageIndex == (len(input.Messages) - 1),
-					Function:     config.Grammar != "" && (messageIndex == (len(input.Messages) - 1)),
-					MessageIndex: messageIndex,
+				fcall := i.FunctionCall
+				if len(i.ToolCalls) > 0 {
+					fcall = i.ToolCalls
 				}
-				templatedChatMessage, err := ml.EvaluateTemplateForChatMessage(config.TemplateConfig.ChatMessage, chatMessageData)
-				if err != nil {
-					log.Error().Err(err).Interface("message", chatMessageData).Str("template", config.TemplateConfig.ChatMessage).Msg("error processing message with template, skipping")
-				} else {
-					if templatedChatMessage == "" {
-						log.Warn().Msgf("template \"%s\" produced blank output for %+v. Skipping!", config.TemplateConfig.ChatMessage, chatMessageData)
-						continue // TODO: This continue is here intentionally to skip over the line `mess = append(mess, content)` below, and to prevent the sprintf
-					}
-					log.Debug().Msgf("templated message for chat: %s", templatedChatMessage)
-					content = templatedChatMessage
-				}
-			}
 
-			marshalAnyRole := func(f any) {
-				j, err := json.Marshal(f)
-				if err == nil {
-					if contentExists {
-						content += "\n" + fmt.Sprint(r, " ", string(j))
-					} else {
-						content = fmt.Sprint(r, " ", string(j))
+				// First attempt to populate content via a chat message specific template
+				if config.TemplateConfig.ChatMessage != "" {
+					chatMessageData := model.ChatMessageTemplateData{
+						SystemPrompt: config.SystemPrompt,
+						Role:         r,
+						RoleName:     role,
+						Content:      i.StringContent,
+						FunctionCall: fcall,
+						FunctionName: i.Name,
+						LastMessage:  messageIndex == (len(input.Messages) - 1),
+						Function:     config.Grammar != "" && (messageIndex == (len(input.Messages) - 1)),
+						MessageIndex: messageIndex,
 					}
-				}
-			}
-			marshalAny := func(f any) {
-				j, err := json.Marshal(f)
-				if err == nil {
-					if contentExists {
-						content += "\n" + string(j)
+					templatedChatMessage, err := ml.EvaluateTemplateForChatMessage(config.TemplateConfig.ChatMessage, chatMessageData)
+					if err != nil {
+						log.Error().Err(err).Interface("message", chatMessageData).Str("template", config.TemplateConfig.ChatMessage).Msg("error processing message with template, skipping")
 					} else {
-						content = string(j)
+						if templatedChatMessage == "" {
+							log.Warn().Msgf("template \"%s\" produced blank output for %+v. Skipping!", config.TemplateConfig.ChatMessage, chatMessageData)
+							continue // TODO: This continue is here intentionally to skip over the line `mess = append(mess, content)` below, and to prevent the sprintf
+						}
+						log.Debug().Msgf("templated message for chat: %s", templatedChatMessage)
+						content = templatedChatMessage
 					}
 				}
-			}
-			// If this model doesn't have such a template, or if that template fails to return a value, template at the message level.
-			if content == "" {
-				if r != "" {
-					if contentExists {
-						content = fmt.Sprint(r, i.StringContent)
-					}
 
-					if i.FunctionCall != nil {
-						marshalAnyRole(i.FunctionCall)
-					}
-					if i.ToolCalls != nil {
-						marshalAnyRole(i.ToolCalls)
+				marshalAnyRole := func(f any) {
+					j, err := json.Marshal(f)
+					if err == nil {
+						if contentExists {
+							content += "\n" + fmt.Sprint(r, " ", string(j))
+						} else {
+							content = fmt.Sprint(r, " ", string(j))
+						}
 					}
-				} else {
-					if contentExists {
-						content = fmt.Sprint(i.StringContent)
+				}
+				marshalAny := func(f any) {
+					j, err := json.Marshal(f)
+					if err == nil {
+						if contentExists {
+							content += "\n" + string(j)
+						} else {
+							content = string(j)
+						}
 					}
-					if i.FunctionCall != nil {
-						marshalAny(i.FunctionCall)
+				}
+				// If this model doesn't have such a template, or if that template fails to return a value, template at the message level.
+				if content == "" {
+					if r != "" {
+						if contentExists {
+							content = fmt.Sprint(r, i.StringContent)
+						}
+
+						if i.FunctionCall != nil {
+							marshalAnyRole(i.FunctionCall)
+						}
+						if i.ToolCalls != nil {
+							marshalAnyRole(i.ToolCalls)
+						}
+					} else {
+						if contentExists {
+							content = fmt.Sprint(i.StringContent)
+						}
+						if i.FunctionCall != nil {
+							marshalAny(i.FunctionCall)
+						}
+						if i.ToolCalls != nil {
+							marshalAny(i.ToolCalls)
+						}
 					}
-					if i.ToolCalls != nil {
-						marshalAny(i.ToolCalls)
+					// Special Handling: System. We care if it was printed at all, not the r branch, so check seperately
+					if contentExists && role == "system" {
+						suppressConfigSystemPrompt = true
 					}
 				}
-				// Special Handling: System. We care if it was printed at all, not the r branch, so check seperately
-				if contentExists && role == "system" {
-					suppressConfigSystemPrompt = true
+
+				mess = append(mess, content)
+			}
+
+			predInput = strings.Join(mess, "\n")
+			log.Debug().Msgf("Prompt (before templating): %s", predInput)
+
+			templateFile := ""
+
+			// A model can have a "file.bin.tmpl" file associated with a prompt template prefix
+			if ml.ExistsInModelPath(fmt.Sprintf("%s.tmpl", config.Model)) {
+				templateFile = config.Model
+			}
+
+			if config.TemplateConfig.Chat != "" && !processFunctions {
+				templateFile = config.TemplateConfig.Chat
+			}
+
+			if config.TemplateConfig.Functions != "" && processFunctions {
+				templateFile = config.TemplateConfig.Functions
+			}
+
+			if templateFile != "" {
+				templatedInput, err := ml.EvaluateTemplateForPrompt(model.ChatPromptTemplate, templateFile, model.PromptTemplateData{
+					SystemPrompt:         config.SystemPrompt,
+					SuppressSystemPrompt: suppressConfigSystemPrompt,
+					Input:                predInput,
+					Functions:            funcs,
+				})
+				if err == nil {
+					predInput = templatedInput
+					log.Debug().Msgf("Template found, input modified to: %s", predInput)
+				} else {
+					log.Debug().Msgf("Template failed loading: %s", err.Error())
 				}
 			}
 
-			mess = append(mess, content)
+			log.Debug().Msgf("Prompt (after templating): %s", predInput)
+			if processFunctions {
+				log.Debug().Msgf("Grammar: %+v", config.Grammar)
+			}
 		}
 
-		predInput = strings.Join(mess, "\n")
-		log.Debug().Msgf("Prompt (before templating): %s", predInput)
+		switch {
+		case toStream:
 
-		if toStream {
 			log.Debug().Msgf("Stream request received")
 			c.Context().SetContentType("text/event-stream")
 			//c.Response().Header.SetContentType(fiber.MIMETextHTMLCharsetUTF8)
@@ -343,45 +383,7 @@ func ChatEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, startup
 			c.Set("Cache-Control", "no-cache")
 			c.Set("Connection", "keep-alive")
 			c.Set("Transfer-Encoding", "chunked")
-		}
-
-		templateFile := ""
-
-		// A model can have a "file.bin.tmpl" file associated with a prompt template prefix
-		if ml.ExistsInModelPath(fmt.Sprintf("%s.tmpl", config.Model)) {
-			templateFile = config.Model
-		}
-
-		if config.TemplateConfig.Chat != "" && !processFunctions {
-			templateFile = config.TemplateConfig.Chat
-		}
-
-		if config.TemplateConfig.Functions != "" && processFunctions {
-			templateFile = config.TemplateConfig.Functions
-		}
 
-		if templateFile != "" {
-			templatedInput, err := ml.EvaluateTemplateForPrompt(model.ChatPromptTemplate, templateFile, model.PromptTemplateData{
-				SystemPrompt:         config.SystemPrompt,
-				SuppressSystemPrompt: suppressConfigSystemPrompt,
-				Input:                predInput,
-				Functions:            funcs,
-			})
-			if err == nil {
-				predInput = templatedInput
-				log.Debug().Msgf("Template found, input modified to: %s", predInput)
-			} else {
-				log.Debug().Msgf("Template failed loading: %s", err.Error())
-			}
-		}
-
-		log.Debug().Msgf("Prompt (after templating): %s", predInput)
-		if processFunctions {
-			log.Debug().Msgf("Grammar: %+v", config.Grammar)
-		}
-
-		switch {
-		case toStream:
 			responses := make(chan schema.OpenAIResponse)
 
 			if !processFunctions {
@@ -563,7 +565,7 @@ func handleQuestion(config *config.BackendConfig, input *schema.OpenAIRequest, m
 		images = append(images, m.StringImages...)
 	}
 
-	predFunc, err := backend.ModelInference(input.Context, prompt, images, ml, *config, o, nil)
+	predFunc, err := backend.ModelInference(input.Context, prompt, input.Messages, images, ml, *config, o, nil)
 	if err != nil {
 		log.Error().Err(err).Msg("model inference failed")
 		return "", err
diff --git a/core/http/endpoints/openai/inference.go b/core/http/endpoints/openai/inference.go
index 5d97d21db8bb..06e784b72048 100644
--- a/core/http/endpoints/openai/inference.go
+++ b/core/http/endpoints/openai/inference.go
@@ -29,7 +29,7 @@ func ComputeChoices(
 	}
 
 	// get the model function to call for the result
-	predFunc, err := backend.ModelInference(req.Context, predInput, images, loader, *config, o, tokenCallback)
+	predFunc, err := backend.ModelInference(req.Context, predInput, req.Messages, images, loader, *config, o, tokenCallback)
 	if err != nil {
 		return result, backend.TokenUsage{}, err
 	}
diff --git a/go.mod b/go.mod
index 4dd207c71c46..1e8aa8c412ff 100644
--- a/go.mod
+++ b/go.mod
@@ -13,8 +13,9 @@ require (
 	github.com/go-skynet/go-bert.cpp v0.0.0-20230716133540-6abe312cded1
 	github.com/go-skynet/go-llama.cpp v0.0.0-20231009155254-aeba71ee8428
 	github.com/gofiber/fiber/v2 v2.52.0
+	github.com/gofiber/swagger v1.0.0
 	github.com/gofiber/template/html/v2 v2.1.1
-	github.com/gomarkdown/markdown v0.0.0-20231222211730-1d6d20845b47
+	github.com/golang/protobuf v1.5.3
 	github.com/google/uuid v1.5.0
 	github.com/hashicorp/go-multierror v1.1.1
 	github.com/hpcloud/tail v1.0.0
@@ -30,9 +31,11 @@ require (
 	github.com/phayes/freeport v0.0.0-20220201140144-74d24b5ae9f5
 	github.com/prometheus/client_golang v1.17.0
 	github.com/rs/zerolog v1.31.0
+	github.com/russross/blackfriday v1.6.0
 	github.com/sashabaranov/go-openai v1.20.4
 	github.com/schollz/progressbar/v3 v3.13.1
 	github.com/stretchr/testify v1.9.0
+	github.com/swaggo/swag v1.16.3
 	github.com/tmc/langchaingo v0.0.0-20231019140956-c636b3da7701
 	github.com/urfave/cli/v2 v2.27.1
 	github.com/valyala/fasthttp v1.51.0
@@ -64,8 +67,6 @@ require (
 	github.com/Masterminds/semver/v3 v3.2.0 // indirect
 	github.com/Microsoft/go-winio v0.6.0 // indirect
 	github.com/Nvveen/Gotty v0.0.0-20120604004816-cd527374f1e5 // indirect
-	github.com/PuerkitoBio/purell v1.2.1 // indirect
-	github.com/PuerkitoBio/urlesc v0.0.0-20170810143723-de5bf2ad4578 // indirect
 	github.com/alecthomas/chroma v0.10.0 // indirect
 	github.com/aymanbagabas/go-osc52 v1.0.3 // indirect
 	github.com/aymerick/douceur v0.2.0 // indirect
@@ -85,11 +86,9 @@ require (
 	github.com/go-openapi/jsonreference v0.21.0 // indirect
 	github.com/go-openapi/spec v0.21.0 // indirect
 	github.com/go-openapi/swag v0.23.0 // indirect
-	github.com/gofiber/swagger v1.0.0 // indirect
 	github.com/gofiber/template v1.8.3 // indirect
 	github.com/gofiber/utils v1.1.0 // indirect
 	github.com/gogo/protobuf v1.3.2 // indirect
-	github.com/golang/protobuf v1.5.3 // indirect
 	github.com/golang/snappy v0.0.2 // indirect
 	github.com/google/shlex v0.0.0-20191202100458-e7afc7fbc510 // indirect
 	github.com/gorilla/css v1.0.0 // indirect
@@ -119,12 +118,10 @@ require (
 	github.com/prometheus/client_model v0.4.1-0.20230718164431-9a2bf3000d16 // indirect
 	github.com/prometheus/common v0.44.0 // indirect
 	github.com/prometheus/procfs v0.11.1 // indirect
-	github.com/russross/blackfriday v1.6.0 // indirect
 	github.com/shopspring/decimal v1.2.0 // indirect
 	github.com/sirupsen/logrus v1.8.1 // indirect
 	github.com/spf13/cast v1.3.1 // indirect
 	github.com/swaggo/files/v2 v2.0.0 // indirect
-	github.com/swaggo/swag v1.16.3 // indirect
 	github.com/ulikunitz/xz v0.5.9 // indirect
 	github.com/xeipuuv/gojsonpointer v0.0.0-20180127040702-4e3ac2762d5f // indirect
 	github.com/xeipuuv/gojsonreference v0.0.0-20180127040603-bd5ef7bd5415 // indirect
@@ -140,7 +137,6 @@ require (
 	google.golang.org/genproto/googleapis/rpc v0.0.0-20230822172742-b8732ec3820d // indirect
 	gopkg.in/fsnotify.v1 v1.4.7 // indirect
 	gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7 // indirect
-	sigs.k8s.io/yaml v1.4.0 // indirect
 )
 
 require (
diff --git a/go.sum b/go.sum
index f81f10c8aff5..872d93866291 100644
--- a/go.sum
+++ b/go.sum
@@ -3,6 +3,8 @@ github.com/Azure/go-ansiterm v0.0.0-20170929234023-d6e3b3328b78/go.mod h1:LmzpDX
 github.com/BurntSushi/toml v0.3.1/go.mod h1:xHWCNGjB5oqiDr8zfno3MHue2Ht5sIBksp03qcyfWMU=
 github.com/KyleBanks/depth v1.2.1 h1:5h8fQADFrWtarTdtDudMmGsC7GPbOAu6RVB3ffsVFHc=
 github.com/KyleBanks/depth v1.2.1/go.mod h1:jzSb9d0L43HxTQfT+oSA1EEp2q+ne2uh6XgeJcm8brE=
+github.com/M0Rf30/go-tiny-dream v0.0.0-20231128165230-772a9c0d9aaf h1:UgjXLcE9I+VaVz7uBIlzAnyZIXwiDlIiTWqCh159aUI=
+github.com/M0Rf30/go-tiny-dream v0.0.0-20231128165230-772a9c0d9aaf/go.mod h1:UOf2Mb/deUri5agct5OJ4SLWjhI+kZKbsUVUeRb24I0=
 github.com/Masterminds/goutils v1.1.1 h1:5nUrii3FMTL5diU80unEVvNevw1nH4+ZV4DSLVJLSYI=
 github.com/Masterminds/goutils v1.1.1/go.mod h1:8cTjp+g8YejhMuvIA5y2vz3BpJxksy863GQaJW2MFNU=
 github.com/Masterminds/semver/v3 v3.2.0 h1:3MEsd0SM6jqZojhjLWWeBY+Kcjy9i6MQAeY7YgDP83g=
@@ -13,10 +15,6 @@ github.com/Microsoft/go-winio v0.6.0 h1:slsWYD/zyx7lCXoZVlvQrj0hPTM1HI4+v1sIda2y
 github.com/Microsoft/go-winio v0.6.0/go.mod h1:cTAf44im0RAYeL23bpB+fzCyDH2MJiz2BO69KH/soAE=
 github.com/Nvveen/Gotty v0.0.0-20120604004816-cd527374f1e5 h1:TngWCqHvy9oXAN6lEVMRuU21PR1EtLVZJmdB18Gu3Rw=
 github.com/Nvveen/Gotty v0.0.0-20120604004816-cd527374f1e5/go.mod h1:lmUJ/7eu/Q8D7ML55dXQrVaamCz2vxCfdQBasLZfHKk=
-github.com/PuerkitoBio/purell v1.2.1 h1:QsZ4TjvwiMpat6gBCBxEQI0rcS9ehtkKtSpiUnd9N28=
-github.com/PuerkitoBio/purell v1.2.1/go.mod h1:ZwHcC/82TOaovDi//J/804umJFFmbOHPngi8iYYv/Eo=
-github.com/PuerkitoBio/urlesc v0.0.0-20170810143723-de5bf2ad4578 h1:d+Bc7a5rLufV/sSk/8dngufqelfh6jnri85riMAaF/M=
-github.com/PuerkitoBio/urlesc v0.0.0-20170810143723-de5bf2ad4578/go.mod h1:uGdkoq3SwY9Y+13GIhn11/XLaGBb4BfwItxLd5jeuXE=
 github.com/alecthomas/chroma v0.10.0 h1:7XDcGkCQopCNKjZHfYrNLraA+M7e0fMiJ/Mfikbfjek=
 github.com/alecthomas/chroma v0.10.0/go.mod h1:jtJATyUxlIORhUOFNA9NZDWGAQ8wpxQQqNSB4rjA/1s=
 github.com/andybalholm/brotli v1.0.1/go.mod h1:loMXtMfwqflxFJPmdbJO0a3KNoPuLBgiu3qAvBg8x/Y=
@@ -45,8 +43,6 @@ github.com/containerd/continuity v0.3.0/go.mod h1:wJEAIwKOm/pBZuBd0JmeTvnLquTB1A
 github.com/coreos/go-systemd/v22 v22.3.2/go.mod h1:Y58oyj3AT4RCenI/lSvhwexgC+NSVTIJ3seZv2GcEnc=
 github.com/coreos/go-systemd/v22 v22.5.0/go.mod h1:Y58oyj3AT4RCenI/lSvhwexgC+NSVTIJ3seZv2GcEnc=
 github.com/cpuguy83/go-md2man/v2 v2.0.0-20190314233015-f79a8a8ca69d/go.mod h1:maD7wRr/U5Z6m/iR4s+kqSMx2CaBsrgA7czyZG/E6dU=
-github.com/cpuguy83/go-md2man/v2 v2.0.2 h1:p1EgwI/C7NhT0JmVkwCD2ZBK8j4aeHQX2pMHHBfMQ6w=
-github.com/cpuguy83/go-md2man/v2 v2.0.2/go.mod h1:tgQtvFlXSQOSOSIRvRPT7W67SCa46tRHOmNcaadrF8o=
 github.com/cpuguy83/go-md2man/v2 v2.0.4 h1:wfIWP927BUkWJb2NmU/kNDYIBTh/ziUX91+lVfRxZq4=
 github.com/cpuguy83/go-md2man/v2 v2.0.4/go.mod h1:tgQtvFlXSQOSOSIRvRPT7W67SCa46tRHOmNcaadrF8o=
 github.com/creack/pty v1.1.11 h1:07n33Z8lZxZ2qwegKbObQohDhXDQxiMMz1NOUGYlesw=
@@ -66,6 +62,8 @@ github.com/docker/go-connections v0.4.0 h1:El9xVISelRB7BuFusrZozjnkIM5YnzCViNKoh
 github.com/docker/go-connections v0.4.0/go.mod h1:Gbd7IOopHjR8Iph03tsViu4nIes5XhDvyHbTtUxmeec=
 github.com/docker/go-units v0.4.0 h1:3uh0PgVws3nIA0Q+MwDC8yjEPf9zjRfZZWXZYDct3Tw=
 github.com/docker/go-units v0.4.0/go.mod h1:fgPhTUdO+D/Jk86RDLlptpiXQzgHJF7gydDDbaIK4Dk=
+github.com/donomii/go-rwkv.cpp v0.0.0-20230715075832-c898cd0f62df h1:qVcBEZlvp5A1gGWNJj02xyDtbsUI2hohlQMSB1fgER4=
+github.com/donomii/go-rwkv.cpp v0.0.0-20230715075832-c898cd0f62df/go.mod h1:gWy7FIWioqYmYxkaoFyBnaKApeZVrUkHhv9EV9pz4dM=
 github.com/dsnet/compress v0.0.2-0.20210315054119-f66993602bf5 h1:iFaUwBSo5Svw6L7HYpRu/0lE3e0BaElwnNO1qkNQxBY=
 github.com/dsnet/compress v0.0.2-0.20210315054119-f66993602bf5/go.mod h1:qssHWj60/X5sZFNxpG4HBPDHVqxNm4DfnCKgrbZOT+s=
 github.com/dsnet/golib v0.0.0-20171103203638-1ea166775780/go.mod h1:Lj+Z9rebOhdfkVLjJ8T6VcRQv3SXugXy999NBtR9aFY=
@@ -74,6 +72,8 @@ github.com/fsnotify/fsnotify v1.4.7/go.mod h1:jwhsz4b93w/PPRr/qN1Yymfu8t87LnFCMo
 github.com/fsnotify/fsnotify v1.4.9/go.mod h1:znqG4EE+3YCdAaPaxE2ZRY/06pZUdp0tY4IgpuI1SZQ=
 github.com/fsnotify/fsnotify v1.7.0 h1:8JEhPFa5W2WU7YfeZzPNqzMP6Lwt7L2715Ggo0nosvA=
 github.com/fsnotify/fsnotify v1.7.0/go.mod h1:40Bi/Hjc2AVfZrqy+aj+yEI+/bRxZnMJyTJwOpGvigM=
+github.com/ggerganov/whisper.cpp/bindings/go v0.0.0-20230628193450-85ed71aaec8e h1:KtbU2JR3lJuXFASHG2+sVLucfMPBjWKUUKByX6C81mQ=
+github.com/ggerganov/whisper.cpp/bindings/go v0.0.0-20230628193450-85ed71aaec8e/go.mod h1:QIjZ9OktHFG7p+/m3sMvrAJKKdWrr1fZIK0rM6HZlyo=
 github.com/go-audio/audio v1.0.0 h1:zS9vebldgbQqktK4H0lUqWrG8P0NxCJVqcj7ZpNnwd4=
 github.com/go-audio/audio v1.0.0/go.mod h1:6uAu0+H2lHkwdGsAY+j2wHPNPpPoeg5AaEFh9FlA+Zs=
 github.com/go-audio/riff v1.0.0 h1:d8iCGbDvox9BfLagY94fBynxSPHO80LmZCaOsmKxokA=
@@ -95,6 +95,8 @@ github.com/go-openapi/spec v0.21.0 h1:LTVzPc3p/RzRnkQqLRndbAzjY0d0BCL72A6j3CdL9Z
 github.com/go-openapi/spec v0.21.0/go.mod h1:78u6VdPw81XU44qEWGhtr982gJ5BWg2c0I5XwVMotYk=
 github.com/go-openapi/swag v0.23.0 h1:vsEVJDUo2hPJ2tu0/Xc+4noaxyEffXNIs3cOULZ+GrE=
 github.com/go-openapi/swag v0.23.0/go.mod h1:esZ8ITTYEsH1V2trKHjAN8Ai7xHb8RV+YSZ577vPjgQ=
+github.com/go-skynet/go-bert.cpp v0.0.0-20230716133540-6abe312cded1 h1:yXvc7QfGtoZ51tUW/YVjoTwAfh8HG88XU7UOrbNlz5Y=
+github.com/go-skynet/go-bert.cpp v0.0.0-20230716133540-6abe312cded1/go.mod h1:fYjkCDRzC+oRLHSjQoajmYK6AmeJnmEanV27CClAcDc=
 github.com/go-skynet/go-llama.cpp v0.0.0-20231009155254-aeba71ee8428 h1:WYjkXL0Nw7dN2uDBMVCWQ8xLavrIhjF/DLczuh5L9TY=
 github.com/go-skynet/go-llama.cpp v0.0.0-20231009155254-aeba71ee8428/go.mod h1:iub0ugfTnflE3rcIuqV2pQSo15nEw3GLW/utm5gyERo=
 github.com/go-sql-driver/mysql v1.7.1 h1:lUIinVbN1DY0xBg0eMOzmmtGoHwWBbvnWubQUrtU8EI=
@@ -104,8 +106,6 @@ github.com/go-task/slim-sprig v0.0.0-20230315185526-52ccab3ef572 h1:tfuBGBXKqDEe
 github.com/go-task/slim-sprig v0.0.0-20230315185526-52ccab3ef572/go.mod h1:9Pwr4B2jHnOSGXyyzV8ROjYa2ojvAY6HCGYYfMoC3Ls=
 github.com/godbus/dbus/v5 v5.0.4/go.mod h1:xhWf0FNVPg57R7Z0UbKHbJfkEywrmjJnf7w5xrFpKfA=
 github.com/godbus/dbus/v5 v5.0.6/go.mod h1:xhWf0FNVPg57R7Z0UbKHbJfkEywrmjJnf7w5xrFpKfA=
-github.com/gofiber/fiber/v2 v2.50.0 h1:ia0JaB+uw3GpNSCR5nvC5dsaxXjRU5OEu36aytx+zGw=
-github.com/gofiber/fiber/v2 v2.50.0/go.mod h1:21eytvay9Is7S6z+OgPi7c7n4++tnClWmhpimVHMimw=
 github.com/gofiber/fiber/v2 v2.52.0 h1:S+qXi7y+/Pgvqq4DrSmREGiFwtB7Bu6+QFLuIHYw/UE=
 github.com/gofiber/fiber/v2 v2.52.0/go.mod h1:KEOE+cXMhXG0zHc9d8+E38hoX+ZN7bhOtgeF2oT6jrQ=
 github.com/gofiber/swagger v1.0.0 h1:BzUzDS9ZT6fDUa692kxmfOjc1DZiloLiPK/W5z1H1tc=
@@ -131,8 +131,6 @@ github.com/golang/protobuf v1.5.3 h1:KhyjKVUg7Usr/dYsdSqoFveMYd5ko72D+zANwlG1mmg
 github.com/golang/protobuf v1.5.3/go.mod h1:XVQd3VNwM+JqD3oG2Ue2ip4fOMUkwXdXDdiuN0vRsmY=
 github.com/golang/snappy v0.0.2 h1:aeE13tS0IiQgFjYdoL8qN3K1N2bXXtI6Vi51/y7BpMw=
 github.com/golang/snappy v0.0.2/go.mod h1:/XxbfmMg8lxefKM7IXC3fBNl/7bRcc72aCRzEWrmP2Q=
-github.com/gomarkdown/markdown v0.0.0-20231222211730-1d6d20845b47 h1:k4Tw0nt6lwro3Uin8eqoET7MDA4JnT8YgbCjc/g5E3k=
-github.com/gomarkdown/markdown v0.0.0-20231222211730-1d6d20845b47/go.mod h1:JDGcbDT52eL4fju3sZ4TeHGsQwhG9nbDV21aMyhwPoA=
 github.com/google/go-cmp v0.3.0/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
 github.com/google/go-cmp v0.3.1/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
 github.com/google/go-cmp v0.4.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
@@ -147,8 +145,6 @@ github.com/google/pprof v0.0.0-20210407192527-94a9f03dee38/go.mod h1:kpwsk12EmLe
 github.com/google/shlex v0.0.0-20191202100458-e7afc7fbc510 h1:El6M4kTTCOh6aBiKaUGG7oYTSPP8MxqL4YI3kZKwcP4=
 github.com/google/shlex v0.0.0-20191202100458-e7afc7fbc510/go.mod h1:pupxD2MaaD3pAXIBCelhxNneeOaAeabZDe5s4K6zSpQ=
 github.com/google/uuid v1.1.1/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
-github.com/google/uuid v1.3.1 h1:KjJaJ9iWZ3jOFZIf1Lqf4laDRCasjl0BCmnEGxkdLb4=
-github.com/google/uuid v1.3.1/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/google/uuid v1.5.0 h1:1p67kYwdtXjb0gL0BPiP1Av9wiZPo5A8z2cWkTZ+eyU=
 github.com/google/uuid v1.5.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/gorilla/css v1.0.0 h1:BQqNyPTi50JCFMTw/b67hByjMVXZRwGha6wxVGkeihY=
@@ -172,8 +168,6 @@ github.com/kisielk/errcheck v1.5.0/go.mod h1:pFxgyoBC7bSaBwPgfKdkLd5X25qrDl4LWUI
 github.com/kisielk/gotool v1.0.0/go.mod h1:XhKaO+MFFWcvkIS/tQcRk01m1F5IRFswLeQ+oQHNcck=
 github.com/klauspost/compress v1.4.1/go.mod h1:RyIbtBH6LamlWaDj8nUwkbUhJ87Yi3uG0guNDohfE1A=
 github.com/klauspost/compress v1.11.4/go.mod h1:aoV0uJVorq1K+umq18yTdKaF57EivdYsUV+/s2qKfXs=
-github.com/klauspost/compress v1.16.7 h1:2mk3MPGNzKyxErAw8YaohYh69+pa4sIQSC0fPGCFR9I=
-github.com/klauspost/compress v1.16.7/go.mod h1:ntbaceVETuRiXiv4DpjP66DpAtAGkEQskQzEyD//IeE=
 github.com/klauspost/compress v1.17.0 h1:Rnbp4K9EjcDuVuHtd0dgA4qNuv9yKDYKK1ulpJwgrqM=
 github.com/klauspost/compress v1.17.0/go.mod h1:ntbaceVETuRiXiv4DpjP66DpAtAGkEQskQzEyD//IeE=
 github.com/klauspost/cpuid v1.2.0/go.mod h1:Pj4uuM528wm8OyEC2QMXAi2YiTZ96dNQPGgoMS4s3ek=
@@ -198,7 +192,6 @@ github.com/mattn/go-colorable v0.1.13 h1:fFA4WZxdEF4tXPZVKMLwD8oUnCTTo08duU7wxec
 github.com/mattn/go-colorable v0.1.13/go.mod h1:7S9/ev0klgBDR4GtXTXX8a3vIGJpMovkB8vQcUbaXHg=
 github.com/mattn/go-isatty v0.0.16/go.mod h1:kYGgaQfpe5nmfYZH+SKPsOc2e4SrIfOl2e/yFXSvRLM=
 github.com/mattn/go-isatty v0.0.17/go.mod h1:kYGgaQfpe5nmfYZH+SKPsOc2e4SrIfOl2e/yFXSvRLM=
-github.com/mattn/go-isatty v0.0.19 h1:JITubQf0MOLdlGRuRq+jtsDlekdYPia9ZFsB8h/APPA=
 github.com/mattn/go-isatty v0.0.19/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
 github.com/mattn/go-isatty v0.0.20 h1:xfD0iDuEKnDkl03q4limB+vH+GxLEtL/jb4xVJSWWEY=
 github.com/mattn/go-isatty v0.0.20/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
@@ -226,12 +219,18 @@ github.com/moby/sys/mountinfo v0.5.0/go.mod h1:3bMD3Rg+zkqx8MRYPi7Pyb0Ie97QEBmdx
 github.com/moby/term v0.0.0-20201216013528-df9cb8a40635 h1:rzf0wL0CHVc8CEsgyygG0Mn9CNCCPZqOPaz8RiiHYQk=
 github.com/moby/term v0.0.0-20201216013528-df9cb8a40635/go.mod h1:FBS0z0QWA44HXygs7VXDUOGoN/1TV3RuWkLO04am3wc=
 github.com/mrunalp/fileutils v0.5.0/go.mod h1:M1WthSahJixYnrXQl/DFQuteStB1weuxD2QJNHXfbSQ=
+github.com/mudler/go-piper v0.0.0-20230621222733-56b8a81b4760 h1:OFVkSxR7CRSRSNm5dvpMRZwmSwWa8EMMnHbc84fW5tU=
+github.com/mudler/go-piper v0.0.0-20230621222733-56b8a81b4760/go.mod h1:O7SwdSWMilAWhBZMK9N9Y/oBDyMMzshE3ju8Xkexwig=
 github.com/mudler/go-processmanager v0.0.0-20230818213616-f204007f963c h1:CI5uGwqBpN8N7BrSKC+nmdfw+9nPQIDyjHHlaIiitZI=
 github.com/mudler/go-processmanager v0.0.0-20230818213616-f204007f963c/go.mod h1:gY3wyrhkRySJtmtI/JPt4a2mKv48h/M9pEZIW+SjeC0=
+github.com/mudler/go-stable-diffusion v0.0.0-20230605122230-d89260f598af h1:XFq6OUqsWQam0OrEr05okXsJK/TQur3zoZTHbiZD3Ks=
+github.com/mudler/go-stable-diffusion v0.0.0-20230605122230-d89260f598af/go.mod h1:8ufRkpz/S/9ahkaxzZ5i4WMgO9w4InEhuRoT7vK5Rnw=
 github.com/muesli/reflow v0.3.0 h1:IFsN6K9NfGtjeggFP+68I4chLZV2yIKsXJFNZ+eWh6s=
 github.com/muesli/reflow v0.3.0/go.mod h1:pbwTDkVPibjO2kyvBQRBxTWEEGDGq0FlB1BIKtnHY/8=
 github.com/muesli/termenv v0.13.0 h1:wK20DRpJdDX8b7Ek2QfhvqhRQFZ237RGRO0RQ/Iqdy0=
 github.com/muesli/termenv v0.13.0/go.mod h1:sP1+uffeLaEYpyOTb8pLCUctGcGLnoFjSn4YJK5e2bc=
+github.com/nomic-ai/gpt4all/gpt4all-bindings/golang v0.0.0-20231022042237-c25dc5193530 h1:YXMxHwHMB9jCBo2Yu5gz3mTB3T1TnZs/HmPLv15LUSA=
+github.com/nomic-ai/gpt4all/gpt4all-bindings/golang v0.0.0-20231022042237-c25dc5193530/go.mod h1:4T3CHXyrt+7FQHXaxULZfPjHbD8/99WuDDJa0YVZARI=
 github.com/nwaples/rardecode v1.1.0 h1:vSxaY8vQhOcVr4mm5e8XllHWTiM4JF507A0Katqw7MQ=
 github.com/nwaples/rardecode v1.1.0/go.mod h1:5DzqNKiOdpKKBH87u8VlvAnPZMXcGRhxWkRpHbbfGS0=
 github.com/nxadm/tail v1.4.4/go.mod h1:kenIhsEOeOJmVchQTgglprH7qJGnHDVpk1VPCcaMI8A=
@@ -328,7 +327,6 @@ github.com/stretchr/testify v1.6.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/
 github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
 github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
 github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
-github.com/stretchr/testify v1.8.4 h1:CcVxjf3Q8PM0mHUKJCdn+eZZtm5yQwehR5yeSVQQcUk=
 github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
 github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsTg=
 github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
@@ -349,14 +347,10 @@ github.com/ulikunitz/xz v0.5.8/go.mod h1:nbz6k7qbPmH4IRqmfOplQw/tblSgqTqBwxkY0oW
 github.com/ulikunitz/xz v0.5.9 h1:RsKRIA2MO8x56wkkcd3LbtcE/uMszhb6DpRf+3uwa3I=
 github.com/ulikunitz/xz v0.5.9/go.mod h1:nbz6k7qbPmH4IRqmfOplQw/tblSgqTqBwxkY0oWt/14=
 github.com/urfave/cli v1.22.1/go.mod h1:Gos4lmkARVdJ6EkW0WaNv/tZAAMe9V7XWyB60NtXRu0=
-github.com/urfave/cli/v2 v2.25.7 h1:VAzn5oq403l5pHjc4OhD54+XGO9cdKVL/7lDjF+iKUs=
-github.com/urfave/cli/v2 v2.25.7/go.mod h1:8qnjx1vcq5s2/wpsqoZFndg2CE5tNFyrTvS6SinrnYQ=
 github.com/urfave/cli/v2 v2.27.1 h1:8xSQ6szndafKVRmfyeUMxkNUJQMjL1F2zmsZ+qHpfho=
 github.com/urfave/cli/v2 v2.27.1/go.mod h1:8qnjx1vcq5s2/wpsqoZFndg2CE5tNFyrTvS6SinrnYQ=
 github.com/valyala/bytebufferpool v1.0.0 h1:GqA5TC/0021Y/b9FG4Oi9Mr3q7XYx6KllzawFIhcdPw=
 github.com/valyala/bytebufferpool v1.0.0/go.mod h1:6bBcMArwyJ5K/AmCkWv1jt77kVWyCJ6HpOuEn7z0Csc=
-github.com/valyala/fasthttp v1.50.0 h1:H7fweIlBm0rXLs2q0XbalvJ6r0CUPFWK3/bB4N13e9M=
-github.com/valyala/fasthttp v1.50.0/go.mod h1:k2zXd82h/7UZc3VOdJ2WaUqt1uZ/XpXAfE9i+HBC3lA=
 github.com/valyala/fasthttp v1.51.0 h1:8b30A5JlZ6C7AS81RsWjYMQmrZG6feChmgAolCl1SqA=
 github.com/valyala/fasthttp v1.51.0/go.mod h1:oI2XroL+lI7vdXyYoQk03bXBThfFl2cVdIA3Xl7cH8g=
 github.com/valyala/tcplisten v1.0.0 h1:rBHj/Xf+E1tRGZyWIWwJDiRY0zc1Js+CV5DqwacVSA8=
@@ -371,8 +365,6 @@ github.com/xeipuuv/gojsonschema v1.2.0 h1:LhYJRs+L4fBtjZUfuSZIKGeVu0QRy8e5Xi7D17
 github.com/xeipuuv/gojsonschema v1.2.0/go.mod h1:anYRn/JVcOK2ZgGU+IjEV4nwlhoK5sQluxsYJ78Id3Y=
 github.com/xi2/xz v0.0.0-20171230120015-48954b6210f8 h1:nIPpBwaJSVYIxUFsDv3M8ofmx9yWTog9BfvIu0q41lo=
 github.com/xi2/xz v0.0.0-20171230120015-48954b6210f8/go.mod h1:HUYIGzjTL3rfEspMxjDjgmT5uz5wzYJKVo23qUhYTos=
-github.com/xrash/smetrics v0.0.0-20201216005158-039620a65673 h1:bAn7/zixMGCfxrRTfdpNzjtPYqr8smhKouy9mxVdGPU=
-github.com/xrash/smetrics v0.0.0-20201216005158-039620a65673/go.mod h1:N3UwUGtsrSj3ccvlPHLoLsHnpR27oXr4ZE984MbSER8=
 github.com/xrash/smetrics v0.0.0-20240312152122-5f08fbb34913 h1:+qGGcbkzsfDQNPPe9UDgpxAWQrhbbBXOYJFQDq/dtJw=
 github.com/xrash/smetrics v0.0.0-20240312152122-5f08fbb34913/go.mod h1:4aEEwZQutDLsQv2Deui4iYQ6DWTxR14g6m8Wv88+Xqk=
 github.com/yuin/goldmark v1.1.27/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
@@ -401,15 +393,11 @@ golang.org/x/crypto v0.0.0-20191011191535-87dc89f01550/go.mod h1:yigFU9vqHzYiE8U
 golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
 golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
 golang.org/x/crypto v0.3.0/go.mod h1:hebNnKkNXi2UzZN1eVRvBB7co0a+JxK6XbPiWVs/3J4=
-golang.org/x/crypto v0.14.0 h1:wBqGXzWJW6m1XrIKlAH0Hs1JJ7+9KBwnIO8v66Q9cHc=
-golang.org/x/crypto v0.14.0/go.mod h1:MVFd36DqK4CsrnJYDkBA3VC4m2GkXAM0PvzMCn4JQf4=
 golang.org/x/crypto v0.21.0 h1:X31++rzVUdKhX5sWmSOFZxx8UW/ldWx55cbf08iNAMA=
 golang.org/x/crypto v0.21.0/go.mod h1:0BP7YvVV9gBbVKyeTG0Gyn+gZm94bibOW5BjDEYAOMs=
 golang.org/x/mod v0.2.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.3.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
-golang.org/x/mod v0.12.0 h1:rmsUpXtvNzj340zd98LZ4KntptpfRHwpFOHG188oHXc=
-golang.org/x/mod v0.12.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
 golang.org/x/mod v0.16.0 h1:QX4fJ0Rr5cPQCF7O9lh9Se4pmwfwskqZfq5moyldzic=
 golang.org/x/mod v0.16.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
 golang.org/x/net v0.0.0-20180906233101-161cd47e91fd/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
@@ -425,8 +413,6 @@ golang.org/x/net v0.0.0-20210428140749-89ef3d95e781/go.mod h1:OJAsFXCWl8Ukc7SiCT
 golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
 golang.org/x/net v0.0.0-20221002022538-bcab6841153b/go.mod h1:YDH+HFinaLZZlnHAfSS6ZXJJ9M9t4Dl22yv3iI2vPwk=
 golang.org/x/net v0.2.0/go.mod h1:KqCZLdyyvdV855qA2rE3GC2aiw5xGR5TEjj8smXukLY=
-golang.org/x/net v0.17.0 h1:pVaXccu2ozPjCXewfr1S7xza/zcXTity9cCdXQYSjIM=
-golang.org/x/net v0.17.0/go.mod h1:NxSsAGuq816PNPmqtQdLE42eU2Fs7NoRIZrHJAlaCOE=
 golang.org/x/net v0.22.0 h1:9sGLhx7iRIHEiX0oAJ3MRZMUCElJgy7Br1nO+AMN3Tc=
 golang.org/x/net v0.22.0/go.mod h1:JKghWKKOSdJwpW2GEx0Ja7fmaKnMsbu+MWVZTokSYmg=
 golang.org/x/sync v0.0.0-20180314180146-1d60e4601c6f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
@@ -435,9 +421,8 @@ golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJ
 golang.org/x/sync v0.0.0-20190911185100-cd5d95a43a6e/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20201020160332-67f06af15bc9/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
-golang.org/x/sync v0.3.0 h1:ftCYgMx6zT/asHUrPw8BLLscYtGznsLAnjq5RH9P66E=
-golang.org/x/sync v0.3.0/go.mod h1:FU7BRWz2tNW+3quACPkgCx/L+uEAv1htQ0V83Z9Rj+Y=
 golang.org/x/sync v0.6.0 h1:5BMeUDZ7vkXGfEr1x9B4bRcTH4lpkTkpdh0T/J+qjbQ=
+golang.org/x/sync v0.6.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
 golang.org/x/sys v0.0.0-20180909124046-d0be0721c37e/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
@@ -471,16 +456,12 @@ golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.10.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.11.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.12.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.17.0 h1:25cE3gD+tdBA7lp7QfhuV+rJiE9YXTcS3VG1SqssI/Y=
-golang.org/x/sys v0.17.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/sys v0.18.0 h1:DBdB3niSjOA/O0blCZBqDefyWNYveAYMNF1Wum0DYQ4=
 golang.org/x/sys v0.18.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
 golang.org/x/term v0.2.0/go.mod h1:TVmDHMZPmdnySmBfhjOoOdhjzdE1h4u1VwSiw2l1Nuc=
 golang.org/x/term v0.6.0/go.mod h1:m6U89DPEgQRMq3DNkDClhWw02AUbt2daBVO4cn4Hv9U=
-golang.org/x/term v0.13.0 h1:bb+I9cTfFazGW51MZqBVmZy7+JEJMouUHTUSKVQLBek=
-golang.org/x/term v0.13.0/go.mod h1:LTmsnFJwVN6bCy1rVCoS+qHT1HhALEFxKncY3WNNh4U=
 golang.org/x/term v0.18.0 h1:FcHjZXDMxI8mM3nwhX9HlKop4C0YQvCVCdwYl2wOtE8=
 golang.org/x/term v0.18.0/go.mod h1:ILwASektA3OnRv7amZ1xhE/KTR+u50pbXfZ03+6Nx58=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
@@ -488,8 +469,6 @@ golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
 golang.org/x/text v0.4.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
-golang.org/x/text v0.13.0 h1:ablQoSUd0tRdKxZewP80B+BaqeKJuVhuRxj/dkrun3k=
-golang.org/x/text v0.13.0/go.mod h1:TvPlkZtksWOMsz7fbANvkp4WM8x/WCo/om8BMLbz+aE=
 golang.org/x/text v0.14.0 h1:ScX5w1eTa3QqT8oi6+ziP7dTV1S2+ALU0bI+0zXKWiQ=
 golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
@@ -499,8 +478,6 @@ golang.org/x/tools v0.0.0-20200619180055-7c47624df98f/go.mod h1:EkVYQZoAsY45+roY
 golang.org/x/tools v0.0.0-20201224043029-2b0845dc783e/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
 golang.org/x/tools v0.0.0-20210106214847-113979e3529a/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
 golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=
-golang.org/x/tools v0.12.0 h1:YW6HUoUmYBpwSgyaGaZq1fHjrBjX1rlpZ54T6mu2kss=
-golang.org/x/tools v0.12.0/go.mod h1:Sc0INKfu04TlqNoRA1hgpFZbhYXHPr4V5DzpSBTPqQM=
 golang.org/x/tools v0.19.0 h1:tfGCXNR1OsFG+sVdLAitlpjAvD/I6dHDKnYrpEZUHkw=
 golang.org/x/tools v0.19.0/go.mod h1:qoJWxmGSIBmAeriMx19ogtrEPrGtDbPK634QFIcLAhc=
 golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
@@ -541,5 +518,3 @@ gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
 gotest.tools/v3 v3.0.2/go.mod h1:3SzNCllyD9/Y+b5r9JIKQ474KzkZyqLqEfYqMsX94Bk=
 gotest.tools/v3 v3.3.0 h1:MfDY1b1/0xN1CyMlQDac0ziEy9zJQd9CXBRRDHw2jJo=
 gotest.tools/v3 v3.3.0/go.mod h1:Mcr9QNxkg0uMvy/YElmo4SpXgJKWgQvYrT7Kw5RzJ1A=
-sigs.k8s.io/yaml v1.4.0 h1:Mk1wCc2gy/F0THH0TAp1QYyJNzRm2KCLy3o5ASXVI5E=
-sigs.k8s.io/yaml v1.4.0/go.mod h1:Ejl7/uTz7PSA4eKMyQCUTnhZYNmLIl+5c2lQPGR2BPY=
diff --git a/pkg/grpc/proto/backend.pb.go b/pkg/grpc/proto/backend.pb.go
index cc68757756f2..e2cd80e78856 100644
--- a/pkg/grpc/proto/backend.pb.go
+++ b/pkg/grpc/proto/backend.pb.go
@@ -1,7 +1,7 @@
 // Code generated by protoc-gen-go. DO NOT EDIT.
 // versions:
-// 	protoc-gen-go v1.31.0
-// 	protoc        v4.23.4
+// 	protoc-gen-go v1.26.0
+// 	protoc        v5.26.1
 // source: backend.proto
 
 package proto
@@ -9,6 +9,7 @@ package proto
 import (
 	protoreflect "google.golang.org/protobuf/reflect/protoreflect"
 	protoimpl "google.golang.org/protobuf/runtime/protoimpl"
+	anypb "google.golang.org/protobuf/types/known/anypb"
 	reflect "reflect"
 	sync "sync"
 )
@@ -532,47 +533,49 @@ type PredictOptions struct {
 	sizeCache     protoimpl.SizeCache
 	unknownFields protoimpl.UnknownFields
 
-	Prompt              string   `protobuf:"bytes,1,opt,name=Prompt,proto3" json:"Prompt,omitempty"`
-	Seed                int32    `protobuf:"varint,2,opt,name=Seed,proto3" json:"Seed,omitempty"`
-	Threads             int32    `protobuf:"varint,3,opt,name=Threads,proto3" json:"Threads,omitempty"`
-	Tokens              int32    `protobuf:"varint,4,opt,name=Tokens,proto3" json:"Tokens,omitempty"`
-	TopK                int32    `protobuf:"varint,5,opt,name=TopK,proto3" json:"TopK,omitempty"`
-	Repeat              int32    `protobuf:"varint,6,opt,name=Repeat,proto3" json:"Repeat,omitempty"`
-	Batch               int32    `protobuf:"varint,7,opt,name=Batch,proto3" json:"Batch,omitempty"`
-	NKeep               int32    `protobuf:"varint,8,opt,name=NKeep,proto3" json:"NKeep,omitempty"`
-	Temperature         float32  `protobuf:"fixed32,9,opt,name=Temperature,proto3" json:"Temperature,omitempty"`
-	Penalty             float32  `protobuf:"fixed32,10,opt,name=Penalty,proto3" json:"Penalty,omitempty"`
-	F16KV               bool     `protobuf:"varint,11,opt,name=F16KV,proto3" json:"F16KV,omitempty"`
-	DebugMode           bool     `protobuf:"varint,12,opt,name=DebugMode,proto3" json:"DebugMode,omitempty"`
-	StopPrompts         []string `protobuf:"bytes,13,rep,name=StopPrompts,proto3" json:"StopPrompts,omitempty"`
-	IgnoreEOS           bool     `protobuf:"varint,14,opt,name=IgnoreEOS,proto3" json:"IgnoreEOS,omitempty"`
-	TailFreeSamplingZ   float32  `protobuf:"fixed32,15,opt,name=TailFreeSamplingZ,proto3" json:"TailFreeSamplingZ,omitempty"`
-	TypicalP            float32  `protobuf:"fixed32,16,opt,name=TypicalP,proto3" json:"TypicalP,omitempty"`
-	FrequencyPenalty    float32  `protobuf:"fixed32,17,opt,name=FrequencyPenalty,proto3" json:"FrequencyPenalty,omitempty"`
-	PresencePenalty     float32  `protobuf:"fixed32,18,opt,name=PresencePenalty,proto3" json:"PresencePenalty,omitempty"`
-	Mirostat            int32    `protobuf:"varint,19,opt,name=Mirostat,proto3" json:"Mirostat,omitempty"`
-	MirostatETA         float32  `protobuf:"fixed32,20,opt,name=MirostatETA,proto3" json:"MirostatETA,omitempty"`
-	MirostatTAU         float32  `protobuf:"fixed32,21,opt,name=MirostatTAU,proto3" json:"MirostatTAU,omitempty"`
-	PenalizeNL          bool     `protobuf:"varint,22,opt,name=PenalizeNL,proto3" json:"PenalizeNL,omitempty"`
-	LogitBias           string   `protobuf:"bytes,23,opt,name=LogitBias,proto3" json:"LogitBias,omitempty"`
-	MLock               bool     `protobuf:"varint,25,opt,name=MLock,proto3" json:"MLock,omitempty"`
-	MMap                bool     `protobuf:"varint,26,opt,name=MMap,proto3" json:"MMap,omitempty"`
-	PromptCacheAll      bool     `protobuf:"varint,27,opt,name=PromptCacheAll,proto3" json:"PromptCacheAll,omitempty"`
-	PromptCacheRO       bool     `protobuf:"varint,28,opt,name=PromptCacheRO,proto3" json:"PromptCacheRO,omitempty"`
-	Grammar             string   `protobuf:"bytes,29,opt,name=Grammar,proto3" json:"Grammar,omitempty"`
-	MainGPU             string   `protobuf:"bytes,30,opt,name=MainGPU,proto3" json:"MainGPU,omitempty"`
-	TensorSplit         string   `protobuf:"bytes,31,opt,name=TensorSplit,proto3" json:"TensorSplit,omitempty"`
-	TopP                float32  `protobuf:"fixed32,32,opt,name=TopP,proto3" json:"TopP,omitempty"`
-	PromptCachePath     string   `protobuf:"bytes,33,opt,name=PromptCachePath,proto3" json:"PromptCachePath,omitempty"`
-	Debug               bool     `protobuf:"varint,34,opt,name=Debug,proto3" json:"Debug,omitempty"`
-	EmbeddingTokens     []int32  `protobuf:"varint,35,rep,packed,name=EmbeddingTokens,proto3" json:"EmbeddingTokens,omitempty"`
-	Embeddings          string   `protobuf:"bytes,36,opt,name=Embeddings,proto3" json:"Embeddings,omitempty"`
-	RopeFreqBase        float32  `protobuf:"fixed32,37,opt,name=RopeFreqBase,proto3" json:"RopeFreqBase,omitempty"`
-	RopeFreqScale       float32  `protobuf:"fixed32,38,opt,name=RopeFreqScale,proto3" json:"RopeFreqScale,omitempty"`
-	NegativePromptScale float32  `protobuf:"fixed32,39,opt,name=NegativePromptScale,proto3" json:"NegativePromptScale,omitempty"`
-	NegativePrompt      string   `protobuf:"bytes,40,opt,name=NegativePrompt,proto3" json:"NegativePrompt,omitempty"`
-	NDraft              int32    `protobuf:"varint,41,opt,name=NDraft,proto3" json:"NDraft,omitempty"`
-	Images              []string `protobuf:"bytes,42,rep,name=Images,proto3" json:"Images,omitempty"`
+	Prompt               string     `protobuf:"bytes,1,opt,name=Prompt,proto3" json:"Prompt,omitempty"`
+	Seed                 int32      `protobuf:"varint,2,opt,name=Seed,proto3" json:"Seed,omitempty"`
+	Threads              int32      `protobuf:"varint,3,opt,name=Threads,proto3" json:"Threads,omitempty"`
+	Tokens               int32      `protobuf:"varint,4,opt,name=Tokens,proto3" json:"Tokens,omitempty"`
+	TopK                 int32      `protobuf:"varint,5,opt,name=TopK,proto3" json:"TopK,omitempty"`
+	Repeat               int32      `protobuf:"varint,6,opt,name=Repeat,proto3" json:"Repeat,omitempty"`
+	Batch                int32      `protobuf:"varint,7,opt,name=Batch,proto3" json:"Batch,omitempty"`
+	NKeep                int32      `protobuf:"varint,8,opt,name=NKeep,proto3" json:"NKeep,omitempty"`
+	Temperature          float32    `protobuf:"fixed32,9,opt,name=Temperature,proto3" json:"Temperature,omitempty"`
+	Penalty              float32    `protobuf:"fixed32,10,opt,name=Penalty,proto3" json:"Penalty,omitempty"`
+	F16KV                bool       `protobuf:"varint,11,opt,name=F16KV,proto3" json:"F16KV,omitempty"`
+	DebugMode            bool       `protobuf:"varint,12,opt,name=DebugMode,proto3" json:"DebugMode,omitempty"`
+	StopPrompts          []string   `protobuf:"bytes,13,rep,name=StopPrompts,proto3" json:"StopPrompts,omitempty"`
+	IgnoreEOS            bool       `protobuf:"varint,14,opt,name=IgnoreEOS,proto3" json:"IgnoreEOS,omitempty"`
+	TailFreeSamplingZ    float32    `protobuf:"fixed32,15,opt,name=TailFreeSamplingZ,proto3" json:"TailFreeSamplingZ,omitempty"`
+	TypicalP             float32    `protobuf:"fixed32,16,opt,name=TypicalP,proto3" json:"TypicalP,omitempty"`
+	FrequencyPenalty     float32    `protobuf:"fixed32,17,opt,name=FrequencyPenalty,proto3" json:"FrequencyPenalty,omitempty"`
+	PresencePenalty      float32    `protobuf:"fixed32,18,opt,name=PresencePenalty,proto3" json:"PresencePenalty,omitempty"`
+	Mirostat             int32      `protobuf:"varint,19,opt,name=Mirostat,proto3" json:"Mirostat,omitempty"`
+	MirostatETA          float32    `protobuf:"fixed32,20,opt,name=MirostatETA,proto3" json:"MirostatETA,omitempty"`
+	MirostatTAU          float32    `protobuf:"fixed32,21,opt,name=MirostatTAU,proto3" json:"MirostatTAU,omitempty"`
+	PenalizeNL           bool       `protobuf:"varint,22,opt,name=PenalizeNL,proto3" json:"PenalizeNL,omitempty"`
+	LogitBias            string     `protobuf:"bytes,23,opt,name=LogitBias,proto3" json:"LogitBias,omitempty"`
+	MLock                bool       `protobuf:"varint,25,opt,name=MLock,proto3" json:"MLock,omitempty"`
+	MMap                 bool       `protobuf:"varint,26,opt,name=MMap,proto3" json:"MMap,omitempty"`
+	PromptCacheAll       bool       `protobuf:"varint,27,opt,name=PromptCacheAll,proto3" json:"PromptCacheAll,omitempty"`
+	PromptCacheRO        bool       `protobuf:"varint,28,opt,name=PromptCacheRO,proto3" json:"PromptCacheRO,omitempty"`
+	Grammar              string     `protobuf:"bytes,29,opt,name=Grammar,proto3" json:"Grammar,omitempty"`
+	MainGPU              string     `protobuf:"bytes,30,opt,name=MainGPU,proto3" json:"MainGPU,omitempty"`
+	TensorSplit          string     `protobuf:"bytes,31,opt,name=TensorSplit,proto3" json:"TensorSplit,omitempty"`
+	TopP                 float32    `protobuf:"fixed32,32,opt,name=TopP,proto3" json:"TopP,omitempty"`
+	PromptCachePath      string     `protobuf:"bytes,33,opt,name=PromptCachePath,proto3" json:"PromptCachePath,omitempty"`
+	Debug                bool       `protobuf:"varint,34,opt,name=Debug,proto3" json:"Debug,omitempty"`
+	EmbeddingTokens      []int32    `protobuf:"varint,35,rep,packed,name=EmbeddingTokens,proto3" json:"EmbeddingTokens,omitempty"`
+	Embeddings           string     `protobuf:"bytes,36,opt,name=Embeddings,proto3" json:"Embeddings,omitempty"`
+	RopeFreqBase         float32    `protobuf:"fixed32,37,opt,name=RopeFreqBase,proto3" json:"RopeFreqBase,omitempty"`
+	RopeFreqScale        float32    `protobuf:"fixed32,38,opt,name=RopeFreqScale,proto3" json:"RopeFreqScale,omitempty"`
+	NegativePromptScale  float32    `protobuf:"fixed32,39,opt,name=NegativePromptScale,proto3" json:"NegativePromptScale,omitempty"`
+	NegativePrompt       string     `protobuf:"bytes,40,opt,name=NegativePrompt,proto3" json:"NegativePrompt,omitempty"`
+	NDraft               int32      `protobuf:"varint,41,opt,name=NDraft,proto3" json:"NDraft,omitempty"`
+	Images               []string   `protobuf:"bytes,42,rep,name=Images,proto3" json:"Images,omitempty"`
+	UseTokenizerTemplate bool       `protobuf:"varint,43,opt,name=UseTokenizerTemplate,proto3" json:"UseTokenizerTemplate,omitempty"`
+	Messages             []*Message `protobuf:"bytes,44,rep,name=Messages,proto3" json:"Messages,omitempty"`
 }
 
 func (x *PredictOptions) Reset() {
@@ -894,6 +897,20 @@ func (x *PredictOptions) GetImages() []string {
 	return nil
 }
 
+func (x *PredictOptions) GetUseTokenizerTemplate() bool {
+	if x != nil {
+		return x.UseTokenizerTemplate
+	}
+	return false
+}
+
+func (x *PredictOptions) GetMessages() []*Message {
+	if x != nil {
+		return x.Messages
+	}
+	return nil
+}
+
 // The response message containing the result
 type Reply struct {
 	state         protoimpl.MessageState
@@ -2080,381 +2097,449 @@ func (x *StatusResponse) GetMemory() *MemoryUsageData {
 	return nil
 }
 
+type Message struct {
+	state         protoimpl.MessageState
+	sizeCache     protoimpl.SizeCache
+	unknownFields protoimpl.UnknownFields
+
+	Role    string     `protobuf:"bytes,1,opt,name=Role,proto3" json:"Role,omitempty"`
+	Content *anypb.Any `protobuf:"bytes,2,opt,name=Content,proto3" json:"Content,omitempty"`
+}
+
+func (x *Message) Reset() {
+	*x = Message{}
+	if protoimpl.UnsafeEnabled {
+		mi := &file_backend_proto_msgTypes[22]
+		ms := protoimpl.X.MessageStateOf(protoimpl.Pointer(x))
+		ms.StoreMessageInfo(mi)
+	}
+}
+
+func (x *Message) String() string {
+	return protoimpl.X.MessageStringOf(x)
+}
+
+func (*Message) ProtoMessage() {}
+
+func (x *Message) ProtoReflect() protoreflect.Message {
+	mi := &file_backend_proto_msgTypes[22]
+	if protoimpl.UnsafeEnabled && x != nil {
+		ms := protoimpl.X.MessageStateOf(protoimpl.Pointer(x))
+		if ms.LoadMessageInfo() == nil {
+			ms.StoreMessageInfo(mi)
+		}
+		return ms
+	}
+	return mi.MessageOf(x)
+}
+
+// Deprecated: Use Message.ProtoReflect.Descriptor instead.
+func (*Message) Descriptor() ([]byte, []int) {
+	return file_backend_proto_rawDescGZIP(), []int{22}
+}
+
+func (x *Message) GetRole() string {
+	if x != nil {
+		return x.Role
+	}
+	return ""
+}
+
+func (x *Message) GetContent() *anypb.Any {
+	if x != nil {
+		return x.Content
+	}
+	return nil
+}
+
 var File_backend_proto protoreflect.FileDescriptor
 
 var file_backend_proto_rawDesc = []byte{
 	0x0a, 0x0d, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x12,
-	0x07, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x22, 0x23, 0x0a, 0x09, 0x53, 0x74, 0x6f, 0x72,
-	0x65, 0x73, 0x4b, 0x65, 0x79, 0x12, 0x16, 0x0a, 0x06, 0x46, 0x6c, 0x6f, 0x61, 0x74, 0x73, 0x18,
-	0x01, 0x20, 0x03, 0x28, 0x02, 0x52, 0x06, 0x46, 0x6c, 0x6f, 0x61, 0x74, 0x73, 0x22, 0x23, 0x0a,
-	0x0b, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x56, 0x61, 0x6c, 0x75, 0x65, 0x12, 0x14, 0x0a, 0x05,
-	0x42, 0x79, 0x74, 0x65, 0x73, 0x18, 0x01, 0x20, 0x01, 0x28, 0x0c, 0x52, 0x05, 0x42, 0x79, 0x74,
-	0x65, 0x73, 0x22, 0x68, 0x0a, 0x10, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x53, 0x65, 0x74, 0x4f,
-	0x70, 0x74, 0x69, 0x6f, 0x6e, 0x73, 0x12, 0x26, 0x0a, 0x04, 0x4b, 0x65, 0x79, 0x73, 0x18, 0x01,
-	0x20, 0x03, 0x28, 0x0b, 0x32, 0x12, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x53,
-	0x74, 0x6f, 0x72, 0x65, 0x73, 0x4b, 0x65, 0x79, 0x52, 0x04, 0x4b, 0x65, 0x79, 0x73, 0x12, 0x2c,
-	0x0a, 0x06, 0x56, 0x61, 0x6c, 0x75, 0x65, 0x73, 0x18, 0x02, 0x20, 0x03, 0x28, 0x0b, 0x32, 0x14,
-	0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x56,
-	0x61, 0x6c, 0x75, 0x65, 0x52, 0x06, 0x56, 0x61, 0x6c, 0x75, 0x65, 0x73, 0x22, 0x3d, 0x0a, 0x13,
-	0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x44, 0x65, 0x6c, 0x65, 0x74, 0x65, 0x4f, 0x70, 0x74, 0x69,
-	0x6f, 0x6e, 0x73, 0x12, 0x26, 0x0a, 0x04, 0x4b, 0x65, 0x79, 0x73, 0x18, 0x01, 0x20, 0x03, 0x28,
-	0x0b, 0x32, 0x12, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x53, 0x74, 0x6f, 0x72,
-	0x65, 0x73, 0x4b, 0x65, 0x79, 0x52, 0x04, 0x4b, 0x65, 0x79, 0x73, 0x22, 0x3a, 0x0a, 0x10, 0x53,
-	0x74, 0x6f, 0x72, 0x65, 0x73, 0x47, 0x65, 0x74, 0x4f, 0x70, 0x74, 0x69, 0x6f, 0x6e, 0x73, 0x12,
-	0x26, 0x0a, 0x04, 0x4b, 0x65, 0x79, 0x73, 0x18, 0x01, 0x20, 0x03, 0x28, 0x0b, 0x32, 0x12, 0x2e,
-	0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x4b, 0x65,
-	0x79, 0x52, 0x04, 0x4b, 0x65, 0x79, 0x73, 0x22, 0x67, 0x0a, 0x0f, 0x53, 0x74, 0x6f, 0x72, 0x65,
-	0x73, 0x47, 0x65, 0x74, 0x52, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x12, 0x26, 0x0a, 0x04, 0x4b, 0x65,
+	0x07, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x1a, 0x19, 0x67, 0x6f, 0x6f, 0x67, 0x6c, 0x65,
+	0x2f, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x62, 0x75, 0x66, 0x2f, 0x61, 0x6e, 0x79, 0x2e, 0x70, 0x72,
+	0x6f, 0x74, 0x6f, 0x22, 0x23, 0x0a, 0x09, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x4b, 0x65, 0x79,
+	0x12, 0x16, 0x0a, 0x06, 0x46, 0x6c, 0x6f, 0x61, 0x74, 0x73, 0x18, 0x01, 0x20, 0x03, 0x28, 0x02,
+	0x52, 0x06, 0x46, 0x6c, 0x6f, 0x61, 0x74, 0x73, 0x22, 0x23, 0x0a, 0x0b, 0x53, 0x74, 0x6f, 0x72,
+	0x65, 0x73, 0x56, 0x61, 0x6c, 0x75, 0x65, 0x12, 0x14, 0x0a, 0x05, 0x42, 0x79, 0x74, 0x65, 0x73,
+	0x18, 0x01, 0x20, 0x01, 0x28, 0x0c, 0x52, 0x05, 0x42, 0x79, 0x74, 0x65, 0x73, 0x22, 0x68, 0x0a,
+	0x10, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x53, 0x65, 0x74, 0x4f, 0x70, 0x74, 0x69, 0x6f, 0x6e,
+	0x73, 0x12, 0x26, 0x0a, 0x04, 0x4b, 0x65, 0x79, 0x73, 0x18, 0x01, 0x20, 0x03, 0x28, 0x0b, 0x32,
+	0x12, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73,
+	0x4b, 0x65, 0x79, 0x52, 0x04, 0x4b, 0x65, 0x79, 0x73, 0x12, 0x2c, 0x0a, 0x06, 0x56, 0x61, 0x6c,
+	0x75, 0x65, 0x73, 0x18, 0x02, 0x20, 0x03, 0x28, 0x0b, 0x32, 0x14, 0x2e, 0x62, 0x61, 0x63, 0x6b,
+	0x65, 0x6e, 0x64, 0x2e, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x56, 0x61, 0x6c, 0x75, 0x65, 0x52,
+	0x06, 0x56, 0x61, 0x6c, 0x75, 0x65, 0x73, 0x22, 0x3d, 0x0a, 0x13, 0x53, 0x74, 0x6f, 0x72, 0x65,
+	0x73, 0x44, 0x65, 0x6c, 0x65, 0x74, 0x65, 0x4f, 0x70, 0x74, 0x69, 0x6f, 0x6e, 0x73, 0x12, 0x26,
+	0x0a, 0x04, 0x4b, 0x65, 0x79, 0x73, 0x18, 0x01, 0x20, 0x03, 0x28, 0x0b, 0x32, 0x12, 0x2e, 0x62,
+	0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x4b, 0x65, 0x79,
+	0x52, 0x04, 0x4b, 0x65, 0x79, 0x73, 0x22, 0x3a, 0x0a, 0x10, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73,
+	0x47, 0x65, 0x74, 0x4f, 0x70, 0x74, 0x69, 0x6f, 0x6e, 0x73, 0x12, 0x26, 0x0a, 0x04, 0x4b, 0x65,
 	0x79, 0x73, 0x18, 0x01, 0x20, 0x03, 0x28, 0x0b, 0x32, 0x12, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65,
 	0x6e, 0x64, 0x2e, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x4b, 0x65, 0x79, 0x52, 0x04, 0x4b, 0x65,
-	0x79, 0x73, 0x12, 0x2c, 0x0a, 0x06, 0x56, 0x61, 0x6c, 0x75, 0x65, 0x73, 0x18, 0x02, 0x20, 0x03,
-	0x28, 0x0b, 0x32, 0x14, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x53, 0x74, 0x6f,
-	0x72, 0x65, 0x73, 0x56, 0x61, 0x6c, 0x75, 0x65, 0x52, 0x06, 0x56, 0x61, 0x6c, 0x75, 0x65, 0x73,
-	0x22, 0x4d, 0x0a, 0x11, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x46, 0x69, 0x6e, 0x64, 0x4f, 0x70,
-	0x74, 0x69, 0x6f, 0x6e, 0x73, 0x12, 0x24, 0x0a, 0x03, 0x4b, 0x65, 0x79, 0x18, 0x01, 0x20, 0x01,
-	0x28, 0x0b, 0x32, 0x12, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x53, 0x74, 0x6f,
-	0x72, 0x65, 0x73, 0x4b, 0x65, 0x79, 0x52, 0x03, 0x4b, 0x65, 0x79, 0x12, 0x12, 0x0a, 0x04, 0x54,
-	0x6f, 0x70, 0x4b, 0x18, 0x02, 0x20, 0x01, 0x28, 0x05, 0x52, 0x04, 0x54, 0x6f, 0x70, 0x4b, 0x22,
-	0x8c, 0x01, 0x0a, 0x10, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x46, 0x69, 0x6e, 0x64, 0x52, 0x65,
-	0x73, 0x75, 0x6c, 0x74, 0x12, 0x26, 0x0a, 0x04, 0x4b, 0x65, 0x79, 0x73, 0x18, 0x01, 0x20, 0x03,
-	0x28, 0x0b, 0x32, 0x12, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x53, 0x74, 0x6f,
-	0x72, 0x65, 0x73, 0x4b, 0x65, 0x79, 0x52, 0x04, 0x4b, 0x65, 0x79, 0x73, 0x12, 0x2c, 0x0a, 0x06,
-	0x56, 0x61, 0x6c, 0x75, 0x65, 0x73, 0x18, 0x02, 0x20, 0x03, 0x28, 0x0b, 0x32, 0x14, 0x2e, 0x62,
-	0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x56, 0x61, 0x6c,
-	0x75, 0x65, 0x52, 0x06, 0x56, 0x61, 0x6c, 0x75, 0x65, 0x73, 0x12, 0x22, 0x0a, 0x0c, 0x53, 0x69,
-	0x6d, 0x69, 0x6c, 0x61, 0x72, 0x69, 0x74, 0x69, 0x65, 0x73, 0x18, 0x03, 0x20, 0x03, 0x28, 0x02,
-	0x52, 0x0c, 0x53, 0x69, 0x6d, 0x69, 0x6c, 0x61, 0x72, 0x69, 0x74, 0x69, 0x65, 0x73, 0x22, 0x0f,
-	0x0a, 0x0d, 0x48, 0x65, 0x61, 0x6c, 0x74, 0x68, 0x4d, 0x65, 0x73, 0x73, 0x61, 0x67, 0x65, 0x22,
-	0xf4, 0x09, 0x0a, 0x0e, 0x50, 0x72, 0x65, 0x64, 0x69, 0x63, 0x74, 0x4f, 0x70, 0x74, 0x69, 0x6f,
-	0x6e, 0x73, 0x12, 0x16, 0x0a, 0x06, 0x50, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x18, 0x01, 0x20, 0x01,
-	0x28, 0x09, 0x52, 0x06, 0x50, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x12, 0x12, 0x0a, 0x04, 0x53, 0x65,
-	0x65, 0x64, 0x18, 0x02, 0x20, 0x01, 0x28, 0x05, 0x52, 0x04, 0x53, 0x65, 0x65, 0x64, 0x12, 0x18,
-	0x0a, 0x07, 0x54, 0x68, 0x72, 0x65, 0x61, 0x64, 0x73, 0x18, 0x03, 0x20, 0x01, 0x28, 0x05, 0x52,
-	0x07, 0x54, 0x68, 0x72, 0x65, 0x61, 0x64, 0x73, 0x12, 0x16, 0x0a, 0x06, 0x54, 0x6f, 0x6b, 0x65,
-	0x6e, 0x73, 0x18, 0x04, 0x20, 0x01, 0x28, 0x05, 0x52, 0x06, 0x54, 0x6f, 0x6b, 0x65, 0x6e, 0x73,
-	0x12, 0x12, 0x0a, 0x04, 0x54, 0x6f, 0x70, 0x4b, 0x18, 0x05, 0x20, 0x01, 0x28, 0x05, 0x52, 0x04,
-	0x54, 0x6f, 0x70, 0x4b, 0x12, 0x16, 0x0a, 0x06, 0x52, 0x65, 0x70, 0x65, 0x61, 0x74, 0x18, 0x06,
-	0x20, 0x01, 0x28, 0x05, 0x52, 0x06, 0x52, 0x65, 0x70, 0x65, 0x61, 0x74, 0x12, 0x14, 0x0a, 0x05,
-	0x42, 0x61, 0x74, 0x63, 0x68, 0x18, 0x07, 0x20, 0x01, 0x28, 0x05, 0x52, 0x05, 0x42, 0x61, 0x74,
-	0x63, 0x68, 0x12, 0x14, 0x0a, 0x05, 0x4e, 0x4b, 0x65, 0x65, 0x70, 0x18, 0x08, 0x20, 0x01, 0x28,
-	0x05, 0x52, 0x05, 0x4e, 0x4b, 0x65, 0x65, 0x70, 0x12, 0x20, 0x0a, 0x0b, 0x54, 0x65, 0x6d, 0x70,
-	0x65, 0x72, 0x61, 0x74, 0x75, 0x72, 0x65, 0x18, 0x09, 0x20, 0x01, 0x28, 0x02, 0x52, 0x0b, 0x54,
-	0x65, 0x6d, 0x70, 0x65, 0x72, 0x61, 0x74, 0x75, 0x72, 0x65, 0x12, 0x18, 0x0a, 0x07, 0x50, 0x65,
-	0x6e, 0x61, 0x6c, 0x74, 0x79, 0x18, 0x0a, 0x20, 0x01, 0x28, 0x02, 0x52, 0x07, 0x50, 0x65, 0x6e,
-	0x61, 0x6c, 0x74, 0x79, 0x12, 0x14, 0x0a, 0x05, 0x46, 0x31, 0x36, 0x4b, 0x56, 0x18, 0x0b, 0x20,
-	0x01, 0x28, 0x08, 0x52, 0x05, 0x46, 0x31, 0x36, 0x4b, 0x56, 0x12, 0x1c, 0x0a, 0x09, 0x44, 0x65,
-	0x62, 0x75, 0x67, 0x4d, 0x6f, 0x64, 0x65, 0x18, 0x0c, 0x20, 0x01, 0x28, 0x08, 0x52, 0x09, 0x44,
-	0x65, 0x62, 0x75, 0x67, 0x4d, 0x6f, 0x64, 0x65, 0x12, 0x20, 0x0a, 0x0b, 0x53, 0x74, 0x6f, 0x70,
-	0x50, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x73, 0x18, 0x0d, 0x20, 0x03, 0x28, 0x09, 0x52, 0x0b, 0x53,
-	0x74, 0x6f, 0x70, 0x50, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x73, 0x12, 0x1c, 0x0a, 0x09, 0x49, 0x67,
-	0x6e, 0x6f, 0x72, 0x65, 0x45, 0x4f, 0x53, 0x18, 0x0e, 0x20, 0x01, 0x28, 0x08, 0x52, 0x09, 0x49,
-	0x67, 0x6e, 0x6f, 0x72, 0x65, 0x45, 0x4f, 0x53, 0x12, 0x2c, 0x0a, 0x11, 0x54, 0x61, 0x69, 0x6c,
-	0x46, 0x72, 0x65, 0x65, 0x53, 0x61, 0x6d, 0x70, 0x6c, 0x69, 0x6e, 0x67, 0x5a, 0x18, 0x0f, 0x20,
-	0x01, 0x28, 0x02, 0x52, 0x11, 0x54, 0x61, 0x69, 0x6c, 0x46, 0x72, 0x65, 0x65, 0x53, 0x61, 0x6d,
-	0x70, 0x6c, 0x69, 0x6e, 0x67, 0x5a, 0x12, 0x1a, 0x0a, 0x08, 0x54, 0x79, 0x70, 0x69, 0x63, 0x61,
-	0x6c, 0x50, 0x18, 0x10, 0x20, 0x01, 0x28, 0x02, 0x52, 0x08, 0x54, 0x79, 0x70, 0x69, 0x63, 0x61,
-	0x6c, 0x50, 0x12, 0x2a, 0x0a, 0x10, 0x46, 0x72, 0x65, 0x71, 0x75, 0x65, 0x6e, 0x63, 0x79, 0x50,
-	0x65, 0x6e, 0x61, 0x6c, 0x74, 0x79, 0x18, 0x11, 0x20, 0x01, 0x28, 0x02, 0x52, 0x10, 0x46, 0x72,
-	0x65, 0x71, 0x75, 0x65, 0x6e, 0x63, 0x79, 0x50, 0x65, 0x6e, 0x61, 0x6c, 0x74, 0x79, 0x12, 0x28,
-	0x0a, 0x0f, 0x50, 0x72, 0x65, 0x73, 0x65, 0x6e, 0x63, 0x65, 0x50, 0x65, 0x6e, 0x61, 0x6c, 0x74,
-	0x79, 0x18, 0x12, 0x20, 0x01, 0x28, 0x02, 0x52, 0x0f, 0x50, 0x72, 0x65, 0x73, 0x65, 0x6e, 0x63,
-	0x65, 0x50, 0x65, 0x6e, 0x61, 0x6c, 0x74, 0x79, 0x12, 0x1a, 0x0a, 0x08, 0x4d, 0x69, 0x72, 0x6f,
-	0x73, 0x74, 0x61, 0x74, 0x18, 0x13, 0x20, 0x01, 0x28, 0x05, 0x52, 0x08, 0x4d, 0x69, 0x72, 0x6f,
-	0x73, 0x74, 0x61, 0x74, 0x12, 0x20, 0x0a, 0x0b, 0x4d, 0x69, 0x72, 0x6f, 0x73, 0x74, 0x61, 0x74,
-	0x45, 0x54, 0x41, 0x18, 0x14, 0x20, 0x01, 0x28, 0x02, 0x52, 0x0b, 0x4d, 0x69, 0x72, 0x6f, 0x73,
-	0x74, 0x61, 0x74, 0x45, 0x54, 0x41, 0x12, 0x20, 0x0a, 0x0b, 0x4d, 0x69, 0x72, 0x6f, 0x73, 0x74,
-	0x61, 0x74, 0x54, 0x41, 0x55, 0x18, 0x15, 0x20, 0x01, 0x28, 0x02, 0x52, 0x0b, 0x4d, 0x69, 0x72,
-	0x6f, 0x73, 0x74, 0x61, 0x74, 0x54, 0x41, 0x55, 0x12, 0x1e, 0x0a, 0x0a, 0x50, 0x65, 0x6e, 0x61,
-	0x6c, 0x69, 0x7a, 0x65, 0x4e, 0x4c, 0x18, 0x16, 0x20, 0x01, 0x28, 0x08, 0x52, 0x0a, 0x50, 0x65,
-	0x6e, 0x61, 0x6c, 0x69, 0x7a, 0x65, 0x4e, 0x4c, 0x12, 0x1c, 0x0a, 0x09, 0x4c, 0x6f, 0x67, 0x69,
-	0x74, 0x42, 0x69, 0x61, 0x73, 0x18, 0x17, 0x20, 0x01, 0x28, 0x09, 0x52, 0x09, 0x4c, 0x6f, 0x67,
-	0x69, 0x74, 0x42, 0x69, 0x61, 0x73, 0x12, 0x14, 0x0a, 0x05, 0x4d, 0x4c, 0x6f, 0x63, 0x6b, 0x18,
-	0x19, 0x20, 0x01, 0x28, 0x08, 0x52, 0x05, 0x4d, 0x4c, 0x6f, 0x63, 0x6b, 0x12, 0x12, 0x0a, 0x04,
-	0x4d, 0x4d, 0x61, 0x70, 0x18, 0x1a, 0x20, 0x01, 0x28, 0x08, 0x52, 0x04, 0x4d, 0x4d, 0x61, 0x70,
-	0x12, 0x26, 0x0a, 0x0e, 0x50, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x43, 0x61, 0x63, 0x68, 0x65, 0x41,
-	0x6c, 0x6c, 0x18, 0x1b, 0x20, 0x01, 0x28, 0x08, 0x52, 0x0e, 0x50, 0x72, 0x6f, 0x6d, 0x70, 0x74,
-	0x43, 0x61, 0x63, 0x68, 0x65, 0x41, 0x6c, 0x6c, 0x12, 0x24, 0x0a, 0x0d, 0x50, 0x72, 0x6f, 0x6d,
-	0x70, 0x74, 0x43, 0x61, 0x63, 0x68, 0x65, 0x52, 0x4f, 0x18, 0x1c, 0x20, 0x01, 0x28, 0x08, 0x52,
-	0x0d, 0x50, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x43, 0x61, 0x63, 0x68, 0x65, 0x52, 0x4f, 0x12, 0x18,
-	0x0a, 0x07, 0x47, 0x72, 0x61, 0x6d, 0x6d, 0x61, 0x72, 0x18, 0x1d, 0x20, 0x01, 0x28, 0x09, 0x52,
-	0x07, 0x47, 0x72, 0x61, 0x6d, 0x6d, 0x61, 0x72, 0x12, 0x18, 0x0a, 0x07, 0x4d, 0x61, 0x69, 0x6e,
-	0x47, 0x50, 0x55, 0x18, 0x1e, 0x20, 0x01, 0x28, 0x09, 0x52, 0x07, 0x4d, 0x61, 0x69, 0x6e, 0x47,
-	0x50, 0x55, 0x12, 0x20, 0x0a, 0x0b, 0x54, 0x65, 0x6e, 0x73, 0x6f, 0x72, 0x53, 0x70, 0x6c, 0x69,
-	0x74, 0x18, 0x1f, 0x20, 0x01, 0x28, 0x09, 0x52, 0x0b, 0x54, 0x65, 0x6e, 0x73, 0x6f, 0x72, 0x53,
-	0x70, 0x6c, 0x69, 0x74, 0x12, 0x12, 0x0a, 0x04, 0x54, 0x6f, 0x70, 0x50, 0x18, 0x20, 0x20, 0x01,
-	0x28, 0x02, 0x52, 0x04, 0x54, 0x6f, 0x70, 0x50, 0x12, 0x28, 0x0a, 0x0f, 0x50, 0x72, 0x6f, 0x6d,
-	0x70, 0x74, 0x43, 0x61, 0x63, 0x68, 0x65, 0x50, 0x61, 0x74, 0x68, 0x18, 0x21, 0x20, 0x01, 0x28,
-	0x09, 0x52, 0x0f, 0x50, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x43, 0x61, 0x63, 0x68, 0x65, 0x50, 0x61,
-	0x74, 0x68, 0x12, 0x14, 0x0a, 0x05, 0x44, 0x65, 0x62, 0x75, 0x67, 0x18, 0x22, 0x20, 0x01, 0x28,
-	0x08, 0x52, 0x05, 0x44, 0x65, 0x62, 0x75, 0x67, 0x12, 0x28, 0x0a, 0x0f, 0x45, 0x6d, 0x62, 0x65,
-	0x64, 0x64, 0x69, 0x6e, 0x67, 0x54, 0x6f, 0x6b, 0x65, 0x6e, 0x73, 0x18, 0x23, 0x20, 0x03, 0x28,
-	0x05, 0x52, 0x0f, 0x45, 0x6d, 0x62, 0x65, 0x64, 0x64, 0x69, 0x6e, 0x67, 0x54, 0x6f, 0x6b, 0x65,
-	0x6e, 0x73, 0x12, 0x1e, 0x0a, 0x0a, 0x45, 0x6d, 0x62, 0x65, 0x64, 0x64, 0x69, 0x6e, 0x67, 0x73,
-	0x18, 0x24, 0x20, 0x01, 0x28, 0x09, 0x52, 0x0a, 0x45, 0x6d, 0x62, 0x65, 0x64, 0x64, 0x69, 0x6e,
-	0x67, 0x73, 0x12, 0x22, 0x0a, 0x0c, 0x52, 0x6f, 0x70, 0x65, 0x46, 0x72, 0x65, 0x71, 0x42, 0x61,
-	0x73, 0x65, 0x18, 0x25, 0x20, 0x01, 0x28, 0x02, 0x52, 0x0c, 0x52, 0x6f, 0x70, 0x65, 0x46, 0x72,
-	0x65, 0x71, 0x42, 0x61, 0x73, 0x65, 0x12, 0x24, 0x0a, 0x0d, 0x52, 0x6f, 0x70, 0x65, 0x46, 0x72,
-	0x65, 0x71, 0x53, 0x63, 0x61, 0x6c, 0x65, 0x18, 0x26, 0x20, 0x01, 0x28, 0x02, 0x52, 0x0d, 0x52,
-	0x6f, 0x70, 0x65, 0x46, 0x72, 0x65, 0x71, 0x53, 0x63, 0x61, 0x6c, 0x65, 0x12, 0x30, 0x0a, 0x13,
-	0x4e, 0x65, 0x67, 0x61, 0x74, 0x69, 0x76, 0x65, 0x50, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x53, 0x63,
-	0x61, 0x6c, 0x65, 0x18, 0x27, 0x20, 0x01, 0x28, 0x02, 0x52, 0x13, 0x4e, 0x65, 0x67, 0x61, 0x74,
-	0x69, 0x76, 0x65, 0x50, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x53, 0x63, 0x61, 0x6c, 0x65, 0x12, 0x26,
-	0x0a, 0x0e, 0x4e, 0x65, 0x67, 0x61, 0x74, 0x69, 0x76, 0x65, 0x50, 0x72, 0x6f, 0x6d, 0x70, 0x74,
-	0x18, 0x28, 0x20, 0x01, 0x28, 0x09, 0x52, 0x0e, 0x4e, 0x65, 0x67, 0x61, 0x74, 0x69, 0x76, 0x65,
-	0x50, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x12, 0x16, 0x0a, 0x06, 0x4e, 0x44, 0x72, 0x61, 0x66, 0x74,
-	0x18, 0x29, 0x20, 0x01, 0x28, 0x05, 0x52, 0x06, 0x4e, 0x44, 0x72, 0x61, 0x66, 0x74, 0x12, 0x16,
-	0x0a, 0x06, 0x49, 0x6d, 0x61, 0x67, 0x65, 0x73, 0x18, 0x2a, 0x20, 0x03, 0x28, 0x09, 0x52, 0x06,
-	0x49, 0x6d, 0x61, 0x67, 0x65, 0x73, 0x22, 0x21, 0x0a, 0x05, 0x52, 0x65, 0x70, 0x6c, 0x79, 0x12,
-	0x18, 0x0a, 0x07, 0x6d, 0x65, 0x73, 0x73, 0x61, 0x67, 0x65, 0x18, 0x01, 0x20, 0x01, 0x28, 0x0c,
-	0x52, 0x07, 0x6d, 0x65, 0x73, 0x73, 0x61, 0x67, 0x65, 0x22, 0xa2, 0x0d, 0x0a, 0x0c, 0x4d, 0x6f,
-	0x64, 0x65, 0x6c, 0x4f, 0x70, 0x74, 0x69, 0x6f, 0x6e, 0x73, 0x12, 0x14, 0x0a, 0x05, 0x4d, 0x6f,
-	0x64, 0x65, 0x6c, 0x18, 0x01, 0x20, 0x01, 0x28, 0x09, 0x52, 0x05, 0x4d, 0x6f, 0x64, 0x65, 0x6c,
-	0x12, 0x20, 0x0a, 0x0b, 0x43, 0x6f, 0x6e, 0x74, 0x65, 0x78, 0x74, 0x53, 0x69, 0x7a, 0x65, 0x18,
-	0x02, 0x20, 0x01, 0x28, 0x05, 0x52, 0x0b, 0x43, 0x6f, 0x6e, 0x74, 0x65, 0x78, 0x74, 0x53, 0x69,
-	0x7a, 0x65, 0x12, 0x12, 0x0a, 0x04, 0x53, 0x65, 0x65, 0x64, 0x18, 0x03, 0x20, 0x01, 0x28, 0x05,
-	0x52, 0x04, 0x53, 0x65, 0x65, 0x64, 0x12, 0x16, 0x0a, 0x06, 0x4e, 0x42, 0x61, 0x74, 0x63, 0x68,
-	0x18, 0x04, 0x20, 0x01, 0x28, 0x05, 0x52, 0x06, 0x4e, 0x42, 0x61, 0x74, 0x63, 0x68, 0x12, 0x1c,
-	0x0a, 0x09, 0x46, 0x31, 0x36, 0x4d, 0x65, 0x6d, 0x6f, 0x72, 0x79, 0x18, 0x05, 0x20, 0x01, 0x28,
-	0x08, 0x52, 0x09, 0x46, 0x31, 0x36, 0x4d, 0x65, 0x6d, 0x6f, 0x72, 0x79, 0x12, 0x14, 0x0a, 0x05,
-	0x4d, 0x4c, 0x6f, 0x63, 0x6b, 0x18, 0x06, 0x20, 0x01, 0x28, 0x08, 0x52, 0x05, 0x4d, 0x4c, 0x6f,
-	0x63, 0x6b, 0x12, 0x12, 0x0a, 0x04, 0x4d, 0x4d, 0x61, 0x70, 0x18, 0x07, 0x20, 0x01, 0x28, 0x08,
-	0x52, 0x04, 0x4d, 0x4d, 0x61, 0x70, 0x12, 0x1c, 0x0a, 0x09, 0x56, 0x6f, 0x63, 0x61, 0x62, 0x4f,
-	0x6e, 0x6c, 0x79, 0x18, 0x08, 0x20, 0x01, 0x28, 0x08, 0x52, 0x09, 0x56, 0x6f, 0x63, 0x61, 0x62,
-	0x4f, 0x6e, 0x6c, 0x79, 0x12, 0x18, 0x0a, 0x07, 0x4c, 0x6f, 0x77, 0x56, 0x52, 0x41, 0x4d, 0x18,
-	0x09, 0x20, 0x01, 0x28, 0x08, 0x52, 0x07, 0x4c, 0x6f, 0x77, 0x56, 0x52, 0x41, 0x4d, 0x12, 0x1e,
-	0x0a, 0x0a, 0x45, 0x6d, 0x62, 0x65, 0x64, 0x64, 0x69, 0x6e, 0x67, 0x73, 0x18, 0x0a, 0x20, 0x01,
-	0x28, 0x08, 0x52, 0x0a, 0x45, 0x6d, 0x62, 0x65, 0x64, 0x64, 0x69, 0x6e, 0x67, 0x73, 0x12, 0x12,
-	0x0a, 0x04, 0x4e, 0x55, 0x4d, 0x41, 0x18, 0x0b, 0x20, 0x01, 0x28, 0x08, 0x52, 0x04, 0x4e, 0x55,
-	0x4d, 0x41, 0x12, 0x1e, 0x0a, 0x0a, 0x4e, 0x47, 0x50, 0x55, 0x4c, 0x61, 0x79, 0x65, 0x72, 0x73,
-	0x18, 0x0c, 0x20, 0x01, 0x28, 0x05, 0x52, 0x0a, 0x4e, 0x47, 0x50, 0x55, 0x4c, 0x61, 0x79, 0x65,
-	0x72, 0x73, 0x12, 0x18, 0x0a, 0x07, 0x4d, 0x61, 0x69, 0x6e, 0x47, 0x50, 0x55, 0x18, 0x0d, 0x20,
-	0x01, 0x28, 0x09, 0x52, 0x07, 0x4d, 0x61, 0x69, 0x6e, 0x47, 0x50, 0x55, 0x12, 0x20, 0x0a, 0x0b,
-	0x54, 0x65, 0x6e, 0x73, 0x6f, 0x72, 0x53, 0x70, 0x6c, 0x69, 0x74, 0x18, 0x0e, 0x20, 0x01, 0x28,
-	0x09, 0x52, 0x0b, 0x54, 0x65, 0x6e, 0x73, 0x6f, 0x72, 0x53, 0x70, 0x6c, 0x69, 0x74, 0x12, 0x18,
-	0x0a, 0x07, 0x54, 0x68, 0x72, 0x65, 0x61, 0x64, 0x73, 0x18, 0x0f, 0x20, 0x01, 0x28, 0x05, 0x52,
-	0x07, 0x54, 0x68, 0x72, 0x65, 0x61, 0x64, 0x73, 0x12, 0x2c, 0x0a, 0x11, 0x4c, 0x69, 0x62, 0x72,
-	0x61, 0x72, 0x79, 0x53, 0x65, 0x61, 0x72, 0x63, 0x68, 0x50, 0x61, 0x74, 0x68, 0x18, 0x10, 0x20,
-	0x01, 0x28, 0x09, 0x52, 0x11, 0x4c, 0x69, 0x62, 0x72, 0x61, 0x72, 0x79, 0x53, 0x65, 0x61, 0x72,
-	0x63, 0x68, 0x50, 0x61, 0x74, 0x68, 0x12, 0x22, 0x0a, 0x0c, 0x52, 0x6f, 0x70, 0x65, 0x46, 0x72,
-	0x65, 0x71, 0x42, 0x61, 0x73, 0x65, 0x18, 0x11, 0x20, 0x01, 0x28, 0x02, 0x52, 0x0c, 0x52, 0x6f,
-	0x70, 0x65, 0x46, 0x72, 0x65, 0x71, 0x42, 0x61, 0x73, 0x65, 0x12, 0x24, 0x0a, 0x0d, 0x52, 0x6f,
-	0x70, 0x65, 0x46, 0x72, 0x65, 0x71, 0x53, 0x63, 0x61, 0x6c, 0x65, 0x18, 0x12, 0x20, 0x01, 0x28,
-	0x02, 0x52, 0x0d, 0x52, 0x6f, 0x70, 0x65, 0x46, 0x72, 0x65, 0x71, 0x53, 0x63, 0x61, 0x6c, 0x65,
-	0x12, 0x1e, 0x0a, 0x0a, 0x52, 0x4d, 0x53, 0x4e, 0x6f, 0x72, 0x6d, 0x45, 0x70, 0x73, 0x18, 0x13,
-	0x20, 0x01, 0x28, 0x02, 0x52, 0x0a, 0x52, 0x4d, 0x53, 0x4e, 0x6f, 0x72, 0x6d, 0x45, 0x70, 0x73,
-	0x12, 0x12, 0x0a, 0x04, 0x4e, 0x47, 0x51, 0x41, 0x18, 0x14, 0x20, 0x01, 0x28, 0x05, 0x52, 0x04,
-	0x4e, 0x47, 0x51, 0x41, 0x12, 0x1c, 0x0a, 0x09, 0x4d, 0x6f, 0x64, 0x65, 0x6c, 0x46, 0x69, 0x6c,
-	0x65, 0x18, 0x15, 0x20, 0x01, 0x28, 0x09, 0x52, 0x09, 0x4d, 0x6f, 0x64, 0x65, 0x6c, 0x46, 0x69,
-	0x6c, 0x65, 0x12, 0x16, 0x0a, 0x06, 0x44, 0x65, 0x76, 0x69, 0x63, 0x65, 0x18, 0x16, 0x20, 0x01,
-	0x28, 0x09, 0x52, 0x06, 0x44, 0x65, 0x76, 0x69, 0x63, 0x65, 0x12, 0x1c, 0x0a, 0x09, 0x55, 0x73,
-	0x65, 0x54, 0x72, 0x69, 0x74, 0x6f, 0x6e, 0x18, 0x17, 0x20, 0x01, 0x28, 0x08, 0x52, 0x09, 0x55,
-	0x73, 0x65, 0x54, 0x72, 0x69, 0x74, 0x6f, 0x6e, 0x12, 0x24, 0x0a, 0x0d, 0x4d, 0x6f, 0x64, 0x65,
-	0x6c, 0x42, 0x61, 0x73, 0x65, 0x4e, 0x61, 0x6d, 0x65, 0x18, 0x18, 0x20, 0x01, 0x28, 0x09, 0x52,
-	0x0d, 0x4d, 0x6f, 0x64, 0x65, 0x6c, 0x42, 0x61, 0x73, 0x65, 0x4e, 0x61, 0x6d, 0x65, 0x12, 0x2a,
-	0x0a, 0x10, 0x55, 0x73, 0x65, 0x46, 0x61, 0x73, 0x74, 0x54, 0x6f, 0x6b, 0x65, 0x6e, 0x69, 0x7a,
-	0x65, 0x72, 0x18, 0x19, 0x20, 0x01, 0x28, 0x08, 0x52, 0x10, 0x55, 0x73, 0x65, 0x46, 0x61, 0x73,
-	0x74, 0x54, 0x6f, 0x6b, 0x65, 0x6e, 0x69, 0x7a, 0x65, 0x72, 0x12, 0x22, 0x0a, 0x0c, 0x50, 0x69,
-	0x70, 0x65, 0x6c, 0x69, 0x6e, 0x65, 0x54, 0x79, 0x70, 0x65, 0x18, 0x1a, 0x20, 0x01, 0x28, 0x09,
-	0x52, 0x0c, 0x50, 0x69, 0x70, 0x65, 0x6c, 0x69, 0x6e, 0x65, 0x54, 0x79, 0x70, 0x65, 0x12, 0x24,
-	0x0a, 0x0d, 0x53, 0x63, 0x68, 0x65, 0x64, 0x75, 0x6c, 0x65, 0x72, 0x54, 0x79, 0x70, 0x65, 0x18,
-	0x1b, 0x20, 0x01, 0x28, 0x09, 0x52, 0x0d, 0x53, 0x63, 0x68, 0x65, 0x64, 0x75, 0x6c, 0x65, 0x72,
-	0x54, 0x79, 0x70, 0x65, 0x12, 0x12, 0x0a, 0x04, 0x43, 0x55, 0x44, 0x41, 0x18, 0x1c, 0x20, 0x01,
-	0x28, 0x08, 0x52, 0x04, 0x43, 0x55, 0x44, 0x41, 0x12, 0x1a, 0x0a, 0x08, 0x43, 0x46, 0x47, 0x53,
-	0x63, 0x61, 0x6c, 0x65, 0x18, 0x1d, 0x20, 0x01, 0x28, 0x02, 0x52, 0x08, 0x43, 0x46, 0x47, 0x53,
-	0x63, 0x61, 0x6c, 0x65, 0x12, 0x18, 0x0a, 0x07, 0x49, 0x4d, 0x47, 0x32, 0x49, 0x4d, 0x47, 0x18,
-	0x1e, 0x20, 0x01, 0x28, 0x08, 0x52, 0x07, 0x49, 0x4d, 0x47, 0x32, 0x49, 0x4d, 0x47, 0x12, 0x1c,
-	0x0a, 0x09, 0x43, 0x4c, 0x49, 0x50, 0x4d, 0x6f, 0x64, 0x65, 0x6c, 0x18, 0x1f, 0x20, 0x01, 0x28,
-	0x09, 0x52, 0x09, 0x43, 0x4c, 0x49, 0x50, 0x4d, 0x6f, 0x64, 0x65, 0x6c, 0x12, 0x24, 0x0a, 0x0d,
-	0x43, 0x4c, 0x49, 0x50, 0x53, 0x75, 0x62, 0x66, 0x6f, 0x6c, 0x64, 0x65, 0x72, 0x18, 0x20, 0x20,
-	0x01, 0x28, 0x09, 0x52, 0x0d, 0x43, 0x4c, 0x49, 0x50, 0x53, 0x75, 0x62, 0x66, 0x6f, 0x6c, 0x64,
-	0x65, 0x72, 0x12, 0x1a, 0x0a, 0x08, 0x43, 0x4c, 0x49, 0x50, 0x53, 0x6b, 0x69, 0x70, 0x18, 0x21,
-	0x20, 0x01, 0x28, 0x05, 0x52, 0x08, 0x43, 0x4c, 0x49, 0x50, 0x53, 0x6b, 0x69, 0x70, 0x12, 0x1e,
-	0x0a, 0x0a, 0x43, 0x6f, 0x6e, 0x74, 0x72, 0x6f, 0x6c, 0x4e, 0x65, 0x74, 0x18, 0x30, 0x20, 0x01,
-	0x28, 0x09, 0x52, 0x0a, 0x43, 0x6f, 0x6e, 0x74, 0x72, 0x6f, 0x6c, 0x4e, 0x65, 0x74, 0x12, 0x1c,
-	0x0a, 0x09, 0x54, 0x6f, 0x6b, 0x65, 0x6e, 0x69, 0x7a, 0x65, 0x72, 0x18, 0x22, 0x20, 0x01, 0x28,
-	0x09, 0x52, 0x09, 0x54, 0x6f, 0x6b, 0x65, 0x6e, 0x69, 0x7a, 0x65, 0x72, 0x12, 0x1a, 0x0a, 0x08,
-	0x4c, 0x6f, 0x72, 0x61, 0x42, 0x61, 0x73, 0x65, 0x18, 0x23, 0x20, 0x01, 0x28, 0x09, 0x52, 0x08,
-	0x4c, 0x6f, 0x72, 0x61, 0x42, 0x61, 0x73, 0x65, 0x12, 0x20, 0x0a, 0x0b, 0x4c, 0x6f, 0x72, 0x61,
-	0x41, 0x64, 0x61, 0x70, 0x74, 0x65, 0x72, 0x18, 0x24, 0x20, 0x01, 0x28, 0x09, 0x52, 0x0b, 0x4c,
-	0x6f, 0x72, 0x61, 0x41, 0x64, 0x61, 0x70, 0x74, 0x65, 0x72, 0x12, 0x1c, 0x0a, 0x09, 0x4c, 0x6f,
-	0x72, 0x61, 0x53, 0x63, 0x61, 0x6c, 0x65, 0x18, 0x2a, 0x20, 0x01, 0x28, 0x02, 0x52, 0x09, 0x4c,
-	0x6f, 0x72, 0x61, 0x53, 0x63, 0x61, 0x6c, 0x65, 0x12, 0x1c, 0x0a, 0x09, 0x4e, 0x6f, 0x4d, 0x75,
-	0x6c, 0x4d, 0x61, 0x74, 0x51, 0x18, 0x25, 0x20, 0x01, 0x28, 0x08, 0x52, 0x09, 0x4e, 0x6f, 0x4d,
-	0x75, 0x6c, 0x4d, 0x61, 0x74, 0x51, 0x12, 0x1e, 0x0a, 0x0a, 0x44, 0x72, 0x61, 0x66, 0x74, 0x4d,
-	0x6f, 0x64, 0x65, 0x6c, 0x18, 0x27, 0x20, 0x01, 0x28, 0x09, 0x52, 0x0a, 0x44, 0x72, 0x61, 0x66,
-	0x74, 0x4d, 0x6f, 0x64, 0x65, 0x6c, 0x12, 0x1c, 0x0a, 0x09, 0x41, 0x75, 0x64, 0x69, 0x6f, 0x50,
-	0x61, 0x74, 0x68, 0x18, 0x26, 0x20, 0x01, 0x28, 0x09, 0x52, 0x09, 0x41, 0x75, 0x64, 0x69, 0x6f,
-	0x50, 0x61, 0x74, 0x68, 0x12, 0x22, 0x0a, 0x0c, 0x51, 0x75, 0x61, 0x6e, 0x74, 0x69, 0x7a, 0x61,
-	0x74, 0x69, 0x6f, 0x6e, 0x18, 0x28, 0x20, 0x01, 0x28, 0x09, 0x52, 0x0c, 0x51, 0x75, 0x61, 0x6e,
-	0x74, 0x69, 0x7a, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x12, 0x32, 0x0a, 0x14, 0x47, 0x50, 0x55, 0x4d,
-	0x65, 0x6d, 0x6f, 0x72, 0x79, 0x55, 0x74, 0x69, 0x6c, 0x69, 0x7a, 0x61, 0x74, 0x69, 0x6f, 0x6e,
-	0x18, 0x32, 0x20, 0x01, 0x28, 0x02, 0x52, 0x14, 0x47, 0x50, 0x55, 0x4d, 0x65, 0x6d, 0x6f, 0x72,
-	0x79, 0x55, 0x74, 0x69, 0x6c, 0x69, 0x7a, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x12, 0x28, 0x0a, 0x0f,
-	0x54, 0x72, 0x75, 0x73, 0x74, 0x52, 0x65, 0x6d, 0x6f, 0x74, 0x65, 0x43, 0x6f, 0x64, 0x65, 0x18,
-	0x33, 0x20, 0x01, 0x28, 0x08, 0x52, 0x0f, 0x54, 0x72, 0x75, 0x73, 0x74, 0x52, 0x65, 0x6d, 0x6f,
-	0x74, 0x65, 0x43, 0x6f, 0x64, 0x65, 0x12, 0x22, 0x0a, 0x0c, 0x45, 0x6e, 0x66, 0x6f, 0x72, 0x63,
-	0x65, 0x45, 0x61, 0x67, 0x65, 0x72, 0x18, 0x34, 0x20, 0x01, 0x28, 0x08, 0x52, 0x0c, 0x45, 0x6e,
-	0x66, 0x6f, 0x72, 0x63, 0x65, 0x45, 0x61, 0x67, 0x65, 0x72, 0x12, 0x1c, 0x0a, 0x09, 0x53, 0x77,
-	0x61, 0x70, 0x53, 0x70, 0x61, 0x63, 0x65, 0x18, 0x35, 0x20, 0x01, 0x28, 0x05, 0x52, 0x09, 0x53,
-	0x77, 0x61, 0x70, 0x53, 0x70, 0x61, 0x63, 0x65, 0x12, 0x20, 0x0a, 0x0b, 0x4d, 0x61, 0x78, 0x4d,
-	0x6f, 0x64, 0x65, 0x6c, 0x4c, 0x65, 0x6e, 0x18, 0x36, 0x20, 0x01, 0x28, 0x05, 0x52, 0x0b, 0x4d,
-	0x61, 0x78, 0x4d, 0x6f, 0x64, 0x65, 0x6c, 0x4c, 0x65, 0x6e, 0x12, 0x16, 0x0a, 0x06, 0x4d, 0x4d,
-	0x50, 0x72, 0x6f, 0x6a, 0x18, 0x29, 0x20, 0x01, 0x28, 0x09, 0x52, 0x06, 0x4d, 0x4d, 0x50, 0x72,
-	0x6f, 0x6a, 0x12, 0x20, 0x0a, 0x0b, 0x52, 0x6f, 0x70, 0x65, 0x53, 0x63, 0x61, 0x6c, 0x69, 0x6e,
-	0x67, 0x18, 0x2b, 0x20, 0x01, 0x28, 0x09, 0x52, 0x0b, 0x52, 0x6f, 0x70, 0x65, 0x53, 0x63, 0x61,
-	0x6c, 0x69, 0x6e, 0x67, 0x12, 0x24, 0x0a, 0x0d, 0x59, 0x61, 0x72, 0x6e, 0x45, 0x78, 0x74, 0x46,
-	0x61, 0x63, 0x74, 0x6f, 0x72, 0x18, 0x2c, 0x20, 0x01, 0x28, 0x02, 0x52, 0x0d, 0x59, 0x61, 0x72,
-	0x6e, 0x45, 0x78, 0x74, 0x46, 0x61, 0x63, 0x74, 0x6f, 0x72, 0x12, 0x26, 0x0a, 0x0e, 0x59, 0x61,
-	0x72, 0x6e, 0x41, 0x74, 0x74, 0x6e, 0x46, 0x61, 0x63, 0x74, 0x6f, 0x72, 0x18, 0x2d, 0x20, 0x01,
-	0x28, 0x02, 0x52, 0x0e, 0x59, 0x61, 0x72, 0x6e, 0x41, 0x74, 0x74, 0x6e, 0x46, 0x61, 0x63, 0x74,
-	0x6f, 0x72, 0x12, 0x22, 0x0a, 0x0c, 0x59, 0x61, 0x72, 0x6e, 0x42, 0x65, 0x74, 0x61, 0x46, 0x61,
-	0x73, 0x74, 0x18, 0x2e, 0x20, 0x01, 0x28, 0x02, 0x52, 0x0c, 0x59, 0x61, 0x72, 0x6e, 0x42, 0x65,
-	0x74, 0x61, 0x46, 0x61, 0x73, 0x74, 0x12, 0x22, 0x0a, 0x0c, 0x59, 0x61, 0x72, 0x6e, 0x42, 0x65,
-	0x74, 0x61, 0x53, 0x6c, 0x6f, 0x77, 0x18, 0x2f, 0x20, 0x01, 0x28, 0x02, 0x52, 0x0c, 0x59, 0x61,
-	0x72, 0x6e, 0x42, 0x65, 0x74, 0x61, 0x53, 0x6c, 0x6f, 0x77, 0x12, 0x12, 0x0a, 0x04, 0x54, 0x79,
-	0x70, 0x65, 0x18, 0x31, 0x20, 0x01, 0x28, 0x09, 0x52, 0x04, 0x54, 0x79, 0x70, 0x65, 0x22, 0x3c,
-	0x0a, 0x06, 0x52, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x12, 0x18, 0x0a, 0x07, 0x6d, 0x65, 0x73, 0x73,
-	0x61, 0x67, 0x65, 0x18, 0x01, 0x20, 0x01, 0x28, 0x09, 0x52, 0x07, 0x6d, 0x65, 0x73, 0x73, 0x61,
-	0x67, 0x65, 0x12, 0x18, 0x0a, 0x07, 0x73, 0x75, 0x63, 0x63, 0x65, 0x73, 0x73, 0x18, 0x02, 0x20,
-	0x01, 0x28, 0x08, 0x52, 0x07, 0x73, 0x75, 0x63, 0x63, 0x65, 0x73, 0x73, 0x22, 0x31, 0x0a, 0x0f,
-	0x45, 0x6d, 0x62, 0x65, 0x64, 0x64, 0x69, 0x6e, 0x67, 0x52, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x12,
-	0x1e, 0x0a, 0x0a, 0x65, 0x6d, 0x62, 0x65, 0x64, 0x64, 0x69, 0x6e, 0x67, 0x73, 0x18, 0x01, 0x20,
-	0x03, 0x28, 0x02, 0x52, 0x0a, 0x65, 0x6d, 0x62, 0x65, 0x64, 0x64, 0x69, 0x6e, 0x67, 0x73, 0x22,
-	0x5b, 0x0a, 0x11, 0x54, 0x72, 0x61, 0x6e, 0x73, 0x63, 0x72, 0x69, 0x70, 0x74, 0x52, 0x65, 0x71,
-	0x75, 0x65, 0x73, 0x74, 0x12, 0x10, 0x0a, 0x03, 0x64, 0x73, 0x74, 0x18, 0x02, 0x20, 0x01, 0x28,
-	0x09, 0x52, 0x03, 0x64, 0x73, 0x74, 0x12, 0x1a, 0x0a, 0x08, 0x6c, 0x61, 0x6e, 0x67, 0x75, 0x61,
-	0x67, 0x65, 0x18, 0x03, 0x20, 0x01, 0x28, 0x09, 0x52, 0x08, 0x6c, 0x61, 0x6e, 0x67, 0x75, 0x61,
-	0x67, 0x65, 0x12, 0x18, 0x0a, 0x07, 0x74, 0x68, 0x72, 0x65, 0x61, 0x64, 0x73, 0x18, 0x04, 0x20,
-	0x01, 0x28, 0x0d, 0x52, 0x07, 0x74, 0x68, 0x72, 0x65, 0x61, 0x64, 0x73, 0x22, 0x5e, 0x0a, 0x10,
-	0x54, 0x72, 0x61, 0x6e, 0x73, 0x63, 0x72, 0x69, 0x70, 0x74, 0x52, 0x65, 0x73, 0x75, 0x6c, 0x74,
-	0x12, 0x36, 0x0a, 0x08, 0x73, 0x65, 0x67, 0x6d, 0x65, 0x6e, 0x74, 0x73, 0x18, 0x01, 0x20, 0x03,
-	0x28, 0x0b, 0x32, 0x1a, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x54, 0x72, 0x61,
-	0x6e, 0x73, 0x63, 0x72, 0x69, 0x70, 0x74, 0x53, 0x65, 0x67, 0x6d, 0x65, 0x6e, 0x74, 0x52, 0x08,
-	0x73, 0x65, 0x67, 0x6d, 0x65, 0x6e, 0x74, 0x73, 0x12, 0x12, 0x0a, 0x04, 0x74, 0x65, 0x78, 0x74,
-	0x18, 0x02, 0x20, 0x01, 0x28, 0x09, 0x52, 0x04, 0x74, 0x65, 0x78, 0x74, 0x22, 0x77, 0x0a, 0x11,
-	0x54, 0x72, 0x61, 0x6e, 0x73, 0x63, 0x72, 0x69, 0x70, 0x74, 0x53, 0x65, 0x67, 0x6d, 0x65, 0x6e,
-	0x74, 0x12, 0x0e, 0x0a, 0x02, 0x69, 0x64, 0x18, 0x01, 0x20, 0x01, 0x28, 0x05, 0x52, 0x02, 0x69,
-	0x64, 0x12, 0x14, 0x0a, 0x05, 0x73, 0x74, 0x61, 0x72, 0x74, 0x18, 0x02, 0x20, 0x01, 0x28, 0x03,
-	0x52, 0x05, 0x73, 0x74, 0x61, 0x72, 0x74, 0x12, 0x10, 0x0a, 0x03, 0x65, 0x6e, 0x64, 0x18, 0x03,
-	0x20, 0x01, 0x28, 0x03, 0x52, 0x03, 0x65, 0x6e, 0x64, 0x12, 0x12, 0x0a, 0x04, 0x74, 0x65, 0x78,
-	0x74, 0x18, 0x04, 0x20, 0x01, 0x28, 0x09, 0x52, 0x04, 0x74, 0x65, 0x78, 0x74, 0x12, 0x16, 0x0a,
-	0x06, 0x74, 0x6f, 0x6b, 0x65, 0x6e, 0x73, 0x18, 0x05, 0x20, 0x03, 0x28, 0x05, 0x52, 0x06, 0x74,
-	0x6f, 0x6b, 0x65, 0x6e, 0x73, 0x22, 0xbe, 0x02, 0x0a, 0x14, 0x47, 0x65, 0x6e, 0x65, 0x72, 0x61,
-	0x74, 0x65, 0x49, 0x6d, 0x61, 0x67, 0x65, 0x52, 0x65, 0x71, 0x75, 0x65, 0x73, 0x74, 0x12, 0x16,
-	0x0a, 0x06, 0x68, 0x65, 0x69, 0x67, 0x68, 0x74, 0x18, 0x01, 0x20, 0x01, 0x28, 0x05, 0x52, 0x06,
-	0x68, 0x65, 0x69, 0x67, 0x68, 0x74, 0x12, 0x14, 0x0a, 0x05, 0x77, 0x69, 0x64, 0x74, 0x68, 0x18,
-	0x02, 0x20, 0x01, 0x28, 0x05, 0x52, 0x05, 0x77, 0x69, 0x64, 0x74, 0x68, 0x12, 0x12, 0x0a, 0x04,
-	0x6d, 0x6f, 0x64, 0x65, 0x18, 0x03, 0x20, 0x01, 0x28, 0x05, 0x52, 0x04, 0x6d, 0x6f, 0x64, 0x65,
-	0x12, 0x12, 0x0a, 0x04, 0x73, 0x74, 0x65, 0x70, 0x18, 0x04, 0x20, 0x01, 0x28, 0x05, 0x52, 0x04,
-	0x73, 0x74, 0x65, 0x70, 0x12, 0x12, 0x0a, 0x04, 0x73, 0x65, 0x65, 0x64, 0x18, 0x05, 0x20, 0x01,
-	0x28, 0x05, 0x52, 0x04, 0x73, 0x65, 0x65, 0x64, 0x12, 0x27, 0x0a, 0x0f, 0x70, 0x6f, 0x73, 0x69,
-	0x74, 0x69, 0x76, 0x65, 0x5f, 0x70, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x18, 0x06, 0x20, 0x01, 0x28,
-	0x09, 0x52, 0x0e, 0x70, 0x6f, 0x73, 0x69, 0x74, 0x69, 0x76, 0x65, 0x50, 0x72, 0x6f, 0x6d, 0x70,
-	0x74, 0x12, 0x27, 0x0a, 0x0f, 0x6e, 0x65, 0x67, 0x61, 0x74, 0x69, 0x76, 0x65, 0x5f, 0x70, 0x72,
-	0x6f, 0x6d, 0x70, 0x74, 0x18, 0x07, 0x20, 0x01, 0x28, 0x09, 0x52, 0x0e, 0x6e, 0x65, 0x67, 0x61,
-	0x74, 0x69, 0x76, 0x65, 0x50, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x12, 0x10, 0x0a, 0x03, 0x64, 0x73,
-	0x74, 0x18, 0x08, 0x20, 0x01, 0x28, 0x09, 0x52, 0x03, 0x64, 0x73, 0x74, 0x12, 0x10, 0x0a, 0x03,
-	0x73, 0x72, 0x63, 0x18, 0x09, 0x20, 0x01, 0x28, 0x09, 0x52, 0x03, 0x73, 0x72, 0x63, 0x12, 0x2a,
-	0x0a, 0x10, 0x45, 0x6e, 0x61, 0x62, 0x6c, 0x65, 0x50, 0x61, 0x72, 0x61, 0x6d, 0x65, 0x74, 0x65,
-	0x72, 0x73, 0x18, 0x0a, 0x20, 0x01, 0x28, 0x09, 0x52, 0x10, 0x45, 0x6e, 0x61, 0x62, 0x6c, 0x65,
-	0x50, 0x61, 0x72, 0x61, 0x6d, 0x65, 0x74, 0x65, 0x72, 0x73, 0x12, 0x1a, 0x0a, 0x08, 0x43, 0x4c,
-	0x49, 0x50, 0x53, 0x6b, 0x69, 0x70, 0x18, 0x0b, 0x20, 0x01, 0x28, 0x05, 0x52, 0x08, 0x43, 0x4c,
-	0x49, 0x50, 0x53, 0x6b, 0x69, 0x70, 0x22, 0x5e, 0x0a, 0x0a, 0x54, 0x54, 0x53, 0x52, 0x65, 0x71,
-	0x75, 0x65, 0x73, 0x74, 0x12, 0x12, 0x0a, 0x04, 0x74, 0x65, 0x78, 0x74, 0x18, 0x01, 0x20, 0x01,
-	0x28, 0x09, 0x52, 0x04, 0x74, 0x65, 0x78, 0x74, 0x12, 0x14, 0x0a, 0x05, 0x6d, 0x6f, 0x64, 0x65,
-	0x6c, 0x18, 0x02, 0x20, 0x01, 0x28, 0x09, 0x52, 0x05, 0x6d, 0x6f, 0x64, 0x65, 0x6c, 0x12, 0x10,
-	0x0a, 0x03, 0x64, 0x73, 0x74, 0x18, 0x03, 0x20, 0x01, 0x28, 0x09, 0x52, 0x03, 0x64, 0x73, 0x74,
-	0x12, 0x14, 0x0a, 0x05, 0x76, 0x6f, 0x69, 0x63, 0x65, 0x18, 0x04, 0x20, 0x01, 0x28, 0x09, 0x52,
-	0x05, 0x76, 0x6f, 0x69, 0x63, 0x65, 0x22, 0x46, 0x0a, 0x14, 0x54, 0x6f, 0x6b, 0x65, 0x6e, 0x69,
-	0x7a, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x52, 0x65, 0x73, 0x70, 0x6f, 0x6e, 0x73, 0x65, 0x12, 0x16,
-	0x0a, 0x06, 0x6c, 0x65, 0x6e, 0x67, 0x74, 0x68, 0x18, 0x01, 0x20, 0x01, 0x28, 0x05, 0x52, 0x06,
-	0x6c, 0x65, 0x6e, 0x67, 0x74, 0x68, 0x12, 0x16, 0x0a, 0x06, 0x74, 0x6f, 0x6b, 0x65, 0x6e, 0x73,
-	0x18, 0x02, 0x20, 0x03, 0x28, 0x05, 0x52, 0x06, 0x74, 0x6f, 0x6b, 0x65, 0x6e, 0x73, 0x22, 0xac,
-	0x01, 0x0a, 0x0f, 0x4d, 0x65, 0x6d, 0x6f, 0x72, 0x79, 0x55, 0x73, 0x61, 0x67, 0x65, 0x44, 0x61,
-	0x74, 0x61, 0x12, 0x14, 0x0a, 0x05, 0x74, 0x6f, 0x74, 0x61, 0x6c, 0x18, 0x01, 0x20, 0x01, 0x28,
-	0x04, 0x52, 0x05, 0x74, 0x6f, 0x74, 0x61, 0x6c, 0x12, 0x45, 0x0a, 0x09, 0x62, 0x72, 0x65, 0x61,
-	0x6b, 0x64, 0x6f, 0x77, 0x6e, 0x18, 0x02, 0x20, 0x03, 0x28, 0x0b, 0x32, 0x27, 0x2e, 0x62, 0x61,
-	0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x4d, 0x65, 0x6d, 0x6f, 0x72, 0x79, 0x55, 0x73, 0x61, 0x67,
-	0x65, 0x44, 0x61, 0x74, 0x61, 0x2e, 0x42, 0x72, 0x65, 0x61, 0x6b, 0x64, 0x6f, 0x77, 0x6e, 0x45,
-	0x6e, 0x74, 0x72, 0x79, 0x52, 0x09, 0x62, 0x72, 0x65, 0x61, 0x6b, 0x64, 0x6f, 0x77, 0x6e, 0x1a,
-	0x3c, 0x0a, 0x0e, 0x42, 0x72, 0x65, 0x61, 0x6b, 0x64, 0x6f, 0x77, 0x6e, 0x45, 0x6e, 0x74, 0x72,
-	0x79, 0x12, 0x10, 0x0a, 0x03, 0x6b, 0x65, 0x79, 0x18, 0x01, 0x20, 0x01, 0x28, 0x09, 0x52, 0x03,
-	0x6b, 0x65, 0x79, 0x12, 0x14, 0x0a, 0x05, 0x76, 0x61, 0x6c, 0x75, 0x65, 0x18, 0x02, 0x20, 0x01,
-	0x28, 0x04, 0x52, 0x05, 0x76, 0x61, 0x6c, 0x75, 0x65, 0x3a, 0x02, 0x38, 0x01, 0x22, 0xbc, 0x01,
-	0x0a, 0x0e, 0x53, 0x74, 0x61, 0x74, 0x75, 0x73, 0x52, 0x65, 0x73, 0x70, 0x6f, 0x6e, 0x73, 0x65,
-	0x12, 0x33, 0x0a, 0x05, 0x73, 0x74, 0x61, 0x74, 0x65, 0x18, 0x01, 0x20, 0x01, 0x28, 0x0e, 0x32,
-	0x1d, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x53, 0x74, 0x61, 0x74, 0x75, 0x73,
-	0x52, 0x65, 0x73, 0x70, 0x6f, 0x6e, 0x73, 0x65, 0x2e, 0x53, 0x74, 0x61, 0x74, 0x65, 0x52, 0x05,
-	0x73, 0x74, 0x61, 0x74, 0x65, 0x12, 0x30, 0x0a, 0x06, 0x6d, 0x65, 0x6d, 0x6f, 0x72, 0x79, 0x18,
-	0x02, 0x20, 0x01, 0x28, 0x0b, 0x32, 0x18, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e,
-	0x4d, 0x65, 0x6d, 0x6f, 0x72, 0x79, 0x55, 0x73, 0x61, 0x67, 0x65, 0x44, 0x61, 0x74, 0x61, 0x52,
-	0x06, 0x6d, 0x65, 0x6d, 0x6f, 0x72, 0x79, 0x22, 0x43, 0x0a, 0x05, 0x53, 0x74, 0x61, 0x74, 0x65,
-	0x12, 0x11, 0x0a, 0x0d, 0x55, 0x4e, 0x49, 0x4e, 0x49, 0x54, 0x49, 0x41, 0x4c, 0x49, 0x5a, 0x45,
-	0x44, 0x10, 0x00, 0x12, 0x08, 0x0a, 0x04, 0x42, 0x55, 0x53, 0x59, 0x10, 0x01, 0x12, 0x09, 0x0a,
-	0x05, 0x52, 0x45, 0x41, 0x44, 0x59, 0x10, 0x02, 0x12, 0x12, 0x0a, 0x05, 0x45, 0x52, 0x52, 0x4f,
-	0x52, 0x10, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x01, 0x32, 0xfb, 0x06, 0x0a,
-	0x07, 0x42, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x12, 0x32, 0x0a, 0x06, 0x48, 0x65, 0x61, 0x6c,
-	0x74, 0x68, 0x12, 0x16, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x48, 0x65, 0x61,
-	0x6c, 0x74, 0x68, 0x4d, 0x65, 0x73, 0x73, 0x61, 0x67, 0x65, 0x1a, 0x0e, 0x2e, 0x62, 0x61, 0x63,
-	0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x52, 0x65, 0x70, 0x6c, 0x79, 0x22, 0x00, 0x12, 0x34, 0x0a, 0x07,
-	0x50, 0x72, 0x65, 0x64, 0x69, 0x63, 0x74, 0x12, 0x17, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e,
-	0x64, 0x2e, 0x50, 0x72, 0x65, 0x64, 0x69, 0x63, 0x74, 0x4f, 0x70, 0x74, 0x69, 0x6f, 0x6e, 0x73,
-	0x1a, 0x0e, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x52, 0x65, 0x70, 0x6c, 0x79,
-	0x22, 0x00, 0x12, 0x35, 0x0a, 0x09, 0x4c, 0x6f, 0x61, 0x64, 0x4d, 0x6f, 0x64, 0x65, 0x6c, 0x12,
-	0x15, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x4d, 0x6f, 0x64, 0x65, 0x6c, 0x4f,
-	0x70, 0x74, 0x69, 0x6f, 0x6e, 0x73, 0x1a, 0x0f, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64,
-	0x2e, 0x52, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x22, 0x00, 0x12, 0x3c, 0x0a, 0x0d, 0x50, 0x72, 0x65,
-	0x64, 0x69, 0x63, 0x74, 0x53, 0x74, 0x72, 0x65, 0x61, 0x6d, 0x12, 0x17, 0x2e, 0x62, 0x61, 0x63,
-	0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x50, 0x72, 0x65, 0x64, 0x69, 0x63, 0x74, 0x4f, 0x70, 0x74, 0x69,
-	0x6f, 0x6e, 0x73, 0x1a, 0x0e, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x52, 0x65,
-	0x70, 0x6c, 0x79, 0x22, 0x00, 0x30, 0x01, 0x12, 0x40, 0x0a, 0x09, 0x45, 0x6d, 0x62, 0x65, 0x64,
-	0x64, 0x69, 0x6e, 0x67, 0x12, 0x17, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x50,
-	0x72, 0x65, 0x64, 0x69, 0x63, 0x74, 0x4f, 0x70, 0x74, 0x69, 0x6f, 0x6e, 0x73, 0x1a, 0x18, 0x2e,
-	0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x45, 0x6d, 0x62, 0x65, 0x64, 0x64, 0x69, 0x6e,
-	0x67, 0x52, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x22, 0x00, 0x12, 0x41, 0x0a, 0x0d, 0x47, 0x65, 0x6e,
-	0x65, 0x72, 0x61, 0x74, 0x65, 0x49, 0x6d, 0x61, 0x67, 0x65, 0x12, 0x1d, 0x2e, 0x62, 0x61, 0x63,
-	0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x47, 0x65, 0x6e, 0x65, 0x72, 0x61, 0x74, 0x65, 0x49, 0x6d, 0x61,
-	0x67, 0x65, 0x52, 0x65, 0x71, 0x75, 0x65, 0x73, 0x74, 0x1a, 0x0f, 0x2e, 0x62, 0x61, 0x63, 0x6b,
-	0x65, 0x6e, 0x64, 0x2e, 0x52, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x22, 0x00, 0x12, 0x4d, 0x0a, 0x12,
-	0x41, 0x75, 0x64, 0x69, 0x6f, 0x54, 0x72, 0x61, 0x6e, 0x73, 0x63, 0x72, 0x69, 0x70, 0x74, 0x69,
-	0x6f, 0x6e, 0x12, 0x1a, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x54, 0x72, 0x61,
-	0x6e, 0x73, 0x63, 0x72, 0x69, 0x70, 0x74, 0x52, 0x65, 0x71, 0x75, 0x65, 0x73, 0x74, 0x1a, 0x19,
+	0x79, 0x73, 0x22, 0x67, 0x0a, 0x0f, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x47, 0x65, 0x74, 0x52,
+	0x65, 0x73, 0x75, 0x6c, 0x74, 0x12, 0x26, 0x0a, 0x04, 0x4b, 0x65, 0x79, 0x73, 0x18, 0x01, 0x20,
+	0x03, 0x28, 0x0b, 0x32, 0x12, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x53, 0x74,
+	0x6f, 0x72, 0x65, 0x73, 0x4b, 0x65, 0x79, 0x52, 0x04, 0x4b, 0x65, 0x79, 0x73, 0x12, 0x2c, 0x0a,
+	0x06, 0x56, 0x61, 0x6c, 0x75, 0x65, 0x73, 0x18, 0x02, 0x20, 0x03, 0x28, 0x0b, 0x32, 0x14, 0x2e,
+	0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x56, 0x61,
+	0x6c, 0x75, 0x65, 0x52, 0x06, 0x56, 0x61, 0x6c, 0x75, 0x65, 0x73, 0x22, 0x4d, 0x0a, 0x11, 0x53,
+	0x74, 0x6f, 0x72, 0x65, 0x73, 0x46, 0x69, 0x6e, 0x64, 0x4f, 0x70, 0x74, 0x69, 0x6f, 0x6e, 0x73,
+	0x12, 0x24, 0x0a, 0x03, 0x4b, 0x65, 0x79, 0x18, 0x01, 0x20, 0x01, 0x28, 0x0b, 0x32, 0x12, 0x2e,
+	0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x4b, 0x65,
+	0x79, 0x52, 0x03, 0x4b, 0x65, 0x79, 0x12, 0x12, 0x0a, 0x04, 0x54, 0x6f, 0x70, 0x4b, 0x18, 0x02,
+	0x20, 0x01, 0x28, 0x05, 0x52, 0x04, 0x54, 0x6f, 0x70, 0x4b, 0x22, 0x8c, 0x01, 0x0a, 0x10, 0x53,
+	0x74, 0x6f, 0x72, 0x65, 0x73, 0x46, 0x69, 0x6e, 0x64, 0x52, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x12,
+	0x26, 0x0a, 0x04, 0x4b, 0x65, 0x79, 0x73, 0x18, 0x01, 0x20, 0x03, 0x28, 0x0b, 0x32, 0x12, 0x2e,
+	0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x4b, 0x65,
+	0x79, 0x52, 0x04, 0x4b, 0x65, 0x79, 0x73, 0x12, 0x2c, 0x0a, 0x06, 0x56, 0x61, 0x6c, 0x75, 0x65,
+	0x73, 0x18, 0x02, 0x20, 0x03, 0x28, 0x0b, 0x32, 0x14, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e,
+	0x64, 0x2e, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x56, 0x61, 0x6c, 0x75, 0x65, 0x52, 0x06, 0x56,
+	0x61, 0x6c, 0x75, 0x65, 0x73, 0x12, 0x22, 0x0a, 0x0c, 0x53, 0x69, 0x6d, 0x69, 0x6c, 0x61, 0x72,
+	0x69, 0x74, 0x69, 0x65, 0x73, 0x18, 0x03, 0x20, 0x03, 0x28, 0x02, 0x52, 0x0c, 0x53, 0x69, 0x6d,
+	0x69, 0x6c, 0x61, 0x72, 0x69, 0x74, 0x69, 0x65, 0x73, 0x22, 0x0f, 0x0a, 0x0d, 0x48, 0x65, 0x61,
+	0x6c, 0x74, 0x68, 0x4d, 0x65, 0x73, 0x73, 0x61, 0x67, 0x65, 0x22, 0xd6, 0x0a, 0x0a, 0x0e, 0x50,
+	0x72, 0x65, 0x64, 0x69, 0x63, 0x74, 0x4f, 0x70, 0x74, 0x69, 0x6f, 0x6e, 0x73, 0x12, 0x16, 0x0a,
+	0x06, 0x50, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x18, 0x01, 0x20, 0x01, 0x28, 0x09, 0x52, 0x06, 0x50,
+	0x72, 0x6f, 0x6d, 0x70, 0x74, 0x12, 0x12, 0x0a, 0x04, 0x53, 0x65, 0x65, 0x64, 0x18, 0x02, 0x20,
+	0x01, 0x28, 0x05, 0x52, 0x04, 0x53, 0x65, 0x65, 0x64, 0x12, 0x18, 0x0a, 0x07, 0x54, 0x68, 0x72,
+	0x65, 0x61, 0x64, 0x73, 0x18, 0x03, 0x20, 0x01, 0x28, 0x05, 0x52, 0x07, 0x54, 0x68, 0x72, 0x65,
+	0x61, 0x64, 0x73, 0x12, 0x16, 0x0a, 0x06, 0x54, 0x6f, 0x6b, 0x65, 0x6e, 0x73, 0x18, 0x04, 0x20,
+	0x01, 0x28, 0x05, 0x52, 0x06, 0x54, 0x6f, 0x6b, 0x65, 0x6e, 0x73, 0x12, 0x12, 0x0a, 0x04, 0x54,
+	0x6f, 0x70, 0x4b, 0x18, 0x05, 0x20, 0x01, 0x28, 0x05, 0x52, 0x04, 0x54, 0x6f, 0x70, 0x4b, 0x12,
+	0x16, 0x0a, 0x06, 0x52, 0x65, 0x70, 0x65, 0x61, 0x74, 0x18, 0x06, 0x20, 0x01, 0x28, 0x05, 0x52,
+	0x06, 0x52, 0x65, 0x70, 0x65, 0x61, 0x74, 0x12, 0x14, 0x0a, 0x05, 0x42, 0x61, 0x74, 0x63, 0x68,
+	0x18, 0x07, 0x20, 0x01, 0x28, 0x05, 0x52, 0x05, 0x42, 0x61, 0x74, 0x63, 0x68, 0x12, 0x14, 0x0a,
+	0x05, 0x4e, 0x4b, 0x65, 0x65, 0x70, 0x18, 0x08, 0x20, 0x01, 0x28, 0x05, 0x52, 0x05, 0x4e, 0x4b,
+	0x65, 0x65, 0x70, 0x12, 0x20, 0x0a, 0x0b, 0x54, 0x65, 0x6d, 0x70, 0x65, 0x72, 0x61, 0x74, 0x75,
+	0x72, 0x65, 0x18, 0x09, 0x20, 0x01, 0x28, 0x02, 0x52, 0x0b, 0x54, 0x65, 0x6d, 0x70, 0x65, 0x72,
+	0x61, 0x74, 0x75, 0x72, 0x65, 0x12, 0x18, 0x0a, 0x07, 0x50, 0x65, 0x6e, 0x61, 0x6c, 0x74, 0x79,
+	0x18, 0x0a, 0x20, 0x01, 0x28, 0x02, 0x52, 0x07, 0x50, 0x65, 0x6e, 0x61, 0x6c, 0x74, 0x79, 0x12,
+	0x14, 0x0a, 0x05, 0x46, 0x31, 0x36, 0x4b, 0x56, 0x18, 0x0b, 0x20, 0x01, 0x28, 0x08, 0x52, 0x05,
+	0x46, 0x31, 0x36, 0x4b, 0x56, 0x12, 0x1c, 0x0a, 0x09, 0x44, 0x65, 0x62, 0x75, 0x67, 0x4d, 0x6f,
+	0x64, 0x65, 0x18, 0x0c, 0x20, 0x01, 0x28, 0x08, 0x52, 0x09, 0x44, 0x65, 0x62, 0x75, 0x67, 0x4d,
+	0x6f, 0x64, 0x65, 0x12, 0x20, 0x0a, 0x0b, 0x53, 0x74, 0x6f, 0x70, 0x50, 0x72, 0x6f, 0x6d, 0x70,
+	0x74, 0x73, 0x18, 0x0d, 0x20, 0x03, 0x28, 0x09, 0x52, 0x0b, 0x53, 0x74, 0x6f, 0x70, 0x50, 0x72,
+	0x6f, 0x6d, 0x70, 0x74, 0x73, 0x12, 0x1c, 0x0a, 0x09, 0x49, 0x67, 0x6e, 0x6f, 0x72, 0x65, 0x45,
+	0x4f, 0x53, 0x18, 0x0e, 0x20, 0x01, 0x28, 0x08, 0x52, 0x09, 0x49, 0x67, 0x6e, 0x6f, 0x72, 0x65,
+	0x45, 0x4f, 0x53, 0x12, 0x2c, 0x0a, 0x11, 0x54, 0x61, 0x69, 0x6c, 0x46, 0x72, 0x65, 0x65, 0x53,
+	0x61, 0x6d, 0x70, 0x6c, 0x69, 0x6e, 0x67, 0x5a, 0x18, 0x0f, 0x20, 0x01, 0x28, 0x02, 0x52, 0x11,
+	0x54, 0x61, 0x69, 0x6c, 0x46, 0x72, 0x65, 0x65, 0x53, 0x61, 0x6d, 0x70, 0x6c, 0x69, 0x6e, 0x67,
+	0x5a, 0x12, 0x1a, 0x0a, 0x08, 0x54, 0x79, 0x70, 0x69, 0x63, 0x61, 0x6c, 0x50, 0x18, 0x10, 0x20,
+	0x01, 0x28, 0x02, 0x52, 0x08, 0x54, 0x79, 0x70, 0x69, 0x63, 0x61, 0x6c, 0x50, 0x12, 0x2a, 0x0a,
+	0x10, 0x46, 0x72, 0x65, 0x71, 0x75, 0x65, 0x6e, 0x63, 0x79, 0x50, 0x65, 0x6e, 0x61, 0x6c, 0x74,
+	0x79, 0x18, 0x11, 0x20, 0x01, 0x28, 0x02, 0x52, 0x10, 0x46, 0x72, 0x65, 0x71, 0x75, 0x65, 0x6e,
+	0x63, 0x79, 0x50, 0x65, 0x6e, 0x61, 0x6c, 0x74, 0x79, 0x12, 0x28, 0x0a, 0x0f, 0x50, 0x72, 0x65,
+	0x73, 0x65, 0x6e, 0x63, 0x65, 0x50, 0x65, 0x6e, 0x61, 0x6c, 0x74, 0x79, 0x18, 0x12, 0x20, 0x01,
+	0x28, 0x02, 0x52, 0x0f, 0x50, 0x72, 0x65, 0x73, 0x65, 0x6e, 0x63, 0x65, 0x50, 0x65, 0x6e, 0x61,
+	0x6c, 0x74, 0x79, 0x12, 0x1a, 0x0a, 0x08, 0x4d, 0x69, 0x72, 0x6f, 0x73, 0x74, 0x61, 0x74, 0x18,
+	0x13, 0x20, 0x01, 0x28, 0x05, 0x52, 0x08, 0x4d, 0x69, 0x72, 0x6f, 0x73, 0x74, 0x61, 0x74, 0x12,
+	0x20, 0x0a, 0x0b, 0x4d, 0x69, 0x72, 0x6f, 0x73, 0x74, 0x61, 0x74, 0x45, 0x54, 0x41, 0x18, 0x14,
+	0x20, 0x01, 0x28, 0x02, 0x52, 0x0b, 0x4d, 0x69, 0x72, 0x6f, 0x73, 0x74, 0x61, 0x74, 0x45, 0x54,
+	0x41, 0x12, 0x20, 0x0a, 0x0b, 0x4d, 0x69, 0x72, 0x6f, 0x73, 0x74, 0x61, 0x74, 0x54, 0x41, 0x55,
+	0x18, 0x15, 0x20, 0x01, 0x28, 0x02, 0x52, 0x0b, 0x4d, 0x69, 0x72, 0x6f, 0x73, 0x74, 0x61, 0x74,
+	0x54, 0x41, 0x55, 0x12, 0x1e, 0x0a, 0x0a, 0x50, 0x65, 0x6e, 0x61, 0x6c, 0x69, 0x7a, 0x65, 0x4e,
+	0x4c, 0x18, 0x16, 0x20, 0x01, 0x28, 0x08, 0x52, 0x0a, 0x50, 0x65, 0x6e, 0x61, 0x6c, 0x69, 0x7a,
+	0x65, 0x4e, 0x4c, 0x12, 0x1c, 0x0a, 0x09, 0x4c, 0x6f, 0x67, 0x69, 0x74, 0x42, 0x69, 0x61, 0x73,
+	0x18, 0x17, 0x20, 0x01, 0x28, 0x09, 0x52, 0x09, 0x4c, 0x6f, 0x67, 0x69, 0x74, 0x42, 0x69, 0x61,
+	0x73, 0x12, 0x14, 0x0a, 0x05, 0x4d, 0x4c, 0x6f, 0x63, 0x6b, 0x18, 0x19, 0x20, 0x01, 0x28, 0x08,
+	0x52, 0x05, 0x4d, 0x4c, 0x6f, 0x63, 0x6b, 0x12, 0x12, 0x0a, 0x04, 0x4d, 0x4d, 0x61, 0x70, 0x18,
+	0x1a, 0x20, 0x01, 0x28, 0x08, 0x52, 0x04, 0x4d, 0x4d, 0x61, 0x70, 0x12, 0x26, 0x0a, 0x0e, 0x50,
+	0x72, 0x6f, 0x6d, 0x70, 0x74, 0x43, 0x61, 0x63, 0x68, 0x65, 0x41, 0x6c, 0x6c, 0x18, 0x1b, 0x20,
+	0x01, 0x28, 0x08, 0x52, 0x0e, 0x50, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x43, 0x61, 0x63, 0x68, 0x65,
+	0x41, 0x6c, 0x6c, 0x12, 0x24, 0x0a, 0x0d, 0x50, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x43, 0x61, 0x63,
+	0x68, 0x65, 0x52, 0x4f, 0x18, 0x1c, 0x20, 0x01, 0x28, 0x08, 0x52, 0x0d, 0x50, 0x72, 0x6f, 0x6d,
+	0x70, 0x74, 0x43, 0x61, 0x63, 0x68, 0x65, 0x52, 0x4f, 0x12, 0x18, 0x0a, 0x07, 0x47, 0x72, 0x61,
+	0x6d, 0x6d, 0x61, 0x72, 0x18, 0x1d, 0x20, 0x01, 0x28, 0x09, 0x52, 0x07, 0x47, 0x72, 0x61, 0x6d,
+	0x6d, 0x61, 0x72, 0x12, 0x18, 0x0a, 0x07, 0x4d, 0x61, 0x69, 0x6e, 0x47, 0x50, 0x55, 0x18, 0x1e,
+	0x20, 0x01, 0x28, 0x09, 0x52, 0x07, 0x4d, 0x61, 0x69, 0x6e, 0x47, 0x50, 0x55, 0x12, 0x20, 0x0a,
+	0x0b, 0x54, 0x65, 0x6e, 0x73, 0x6f, 0x72, 0x53, 0x70, 0x6c, 0x69, 0x74, 0x18, 0x1f, 0x20, 0x01,
+	0x28, 0x09, 0x52, 0x0b, 0x54, 0x65, 0x6e, 0x73, 0x6f, 0x72, 0x53, 0x70, 0x6c, 0x69, 0x74, 0x12,
+	0x12, 0x0a, 0x04, 0x54, 0x6f, 0x70, 0x50, 0x18, 0x20, 0x20, 0x01, 0x28, 0x02, 0x52, 0x04, 0x54,
+	0x6f, 0x70, 0x50, 0x12, 0x28, 0x0a, 0x0f, 0x50, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x43, 0x61, 0x63,
+	0x68, 0x65, 0x50, 0x61, 0x74, 0x68, 0x18, 0x21, 0x20, 0x01, 0x28, 0x09, 0x52, 0x0f, 0x50, 0x72,
+	0x6f, 0x6d, 0x70, 0x74, 0x43, 0x61, 0x63, 0x68, 0x65, 0x50, 0x61, 0x74, 0x68, 0x12, 0x14, 0x0a,
+	0x05, 0x44, 0x65, 0x62, 0x75, 0x67, 0x18, 0x22, 0x20, 0x01, 0x28, 0x08, 0x52, 0x05, 0x44, 0x65,
+	0x62, 0x75, 0x67, 0x12, 0x28, 0x0a, 0x0f, 0x45, 0x6d, 0x62, 0x65, 0x64, 0x64, 0x69, 0x6e, 0x67,
+	0x54, 0x6f, 0x6b, 0x65, 0x6e, 0x73, 0x18, 0x23, 0x20, 0x03, 0x28, 0x05, 0x52, 0x0f, 0x45, 0x6d,
+	0x62, 0x65, 0x64, 0x64, 0x69, 0x6e, 0x67, 0x54, 0x6f, 0x6b, 0x65, 0x6e, 0x73, 0x12, 0x1e, 0x0a,
+	0x0a, 0x45, 0x6d, 0x62, 0x65, 0x64, 0x64, 0x69, 0x6e, 0x67, 0x73, 0x18, 0x24, 0x20, 0x01, 0x28,
+	0x09, 0x52, 0x0a, 0x45, 0x6d, 0x62, 0x65, 0x64, 0x64, 0x69, 0x6e, 0x67, 0x73, 0x12, 0x22, 0x0a,
+	0x0c, 0x52, 0x6f, 0x70, 0x65, 0x46, 0x72, 0x65, 0x71, 0x42, 0x61, 0x73, 0x65, 0x18, 0x25, 0x20,
+	0x01, 0x28, 0x02, 0x52, 0x0c, 0x52, 0x6f, 0x70, 0x65, 0x46, 0x72, 0x65, 0x71, 0x42, 0x61, 0x73,
+	0x65, 0x12, 0x24, 0x0a, 0x0d, 0x52, 0x6f, 0x70, 0x65, 0x46, 0x72, 0x65, 0x71, 0x53, 0x63, 0x61,
+	0x6c, 0x65, 0x18, 0x26, 0x20, 0x01, 0x28, 0x02, 0x52, 0x0d, 0x52, 0x6f, 0x70, 0x65, 0x46, 0x72,
+	0x65, 0x71, 0x53, 0x63, 0x61, 0x6c, 0x65, 0x12, 0x30, 0x0a, 0x13, 0x4e, 0x65, 0x67, 0x61, 0x74,
+	0x69, 0x76, 0x65, 0x50, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x53, 0x63, 0x61, 0x6c, 0x65, 0x18, 0x27,
+	0x20, 0x01, 0x28, 0x02, 0x52, 0x13, 0x4e, 0x65, 0x67, 0x61, 0x74, 0x69, 0x76, 0x65, 0x50, 0x72,
+	0x6f, 0x6d, 0x70, 0x74, 0x53, 0x63, 0x61, 0x6c, 0x65, 0x12, 0x26, 0x0a, 0x0e, 0x4e, 0x65, 0x67,
+	0x61, 0x74, 0x69, 0x76, 0x65, 0x50, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x18, 0x28, 0x20, 0x01, 0x28,
+	0x09, 0x52, 0x0e, 0x4e, 0x65, 0x67, 0x61, 0x74, 0x69, 0x76, 0x65, 0x50, 0x72, 0x6f, 0x6d, 0x70,
+	0x74, 0x12, 0x16, 0x0a, 0x06, 0x4e, 0x44, 0x72, 0x61, 0x66, 0x74, 0x18, 0x29, 0x20, 0x01, 0x28,
+	0x05, 0x52, 0x06, 0x4e, 0x44, 0x72, 0x61, 0x66, 0x74, 0x12, 0x16, 0x0a, 0x06, 0x49, 0x6d, 0x61,
+	0x67, 0x65, 0x73, 0x18, 0x2a, 0x20, 0x03, 0x28, 0x09, 0x52, 0x06, 0x49, 0x6d, 0x61, 0x67, 0x65,
+	0x73, 0x12, 0x32, 0x0a, 0x14, 0x55, 0x73, 0x65, 0x54, 0x6f, 0x6b, 0x65, 0x6e, 0x69, 0x7a, 0x65,
+	0x72, 0x54, 0x65, 0x6d, 0x70, 0x6c, 0x61, 0x74, 0x65, 0x18, 0x2b, 0x20, 0x01, 0x28, 0x08, 0x52,
+	0x14, 0x55, 0x73, 0x65, 0x54, 0x6f, 0x6b, 0x65, 0x6e, 0x69, 0x7a, 0x65, 0x72, 0x54, 0x65, 0x6d,
+	0x70, 0x6c, 0x61, 0x74, 0x65, 0x12, 0x2c, 0x0a, 0x08, 0x4d, 0x65, 0x73, 0x73, 0x61, 0x67, 0x65,
+	0x73, 0x18, 0x2c, 0x20, 0x03, 0x28, 0x0b, 0x32, 0x10, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e,
+	0x64, 0x2e, 0x4d, 0x65, 0x73, 0x73, 0x61, 0x67, 0x65, 0x52, 0x08, 0x4d, 0x65, 0x73, 0x73, 0x61,
+	0x67, 0x65, 0x73, 0x22, 0x21, 0x0a, 0x05, 0x52, 0x65, 0x70, 0x6c, 0x79, 0x12, 0x18, 0x0a, 0x07,
+	0x6d, 0x65, 0x73, 0x73, 0x61, 0x67, 0x65, 0x18, 0x01, 0x20, 0x01, 0x28, 0x0c, 0x52, 0x07, 0x6d,
+	0x65, 0x73, 0x73, 0x61, 0x67, 0x65, 0x22, 0xa2, 0x0d, 0x0a, 0x0c, 0x4d, 0x6f, 0x64, 0x65, 0x6c,
+	0x4f, 0x70, 0x74, 0x69, 0x6f, 0x6e, 0x73, 0x12, 0x14, 0x0a, 0x05, 0x4d, 0x6f, 0x64, 0x65, 0x6c,
+	0x18, 0x01, 0x20, 0x01, 0x28, 0x09, 0x52, 0x05, 0x4d, 0x6f, 0x64, 0x65, 0x6c, 0x12, 0x20, 0x0a,
+	0x0b, 0x43, 0x6f, 0x6e, 0x74, 0x65, 0x78, 0x74, 0x53, 0x69, 0x7a, 0x65, 0x18, 0x02, 0x20, 0x01,
+	0x28, 0x05, 0x52, 0x0b, 0x43, 0x6f, 0x6e, 0x74, 0x65, 0x78, 0x74, 0x53, 0x69, 0x7a, 0x65, 0x12,
+	0x12, 0x0a, 0x04, 0x53, 0x65, 0x65, 0x64, 0x18, 0x03, 0x20, 0x01, 0x28, 0x05, 0x52, 0x04, 0x53,
+	0x65, 0x65, 0x64, 0x12, 0x16, 0x0a, 0x06, 0x4e, 0x42, 0x61, 0x74, 0x63, 0x68, 0x18, 0x04, 0x20,
+	0x01, 0x28, 0x05, 0x52, 0x06, 0x4e, 0x42, 0x61, 0x74, 0x63, 0x68, 0x12, 0x1c, 0x0a, 0x09, 0x46,
+	0x31, 0x36, 0x4d, 0x65, 0x6d, 0x6f, 0x72, 0x79, 0x18, 0x05, 0x20, 0x01, 0x28, 0x08, 0x52, 0x09,
+	0x46, 0x31, 0x36, 0x4d, 0x65, 0x6d, 0x6f, 0x72, 0x79, 0x12, 0x14, 0x0a, 0x05, 0x4d, 0x4c, 0x6f,
+	0x63, 0x6b, 0x18, 0x06, 0x20, 0x01, 0x28, 0x08, 0x52, 0x05, 0x4d, 0x4c, 0x6f, 0x63, 0x6b, 0x12,
+	0x12, 0x0a, 0x04, 0x4d, 0x4d, 0x61, 0x70, 0x18, 0x07, 0x20, 0x01, 0x28, 0x08, 0x52, 0x04, 0x4d,
+	0x4d, 0x61, 0x70, 0x12, 0x1c, 0x0a, 0x09, 0x56, 0x6f, 0x63, 0x61, 0x62, 0x4f, 0x6e, 0x6c, 0x79,
+	0x18, 0x08, 0x20, 0x01, 0x28, 0x08, 0x52, 0x09, 0x56, 0x6f, 0x63, 0x61, 0x62, 0x4f, 0x6e, 0x6c,
+	0x79, 0x12, 0x18, 0x0a, 0x07, 0x4c, 0x6f, 0x77, 0x56, 0x52, 0x41, 0x4d, 0x18, 0x09, 0x20, 0x01,
+	0x28, 0x08, 0x52, 0x07, 0x4c, 0x6f, 0x77, 0x56, 0x52, 0x41, 0x4d, 0x12, 0x1e, 0x0a, 0x0a, 0x45,
+	0x6d, 0x62, 0x65, 0x64, 0x64, 0x69, 0x6e, 0x67, 0x73, 0x18, 0x0a, 0x20, 0x01, 0x28, 0x08, 0x52,
+	0x0a, 0x45, 0x6d, 0x62, 0x65, 0x64, 0x64, 0x69, 0x6e, 0x67, 0x73, 0x12, 0x12, 0x0a, 0x04, 0x4e,
+	0x55, 0x4d, 0x41, 0x18, 0x0b, 0x20, 0x01, 0x28, 0x08, 0x52, 0x04, 0x4e, 0x55, 0x4d, 0x41, 0x12,
+	0x1e, 0x0a, 0x0a, 0x4e, 0x47, 0x50, 0x55, 0x4c, 0x61, 0x79, 0x65, 0x72, 0x73, 0x18, 0x0c, 0x20,
+	0x01, 0x28, 0x05, 0x52, 0x0a, 0x4e, 0x47, 0x50, 0x55, 0x4c, 0x61, 0x79, 0x65, 0x72, 0x73, 0x12,
+	0x18, 0x0a, 0x07, 0x4d, 0x61, 0x69, 0x6e, 0x47, 0x50, 0x55, 0x18, 0x0d, 0x20, 0x01, 0x28, 0x09,
+	0x52, 0x07, 0x4d, 0x61, 0x69, 0x6e, 0x47, 0x50, 0x55, 0x12, 0x20, 0x0a, 0x0b, 0x54, 0x65, 0x6e,
+	0x73, 0x6f, 0x72, 0x53, 0x70, 0x6c, 0x69, 0x74, 0x18, 0x0e, 0x20, 0x01, 0x28, 0x09, 0x52, 0x0b,
+	0x54, 0x65, 0x6e, 0x73, 0x6f, 0x72, 0x53, 0x70, 0x6c, 0x69, 0x74, 0x12, 0x18, 0x0a, 0x07, 0x54,
+	0x68, 0x72, 0x65, 0x61, 0x64, 0x73, 0x18, 0x0f, 0x20, 0x01, 0x28, 0x05, 0x52, 0x07, 0x54, 0x68,
+	0x72, 0x65, 0x61, 0x64, 0x73, 0x12, 0x2c, 0x0a, 0x11, 0x4c, 0x69, 0x62, 0x72, 0x61, 0x72, 0x79,
+	0x53, 0x65, 0x61, 0x72, 0x63, 0x68, 0x50, 0x61, 0x74, 0x68, 0x18, 0x10, 0x20, 0x01, 0x28, 0x09,
+	0x52, 0x11, 0x4c, 0x69, 0x62, 0x72, 0x61, 0x72, 0x79, 0x53, 0x65, 0x61, 0x72, 0x63, 0x68, 0x50,
+	0x61, 0x74, 0x68, 0x12, 0x22, 0x0a, 0x0c, 0x52, 0x6f, 0x70, 0x65, 0x46, 0x72, 0x65, 0x71, 0x42,
+	0x61, 0x73, 0x65, 0x18, 0x11, 0x20, 0x01, 0x28, 0x02, 0x52, 0x0c, 0x52, 0x6f, 0x70, 0x65, 0x46,
+	0x72, 0x65, 0x71, 0x42, 0x61, 0x73, 0x65, 0x12, 0x24, 0x0a, 0x0d, 0x52, 0x6f, 0x70, 0x65, 0x46,
+	0x72, 0x65, 0x71, 0x53, 0x63, 0x61, 0x6c, 0x65, 0x18, 0x12, 0x20, 0x01, 0x28, 0x02, 0x52, 0x0d,
+	0x52, 0x6f, 0x70, 0x65, 0x46, 0x72, 0x65, 0x71, 0x53, 0x63, 0x61, 0x6c, 0x65, 0x12, 0x1e, 0x0a,
+	0x0a, 0x52, 0x4d, 0x53, 0x4e, 0x6f, 0x72, 0x6d, 0x45, 0x70, 0x73, 0x18, 0x13, 0x20, 0x01, 0x28,
+	0x02, 0x52, 0x0a, 0x52, 0x4d, 0x53, 0x4e, 0x6f, 0x72, 0x6d, 0x45, 0x70, 0x73, 0x12, 0x12, 0x0a,
+	0x04, 0x4e, 0x47, 0x51, 0x41, 0x18, 0x14, 0x20, 0x01, 0x28, 0x05, 0x52, 0x04, 0x4e, 0x47, 0x51,
+	0x41, 0x12, 0x1c, 0x0a, 0x09, 0x4d, 0x6f, 0x64, 0x65, 0x6c, 0x46, 0x69, 0x6c, 0x65, 0x18, 0x15,
+	0x20, 0x01, 0x28, 0x09, 0x52, 0x09, 0x4d, 0x6f, 0x64, 0x65, 0x6c, 0x46, 0x69, 0x6c, 0x65, 0x12,
+	0x16, 0x0a, 0x06, 0x44, 0x65, 0x76, 0x69, 0x63, 0x65, 0x18, 0x16, 0x20, 0x01, 0x28, 0x09, 0x52,
+	0x06, 0x44, 0x65, 0x76, 0x69, 0x63, 0x65, 0x12, 0x1c, 0x0a, 0x09, 0x55, 0x73, 0x65, 0x54, 0x72,
+	0x69, 0x74, 0x6f, 0x6e, 0x18, 0x17, 0x20, 0x01, 0x28, 0x08, 0x52, 0x09, 0x55, 0x73, 0x65, 0x54,
+	0x72, 0x69, 0x74, 0x6f, 0x6e, 0x12, 0x24, 0x0a, 0x0d, 0x4d, 0x6f, 0x64, 0x65, 0x6c, 0x42, 0x61,
+	0x73, 0x65, 0x4e, 0x61, 0x6d, 0x65, 0x18, 0x18, 0x20, 0x01, 0x28, 0x09, 0x52, 0x0d, 0x4d, 0x6f,
+	0x64, 0x65, 0x6c, 0x42, 0x61, 0x73, 0x65, 0x4e, 0x61, 0x6d, 0x65, 0x12, 0x2a, 0x0a, 0x10, 0x55,
+	0x73, 0x65, 0x46, 0x61, 0x73, 0x74, 0x54, 0x6f, 0x6b, 0x65, 0x6e, 0x69, 0x7a, 0x65, 0x72, 0x18,
+	0x19, 0x20, 0x01, 0x28, 0x08, 0x52, 0x10, 0x55, 0x73, 0x65, 0x46, 0x61, 0x73, 0x74, 0x54, 0x6f,
+	0x6b, 0x65, 0x6e, 0x69, 0x7a, 0x65, 0x72, 0x12, 0x22, 0x0a, 0x0c, 0x50, 0x69, 0x70, 0x65, 0x6c,
+	0x69, 0x6e, 0x65, 0x54, 0x79, 0x70, 0x65, 0x18, 0x1a, 0x20, 0x01, 0x28, 0x09, 0x52, 0x0c, 0x50,
+	0x69, 0x70, 0x65, 0x6c, 0x69, 0x6e, 0x65, 0x54, 0x79, 0x70, 0x65, 0x12, 0x24, 0x0a, 0x0d, 0x53,
+	0x63, 0x68, 0x65, 0x64, 0x75, 0x6c, 0x65, 0x72, 0x54, 0x79, 0x70, 0x65, 0x18, 0x1b, 0x20, 0x01,
+	0x28, 0x09, 0x52, 0x0d, 0x53, 0x63, 0x68, 0x65, 0x64, 0x75, 0x6c, 0x65, 0x72, 0x54, 0x79, 0x70,
+	0x65, 0x12, 0x12, 0x0a, 0x04, 0x43, 0x55, 0x44, 0x41, 0x18, 0x1c, 0x20, 0x01, 0x28, 0x08, 0x52,
+	0x04, 0x43, 0x55, 0x44, 0x41, 0x12, 0x1a, 0x0a, 0x08, 0x43, 0x46, 0x47, 0x53, 0x63, 0x61, 0x6c,
+	0x65, 0x18, 0x1d, 0x20, 0x01, 0x28, 0x02, 0x52, 0x08, 0x43, 0x46, 0x47, 0x53, 0x63, 0x61, 0x6c,
+	0x65, 0x12, 0x18, 0x0a, 0x07, 0x49, 0x4d, 0x47, 0x32, 0x49, 0x4d, 0x47, 0x18, 0x1e, 0x20, 0x01,
+	0x28, 0x08, 0x52, 0x07, 0x49, 0x4d, 0x47, 0x32, 0x49, 0x4d, 0x47, 0x12, 0x1c, 0x0a, 0x09, 0x43,
+	0x4c, 0x49, 0x50, 0x4d, 0x6f, 0x64, 0x65, 0x6c, 0x18, 0x1f, 0x20, 0x01, 0x28, 0x09, 0x52, 0x09,
+	0x43, 0x4c, 0x49, 0x50, 0x4d, 0x6f, 0x64, 0x65, 0x6c, 0x12, 0x24, 0x0a, 0x0d, 0x43, 0x4c, 0x49,
+	0x50, 0x53, 0x75, 0x62, 0x66, 0x6f, 0x6c, 0x64, 0x65, 0x72, 0x18, 0x20, 0x20, 0x01, 0x28, 0x09,
+	0x52, 0x0d, 0x43, 0x4c, 0x49, 0x50, 0x53, 0x75, 0x62, 0x66, 0x6f, 0x6c, 0x64, 0x65, 0x72, 0x12,
+	0x1a, 0x0a, 0x08, 0x43, 0x4c, 0x49, 0x50, 0x53, 0x6b, 0x69, 0x70, 0x18, 0x21, 0x20, 0x01, 0x28,
+	0x05, 0x52, 0x08, 0x43, 0x4c, 0x49, 0x50, 0x53, 0x6b, 0x69, 0x70, 0x12, 0x1e, 0x0a, 0x0a, 0x43,
+	0x6f, 0x6e, 0x74, 0x72, 0x6f, 0x6c, 0x4e, 0x65, 0x74, 0x18, 0x30, 0x20, 0x01, 0x28, 0x09, 0x52,
+	0x0a, 0x43, 0x6f, 0x6e, 0x74, 0x72, 0x6f, 0x6c, 0x4e, 0x65, 0x74, 0x12, 0x1c, 0x0a, 0x09, 0x54,
+	0x6f, 0x6b, 0x65, 0x6e, 0x69, 0x7a, 0x65, 0x72, 0x18, 0x22, 0x20, 0x01, 0x28, 0x09, 0x52, 0x09,
+	0x54, 0x6f, 0x6b, 0x65, 0x6e, 0x69, 0x7a, 0x65, 0x72, 0x12, 0x1a, 0x0a, 0x08, 0x4c, 0x6f, 0x72,
+	0x61, 0x42, 0x61, 0x73, 0x65, 0x18, 0x23, 0x20, 0x01, 0x28, 0x09, 0x52, 0x08, 0x4c, 0x6f, 0x72,
+	0x61, 0x42, 0x61, 0x73, 0x65, 0x12, 0x20, 0x0a, 0x0b, 0x4c, 0x6f, 0x72, 0x61, 0x41, 0x64, 0x61,
+	0x70, 0x74, 0x65, 0x72, 0x18, 0x24, 0x20, 0x01, 0x28, 0x09, 0x52, 0x0b, 0x4c, 0x6f, 0x72, 0x61,
+	0x41, 0x64, 0x61, 0x70, 0x74, 0x65, 0x72, 0x12, 0x1c, 0x0a, 0x09, 0x4c, 0x6f, 0x72, 0x61, 0x53,
+	0x63, 0x61, 0x6c, 0x65, 0x18, 0x2a, 0x20, 0x01, 0x28, 0x02, 0x52, 0x09, 0x4c, 0x6f, 0x72, 0x61,
+	0x53, 0x63, 0x61, 0x6c, 0x65, 0x12, 0x1c, 0x0a, 0x09, 0x4e, 0x6f, 0x4d, 0x75, 0x6c, 0x4d, 0x61,
+	0x74, 0x51, 0x18, 0x25, 0x20, 0x01, 0x28, 0x08, 0x52, 0x09, 0x4e, 0x6f, 0x4d, 0x75, 0x6c, 0x4d,
+	0x61, 0x74, 0x51, 0x12, 0x1e, 0x0a, 0x0a, 0x44, 0x72, 0x61, 0x66, 0x74, 0x4d, 0x6f, 0x64, 0x65,
+	0x6c, 0x18, 0x27, 0x20, 0x01, 0x28, 0x09, 0x52, 0x0a, 0x44, 0x72, 0x61, 0x66, 0x74, 0x4d, 0x6f,
+	0x64, 0x65, 0x6c, 0x12, 0x1c, 0x0a, 0x09, 0x41, 0x75, 0x64, 0x69, 0x6f, 0x50, 0x61, 0x74, 0x68,
+	0x18, 0x26, 0x20, 0x01, 0x28, 0x09, 0x52, 0x09, 0x41, 0x75, 0x64, 0x69, 0x6f, 0x50, 0x61, 0x74,
+	0x68, 0x12, 0x22, 0x0a, 0x0c, 0x51, 0x75, 0x61, 0x6e, 0x74, 0x69, 0x7a, 0x61, 0x74, 0x69, 0x6f,
+	0x6e, 0x18, 0x28, 0x20, 0x01, 0x28, 0x09, 0x52, 0x0c, 0x51, 0x75, 0x61, 0x6e, 0x74, 0x69, 0x7a,
+	0x61, 0x74, 0x69, 0x6f, 0x6e, 0x12, 0x32, 0x0a, 0x14, 0x47, 0x50, 0x55, 0x4d, 0x65, 0x6d, 0x6f,
+	0x72, 0x79, 0x55, 0x74, 0x69, 0x6c, 0x69, 0x7a, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x18, 0x32, 0x20,
+	0x01, 0x28, 0x02, 0x52, 0x14, 0x47, 0x50, 0x55, 0x4d, 0x65, 0x6d, 0x6f, 0x72, 0x79, 0x55, 0x74,
+	0x69, 0x6c, 0x69, 0x7a, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x12, 0x28, 0x0a, 0x0f, 0x54, 0x72, 0x75,
+	0x73, 0x74, 0x52, 0x65, 0x6d, 0x6f, 0x74, 0x65, 0x43, 0x6f, 0x64, 0x65, 0x18, 0x33, 0x20, 0x01,
+	0x28, 0x08, 0x52, 0x0f, 0x54, 0x72, 0x75, 0x73, 0x74, 0x52, 0x65, 0x6d, 0x6f, 0x74, 0x65, 0x43,
+	0x6f, 0x64, 0x65, 0x12, 0x22, 0x0a, 0x0c, 0x45, 0x6e, 0x66, 0x6f, 0x72, 0x63, 0x65, 0x45, 0x61,
+	0x67, 0x65, 0x72, 0x18, 0x34, 0x20, 0x01, 0x28, 0x08, 0x52, 0x0c, 0x45, 0x6e, 0x66, 0x6f, 0x72,
+	0x63, 0x65, 0x45, 0x61, 0x67, 0x65, 0x72, 0x12, 0x1c, 0x0a, 0x09, 0x53, 0x77, 0x61, 0x70, 0x53,
+	0x70, 0x61, 0x63, 0x65, 0x18, 0x35, 0x20, 0x01, 0x28, 0x05, 0x52, 0x09, 0x53, 0x77, 0x61, 0x70,
+	0x53, 0x70, 0x61, 0x63, 0x65, 0x12, 0x20, 0x0a, 0x0b, 0x4d, 0x61, 0x78, 0x4d, 0x6f, 0x64, 0x65,
+	0x6c, 0x4c, 0x65, 0x6e, 0x18, 0x36, 0x20, 0x01, 0x28, 0x05, 0x52, 0x0b, 0x4d, 0x61, 0x78, 0x4d,
+	0x6f, 0x64, 0x65, 0x6c, 0x4c, 0x65, 0x6e, 0x12, 0x16, 0x0a, 0x06, 0x4d, 0x4d, 0x50, 0x72, 0x6f,
+	0x6a, 0x18, 0x29, 0x20, 0x01, 0x28, 0x09, 0x52, 0x06, 0x4d, 0x4d, 0x50, 0x72, 0x6f, 0x6a, 0x12,
+	0x20, 0x0a, 0x0b, 0x52, 0x6f, 0x70, 0x65, 0x53, 0x63, 0x61, 0x6c, 0x69, 0x6e, 0x67, 0x18, 0x2b,
+	0x20, 0x01, 0x28, 0x09, 0x52, 0x0b, 0x52, 0x6f, 0x70, 0x65, 0x53, 0x63, 0x61, 0x6c, 0x69, 0x6e,
+	0x67, 0x12, 0x24, 0x0a, 0x0d, 0x59, 0x61, 0x72, 0x6e, 0x45, 0x78, 0x74, 0x46, 0x61, 0x63, 0x74,
+	0x6f, 0x72, 0x18, 0x2c, 0x20, 0x01, 0x28, 0x02, 0x52, 0x0d, 0x59, 0x61, 0x72, 0x6e, 0x45, 0x78,
+	0x74, 0x46, 0x61, 0x63, 0x74, 0x6f, 0x72, 0x12, 0x26, 0x0a, 0x0e, 0x59, 0x61, 0x72, 0x6e, 0x41,
+	0x74, 0x74, 0x6e, 0x46, 0x61, 0x63, 0x74, 0x6f, 0x72, 0x18, 0x2d, 0x20, 0x01, 0x28, 0x02, 0x52,
+	0x0e, 0x59, 0x61, 0x72, 0x6e, 0x41, 0x74, 0x74, 0x6e, 0x46, 0x61, 0x63, 0x74, 0x6f, 0x72, 0x12,
+	0x22, 0x0a, 0x0c, 0x59, 0x61, 0x72, 0x6e, 0x42, 0x65, 0x74, 0x61, 0x46, 0x61, 0x73, 0x74, 0x18,
+	0x2e, 0x20, 0x01, 0x28, 0x02, 0x52, 0x0c, 0x59, 0x61, 0x72, 0x6e, 0x42, 0x65, 0x74, 0x61, 0x46,
+	0x61, 0x73, 0x74, 0x12, 0x22, 0x0a, 0x0c, 0x59, 0x61, 0x72, 0x6e, 0x42, 0x65, 0x74, 0x61, 0x53,
+	0x6c, 0x6f, 0x77, 0x18, 0x2f, 0x20, 0x01, 0x28, 0x02, 0x52, 0x0c, 0x59, 0x61, 0x72, 0x6e, 0x42,
+	0x65, 0x74, 0x61, 0x53, 0x6c, 0x6f, 0x77, 0x12, 0x12, 0x0a, 0x04, 0x54, 0x79, 0x70, 0x65, 0x18,
+	0x31, 0x20, 0x01, 0x28, 0x09, 0x52, 0x04, 0x54, 0x79, 0x70, 0x65, 0x22, 0x3c, 0x0a, 0x06, 0x52,
+	0x65, 0x73, 0x75, 0x6c, 0x74, 0x12, 0x18, 0x0a, 0x07, 0x6d, 0x65, 0x73, 0x73, 0x61, 0x67, 0x65,
+	0x18, 0x01, 0x20, 0x01, 0x28, 0x09, 0x52, 0x07, 0x6d, 0x65, 0x73, 0x73, 0x61, 0x67, 0x65, 0x12,
+	0x18, 0x0a, 0x07, 0x73, 0x75, 0x63, 0x63, 0x65, 0x73, 0x73, 0x18, 0x02, 0x20, 0x01, 0x28, 0x08,
+	0x52, 0x07, 0x73, 0x75, 0x63, 0x63, 0x65, 0x73, 0x73, 0x22, 0x31, 0x0a, 0x0f, 0x45, 0x6d, 0x62,
+	0x65, 0x64, 0x64, 0x69, 0x6e, 0x67, 0x52, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x12, 0x1e, 0x0a, 0x0a,
+	0x65, 0x6d, 0x62, 0x65, 0x64, 0x64, 0x69, 0x6e, 0x67, 0x73, 0x18, 0x01, 0x20, 0x03, 0x28, 0x02,
+	0x52, 0x0a, 0x65, 0x6d, 0x62, 0x65, 0x64, 0x64, 0x69, 0x6e, 0x67, 0x73, 0x22, 0x5b, 0x0a, 0x11,
+	0x54, 0x72, 0x61, 0x6e, 0x73, 0x63, 0x72, 0x69, 0x70, 0x74, 0x52, 0x65, 0x71, 0x75, 0x65, 0x73,
+	0x74, 0x12, 0x10, 0x0a, 0x03, 0x64, 0x73, 0x74, 0x18, 0x02, 0x20, 0x01, 0x28, 0x09, 0x52, 0x03,
+	0x64, 0x73, 0x74, 0x12, 0x1a, 0x0a, 0x08, 0x6c, 0x61, 0x6e, 0x67, 0x75, 0x61, 0x67, 0x65, 0x18,
+	0x03, 0x20, 0x01, 0x28, 0x09, 0x52, 0x08, 0x6c, 0x61, 0x6e, 0x67, 0x75, 0x61, 0x67, 0x65, 0x12,
+	0x18, 0x0a, 0x07, 0x74, 0x68, 0x72, 0x65, 0x61, 0x64, 0x73, 0x18, 0x04, 0x20, 0x01, 0x28, 0x0d,
+	0x52, 0x07, 0x74, 0x68, 0x72, 0x65, 0x61, 0x64, 0x73, 0x22, 0x5e, 0x0a, 0x10, 0x54, 0x72, 0x61,
+	0x6e, 0x73, 0x63, 0x72, 0x69, 0x70, 0x74, 0x52, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x12, 0x36, 0x0a,
+	0x08, 0x73, 0x65, 0x67, 0x6d, 0x65, 0x6e, 0x74, 0x73, 0x18, 0x01, 0x20, 0x03, 0x28, 0x0b, 0x32,
+	0x1a, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x54, 0x72, 0x61, 0x6e, 0x73, 0x63,
+	0x72, 0x69, 0x70, 0x74, 0x53, 0x65, 0x67, 0x6d, 0x65, 0x6e, 0x74, 0x52, 0x08, 0x73, 0x65, 0x67,
+	0x6d, 0x65, 0x6e, 0x74, 0x73, 0x12, 0x12, 0x0a, 0x04, 0x74, 0x65, 0x78, 0x74, 0x18, 0x02, 0x20,
+	0x01, 0x28, 0x09, 0x52, 0x04, 0x74, 0x65, 0x78, 0x74, 0x22, 0x77, 0x0a, 0x11, 0x54, 0x72, 0x61,
+	0x6e, 0x73, 0x63, 0x72, 0x69, 0x70, 0x74, 0x53, 0x65, 0x67, 0x6d, 0x65, 0x6e, 0x74, 0x12, 0x0e,
+	0x0a, 0x02, 0x69, 0x64, 0x18, 0x01, 0x20, 0x01, 0x28, 0x05, 0x52, 0x02, 0x69, 0x64, 0x12, 0x14,
+	0x0a, 0x05, 0x73, 0x74, 0x61, 0x72, 0x74, 0x18, 0x02, 0x20, 0x01, 0x28, 0x03, 0x52, 0x05, 0x73,
+	0x74, 0x61, 0x72, 0x74, 0x12, 0x10, 0x0a, 0x03, 0x65, 0x6e, 0x64, 0x18, 0x03, 0x20, 0x01, 0x28,
+	0x03, 0x52, 0x03, 0x65, 0x6e, 0x64, 0x12, 0x12, 0x0a, 0x04, 0x74, 0x65, 0x78, 0x74, 0x18, 0x04,
+	0x20, 0x01, 0x28, 0x09, 0x52, 0x04, 0x74, 0x65, 0x78, 0x74, 0x12, 0x16, 0x0a, 0x06, 0x74, 0x6f,
+	0x6b, 0x65, 0x6e, 0x73, 0x18, 0x05, 0x20, 0x03, 0x28, 0x05, 0x52, 0x06, 0x74, 0x6f, 0x6b, 0x65,
+	0x6e, 0x73, 0x22, 0xbe, 0x02, 0x0a, 0x14, 0x47, 0x65, 0x6e, 0x65, 0x72, 0x61, 0x74, 0x65, 0x49,
+	0x6d, 0x61, 0x67, 0x65, 0x52, 0x65, 0x71, 0x75, 0x65, 0x73, 0x74, 0x12, 0x16, 0x0a, 0x06, 0x68,
+	0x65, 0x69, 0x67, 0x68, 0x74, 0x18, 0x01, 0x20, 0x01, 0x28, 0x05, 0x52, 0x06, 0x68, 0x65, 0x69,
+	0x67, 0x68, 0x74, 0x12, 0x14, 0x0a, 0x05, 0x77, 0x69, 0x64, 0x74, 0x68, 0x18, 0x02, 0x20, 0x01,
+	0x28, 0x05, 0x52, 0x05, 0x77, 0x69, 0x64, 0x74, 0x68, 0x12, 0x12, 0x0a, 0x04, 0x6d, 0x6f, 0x64,
+	0x65, 0x18, 0x03, 0x20, 0x01, 0x28, 0x05, 0x52, 0x04, 0x6d, 0x6f, 0x64, 0x65, 0x12, 0x12, 0x0a,
+	0x04, 0x73, 0x74, 0x65, 0x70, 0x18, 0x04, 0x20, 0x01, 0x28, 0x05, 0x52, 0x04, 0x73, 0x74, 0x65,
+	0x70, 0x12, 0x12, 0x0a, 0x04, 0x73, 0x65, 0x65, 0x64, 0x18, 0x05, 0x20, 0x01, 0x28, 0x05, 0x52,
+	0x04, 0x73, 0x65, 0x65, 0x64, 0x12, 0x27, 0x0a, 0x0f, 0x70, 0x6f, 0x73, 0x69, 0x74, 0x69, 0x76,
+	0x65, 0x5f, 0x70, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x18, 0x06, 0x20, 0x01, 0x28, 0x09, 0x52, 0x0e,
+	0x70, 0x6f, 0x73, 0x69, 0x74, 0x69, 0x76, 0x65, 0x50, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x12, 0x27,
+	0x0a, 0x0f, 0x6e, 0x65, 0x67, 0x61, 0x74, 0x69, 0x76, 0x65, 0x5f, 0x70, 0x72, 0x6f, 0x6d, 0x70,
+	0x74, 0x18, 0x07, 0x20, 0x01, 0x28, 0x09, 0x52, 0x0e, 0x6e, 0x65, 0x67, 0x61, 0x74, 0x69, 0x76,
+	0x65, 0x50, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x12, 0x10, 0x0a, 0x03, 0x64, 0x73, 0x74, 0x18, 0x08,
+	0x20, 0x01, 0x28, 0x09, 0x52, 0x03, 0x64, 0x73, 0x74, 0x12, 0x10, 0x0a, 0x03, 0x73, 0x72, 0x63,
+	0x18, 0x09, 0x20, 0x01, 0x28, 0x09, 0x52, 0x03, 0x73, 0x72, 0x63, 0x12, 0x2a, 0x0a, 0x10, 0x45,
+	0x6e, 0x61, 0x62, 0x6c, 0x65, 0x50, 0x61, 0x72, 0x61, 0x6d, 0x65, 0x74, 0x65, 0x72, 0x73, 0x18,
+	0x0a, 0x20, 0x01, 0x28, 0x09, 0x52, 0x10, 0x45, 0x6e, 0x61, 0x62, 0x6c, 0x65, 0x50, 0x61, 0x72,
+	0x61, 0x6d, 0x65, 0x74, 0x65, 0x72, 0x73, 0x12, 0x1a, 0x0a, 0x08, 0x43, 0x4c, 0x49, 0x50, 0x53,
+	0x6b, 0x69, 0x70, 0x18, 0x0b, 0x20, 0x01, 0x28, 0x05, 0x52, 0x08, 0x43, 0x4c, 0x49, 0x50, 0x53,
+	0x6b, 0x69, 0x70, 0x22, 0x5e, 0x0a, 0x0a, 0x54, 0x54, 0x53, 0x52, 0x65, 0x71, 0x75, 0x65, 0x73,
+	0x74, 0x12, 0x12, 0x0a, 0x04, 0x74, 0x65, 0x78, 0x74, 0x18, 0x01, 0x20, 0x01, 0x28, 0x09, 0x52,
+	0x04, 0x74, 0x65, 0x78, 0x74, 0x12, 0x14, 0x0a, 0x05, 0x6d, 0x6f, 0x64, 0x65, 0x6c, 0x18, 0x02,
+	0x20, 0x01, 0x28, 0x09, 0x52, 0x05, 0x6d, 0x6f, 0x64, 0x65, 0x6c, 0x12, 0x10, 0x0a, 0x03, 0x64,
+	0x73, 0x74, 0x18, 0x03, 0x20, 0x01, 0x28, 0x09, 0x52, 0x03, 0x64, 0x73, 0x74, 0x12, 0x14, 0x0a,
+	0x05, 0x76, 0x6f, 0x69, 0x63, 0x65, 0x18, 0x04, 0x20, 0x01, 0x28, 0x09, 0x52, 0x05, 0x76, 0x6f,
+	0x69, 0x63, 0x65, 0x22, 0x46, 0x0a, 0x14, 0x54, 0x6f, 0x6b, 0x65, 0x6e, 0x69, 0x7a, 0x61, 0x74,
+	0x69, 0x6f, 0x6e, 0x52, 0x65, 0x73, 0x70, 0x6f, 0x6e, 0x73, 0x65, 0x12, 0x16, 0x0a, 0x06, 0x6c,
+	0x65, 0x6e, 0x67, 0x74, 0x68, 0x18, 0x01, 0x20, 0x01, 0x28, 0x05, 0x52, 0x06, 0x6c, 0x65, 0x6e,
+	0x67, 0x74, 0x68, 0x12, 0x16, 0x0a, 0x06, 0x74, 0x6f, 0x6b, 0x65, 0x6e, 0x73, 0x18, 0x02, 0x20,
+	0x03, 0x28, 0x05, 0x52, 0x06, 0x74, 0x6f, 0x6b, 0x65, 0x6e, 0x73, 0x22, 0xac, 0x01, 0x0a, 0x0f,
+	0x4d, 0x65, 0x6d, 0x6f, 0x72, 0x79, 0x55, 0x73, 0x61, 0x67, 0x65, 0x44, 0x61, 0x74, 0x61, 0x12,
+	0x14, 0x0a, 0x05, 0x74, 0x6f, 0x74, 0x61, 0x6c, 0x18, 0x01, 0x20, 0x01, 0x28, 0x04, 0x52, 0x05,
+	0x74, 0x6f, 0x74, 0x61, 0x6c, 0x12, 0x45, 0x0a, 0x09, 0x62, 0x72, 0x65, 0x61, 0x6b, 0x64, 0x6f,
+	0x77, 0x6e, 0x18, 0x02, 0x20, 0x03, 0x28, 0x0b, 0x32, 0x27, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65,
+	0x6e, 0x64, 0x2e, 0x4d, 0x65, 0x6d, 0x6f, 0x72, 0x79, 0x55, 0x73, 0x61, 0x67, 0x65, 0x44, 0x61,
+	0x74, 0x61, 0x2e, 0x42, 0x72, 0x65, 0x61, 0x6b, 0x64, 0x6f, 0x77, 0x6e, 0x45, 0x6e, 0x74, 0x72,
+	0x79, 0x52, 0x09, 0x62, 0x72, 0x65, 0x61, 0x6b, 0x64, 0x6f, 0x77, 0x6e, 0x1a, 0x3c, 0x0a, 0x0e,
+	0x42, 0x72, 0x65, 0x61, 0x6b, 0x64, 0x6f, 0x77, 0x6e, 0x45, 0x6e, 0x74, 0x72, 0x79, 0x12, 0x10,
+	0x0a, 0x03, 0x6b, 0x65, 0x79, 0x18, 0x01, 0x20, 0x01, 0x28, 0x09, 0x52, 0x03, 0x6b, 0x65, 0x79,
+	0x12, 0x14, 0x0a, 0x05, 0x76, 0x61, 0x6c, 0x75, 0x65, 0x18, 0x02, 0x20, 0x01, 0x28, 0x04, 0x52,
+	0x05, 0x76, 0x61, 0x6c, 0x75, 0x65, 0x3a, 0x02, 0x38, 0x01, 0x22, 0xbc, 0x01, 0x0a, 0x0e, 0x53,
+	0x74, 0x61, 0x74, 0x75, 0x73, 0x52, 0x65, 0x73, 0x70, 0x6f, 0x6e, 0x73, 0x65, 0x12, 0x33, 0x0a,
+	0x05, 0x73, 0x74, 0x61, 0x74, 0x65, 0x18, 0x01, 0x20, 0x01, 0x28, 0x0e, 0x32, 0x1d, 0x2e, 0x62,
+	0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x53, 0x74, 0x61, 0x74, 0x75, 0x73, 0x52, 0x65, 0x73,
+	0x70, 0x6f, 0x6e, 0x73, 0x65, 0x2e, 0x53, 0x74, 0x61, 0x74, 0x65, 0x52, 0x05, 0x73, 0x74, 0x61,
+	0x74, 0x65, 0x12, 0x30, 0x0a, 0x06, 0x6d, 0x65, 0x6d, 0x6f, 0x72, 0x79, 0x18, 0x02, 0x20, 0x01,
+	0x28, 0x0b, 0x32, 0x18, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x4d, 0x65, 0x6d,
+	0x6f, 0x72, 0x79, 0x55, 0x73, 0x61, 0x67, 0x65, 0x44, 0x61, 0x74, 0x61, 0x52, 0x06, 0x6d, 0x65,
+	0x6d, 0x6f, 0x72, 0x79, 0x22, 0x43, 0x0a, 0x05, 0x53, 0x74, 0x61, 0x74, 0x65, 0x12, 0x11, 0x0a,
+	0x0d, 0x55, 0x4e, 0x49, 0x4e, 0x49, 0x54, 0x49, 0x41, 0x4c, 0x49, 0x5a, 0x45, 0x44, 0x10, 0x00,
+	0x12, 0x08, 0x0a, 0x04, 0x42, 0x55, 0x53, 0x59, 0x10, 0x01, 0x12, 0x09, 0x0a, 0x05, 0x52, 0x45,
+	0x41, 0x44, 0x59, 0x10, 0x02, 0x12, 0x12, 0x0a, 0x05, 0x45, 0x52, 0x52, 0x4f, 0x52, 0x10, 0xff,
+	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x01, 0x22, 0x4d, 0x0a, 0x07, 0x4d, 0x65, 0x73,
+	0x73, 0x61, 0x67, 0x65, 0x12, 0x12, 0x0a, 0x04, 0x52, 0x6f, 0x6c, 0x65, 0x18, 0x01, 0x20, 0x01,
+	0x28, 0x09, 0x52, 0x04, 0x52, 0x6f, 0x6c, 0x65, 0x12, 0x2e, 0x0a, 0x07, 0x43, 0x6f, 0x6e, 0x74,
+	0x65, 0x6e, 0x74, 0x18, 0x02, 0x20, 0x01, 0x28, 0x0b, 0x32, 0x14, 0x2e, 0x67, 0x6f, 0x6f, 0x67,
+	0x6c, 0x65, 0x2e, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x62, 0x75, 0x66, 0x2e, 0x41, 0x6e, 0x79, 0x52,
+	0x07, 0x43, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x32, 0xfb, 0x06, 0x0a, 0x07, 0x42, 0x61, 0x63,
+	0x6b, 0x65, 0x6e, 0x64, 0x12, 0x32, 0x0a, 0x06, 0x48, 0x65, 0x61, 0x6c, 0x74, 0x68, 0x12, 0x16,
+	0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x48, 0x65, 0x61, 0x6c, 0x74, 0x68, 0x4d,
+	0x65, 0x73, 0x73, 0x61, 0x67, 0x65, 0x1a, 0x0e, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64,
+	0x2e, 0x52, 0x65, 0x70, 0x6c, 0x79, 0x22, 0x00, 0x12, 0x34, 0x0a, 0x07, 0x50, 0x72, 0x65, 0x64,
+	0x69, 0x63, 0x74, 0x12, 0x17, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x50, 0x72,
+	0x65, 0x64, 0x69, 0x63, 0x74, 0x4f, 0x70, 0x74, 0x69, 0x6f, 0x6e, 0x73, 0x1a, 0x0e, 0x2e, 0x62,
+	0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x52, 0x65, 0x70, 0x6c, 0x79, 0x22, 0x00, 0x12, 0x35,
+	0x0a, 0x09, 0x4c, 0x6f, 0x61, 0x64, 0x4d, 0x6f, 0x64, 0x65, 0x6c, 0x12, 0x15, 0x2e, 0x62, 0x61,
+	0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x4d, 0x6f, 0x64, 0x65, 0x6c, 0x4f, 0x70, 0x74, 0x69, 0x6f,
+	0x6e, 0x73, 0x1a, 0x0f, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x52, 0x65, 0x73,
+	0x75, 0x6c, 0x74, 0x22, 0x00, 0x12, 0x3c, 0x0a, 0x0d, 0x50, 0x72, 0x65, 0x64, 0x69, 0x63, 0x74,
+	0x53, 0x74, 0x72, 0x65, 0x61, 0x6d, 0x12, 0x17, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64,
+	0x2e, 0x50, 0x72, 0x65, 0x64, 0x69, 0x63, 0x74, 0x4f, 0x70, 0x74, 0x69, 0x6f, 0x6e, 0x73, 0x1a,
+	0x0e, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x52, 0x65, 0x70, 0x6c, 0x79, 0x22,
+	0x00, 0x30, 0x01, 0x12, 0x40, 0x0a, 0x09, 0x45, 0x6d, 0x62, 0x65, 0x64, 0x64, 0x69, 0x6e, 0x67,
+	0x12, 0x17, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x50, 0x72, 0x65, 0x64, 0x69,
+	0x63, 0x74, 0x4f, 0x70, 0x74, 0x69, 0x6f, 0x6e, 0x73, 0x1a, 0x18, 0x2e, 0x62, 0x61, 0x63, 0x6b,
+	0x65, 0x6e, 0x64, 0x2e, 0x45, 0x6d, 0x62, 0x65, 0x64, 0x64, 0x69, 0x6e, 0x67, 0x52, 0x65, 0x73,
+	0x75, 0x6c, 0x74, 0x22, 0x00, 0x12, 0x41, 0x0a, 0x0d, 0x47, 0x65, 0x6e, 0x65, 0x72, 0x61, 0x74,
+	0x65, 0x49, 0x6d, 0x61, 0x67, 0x65, 0x12, 0x1d, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64,
+	0x2e, 0x47, 0x65, 0x6e, 0x65, 0x72, 0x61, 0x74, 0x65, 0x49, 0x6d, 0x61, 0x67, 0x65, 0x52, 0x65,
+	0x71, 0x75, 0x65, 0x73, 0x74, 0x1a, 0x0f, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e,
+	0x52, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x22, 0x00, 0x12, 0x4d, 0x0a, 0x12, 0x41, 0x75, 0x64, 0x69,
+	0x6f, 0x54, 0x72, 0x61, 0x6e, 0x73, 0x63, 0x72, 0x69, 0x70, 0x74, 0x69, 0x6f, 0x6e, 0x12, 0x1a,
 	0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x54, 0x72, 0x61, 0x6e, 0x73, 0x63, 0x72,
-	0x69, 0x70, 0x74, 0x52, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x22, 0x00, 0x12, 0x2d, 0x0a, 0x03, 0x54,
-	0x54, 0x53, 0x12, 0x13, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x54, 0x54, 0x53,
-	0x52, 0x65, 0x71, 0x75, 0x65, 0x73, 0x74, 0x1a, 0x0f, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e,
-	0x64, 0x2e, 0x52, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x22, 0x00, 0x12, 0x4a, 0x0a, 0x0e, 0x54, 0x6f,
-	0x6b, 0x65, 0x6e, 0x69, 0x7a, 0x65, 0x53, 0x74, 0x72, 0x69, 0x6e, 0x67, 0x12, 0x17, 0x2e, 0x62,
-	0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x50, 0x72, 0x65, 0x64, 0x69, 0x63, 0x74, 0x4f, 0x70,
-	0x74, 0x69, 0x6f, 0x6e, 0x73, 0x1a, 0x1d, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e,
-	0x54, 0x6f, 0x6b, 0x65, 0x6e, 0x69, 0x7a, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x52, 0x65, 0x73, 0x70,
-	0x6f, 0x6e, 0x73, 0x65, 0x22, 0x00, 0x12, 0x3b, 0x0a, 0x06, 0x53, 0x74, 0x61, 0x74, 0x75, 0x73,
-	0x12, 0x16, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x48, 0x65, 0x61, 0x6c, 0x74,
-	0x68, 0x4d, 0x65, 0x73, 0x73, 0x61, 0x67, 0x65, 0x1a, 0x17, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65,
-	0x6e, 0x64, 0x2e, 0x53, 0x74, 0x61, 0x74, 0x75, 0x73, 0x52, 0x65, 0x73, 0x70, 0x6f, 0x6e, 0x73,
-	0x65, 0x22, 0x00, 0x12, 0x39, 0x0a, 0x09, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x53, 0x65, 0x74,
-	0x12, 0x19, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x53, 0x74, 0x6f, 0x72, 0x65,
-	0x73, 0x53, 0x65, 0x74, 0x4f, 0x70, 0x74, 0x69, 0x6f, 0x6e, 0x73, 0x1a, 0x0f, 0x2e, 0x62, 0x61,
-	0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x52, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x22, 0x00, 0x12, 0x3f,
-	0x0a, 0x0c, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x44, 0x65, 0x6c, 0x65, 0x74, 0x65, 0x12, 0x1c,
-	0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x44,
-	0x65, 0x6c, 0x65, 0x74, 0x65, 0x4f, 0x70, 0x74, 0x69, 0x6f, 0x6e, 0x73, 0x1a, 0x0f, 0x2e, 0x62,
-	0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x52, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x22, 0x00, 0x12,
-	0x42, 0x0a, 0x09, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x47, 0x65, 0x74, 0x12, 0x19, 0x2e, 0x62,
-	0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x47, 0x65, 0x74,
-	0x4f, 0x70, 0x74, 0x69, 0x6f, 0x6e, 0x73, 0x1a, 0x18, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e,
-	0x64, 0x2e, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x47, 0x65, 0x74, 0x52, 0x65, 0x73, 0x75, 0x6c,
-	0x74, 0x22, 0x00, 0x12, 0x45, 0x0a, 0x0a, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x46, 0x69, 0x6e,
-	0x64, 0x12, 0x1a, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x53, 0x74, 0x6f, 0x72,
-	0x65, 0x73, 0x46, 0x69, 0x6e, 0x64, 0x4f, 0x70, 0x74, 0x69, 0x6f, 0x6e, 0x73, 0x1a, 0x19, 0x2e,
+	0x69, 0x70, 0x74, 0x52, 0x65, 0x71, 0x75, 0x65, 0x73, 0x74, 0x1a, 0x19, 0x2e, 0x62, 0x61, 0x63,
+	0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x54, 0x72, 0x61, 0x6e, 0x73, 0x63, 0x72, 0x69, 0x70, 0x74, 0x52,
+	0x65, 0x73, 0x75, 0x6c, 0x74, 0x22, 0x00, 0x12, 0x2d, 0x0a, 0x03, 0x54, 0x54, 0x53, 0x12, 0x13,
+	0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x54, 0x54, 0x53, 0x52, 0x65, 0x71, 0x75,
+	0x65, 0x73, 0x74, 0x1a, 0x0f, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x52, 0x65,
+	0x73, 0x75, 0x6c, 0x74, 0x22, 0x00, 0x12, 0x4a, 0x0a, 0x0e, 0x54, 0x6f, 0x6b, 0x65, 0x6e, 0x69,
+	0x7a, 0x65, 0x53, 0x74, 0x72, 0x69, 0x6e, 0x67, 0x12, 0x17, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65,
+	0x6e, 0x64, 0x2e, 0x50, 0x72, 0x65, 0x64, 0x69, 0x63, 0x74, 0x4f, 0x70, 0x74, 0x69, 0x6f, 0x6e,
+	0x73, 0x1a, 0x1d, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x54, 0x6f, 0x6b, 0x65,
+	0x6e, 0x69, 0x7a, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x52, 0x65, 0x73, 0x70, 0x6f, 0x6e, 0x73, 0x65,
+	0x22, 0x00, 0x12, 0x3b, 0x0a, 0x06, 0x53, 0x74, 0x61, 0x74, 0x75, 0x73, 0x12, 0x16, 0x2e, 0x62,
+	0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x48, 0x65, 0x61, 0x6c, 0x74, 0x68, 0x4d, 0x65, 0x73,
+	0x73, 0x61, 0x67, 0x65, 0x1a, 0x17, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x53,
+	0x74, 0x61, 0x74, 0x75, 0x73, 0x52, 0x65, 0x73, 0x70, 0x6f, 0x6e, 0x73, 0x65, 0x22, 0x00, 0x12,
+	0x39, 0x0a, 0x09, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x53, 0x65, 0x74, 0x12, 0x19, 0x2e, 0x62,
+	0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x53, 0x65, 0x74,
+	0x4f, 0x70, 0x74, 0x69, 0x6f, 0x6e, 0x73, 0x1a, 0x0f, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e,
+	0x64, 0x2e, 0x52, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x22, 0x00, 0x12, 0x3f, 0x0a, 0x0c, 0x53, 0x74,
+	0x6f, 0x72, 0x65, 0x73, 0x44, 0x65, 0x6c, 0x65, 0x74, 0x65, 0x12, 0x1c, 0x2e, 0x62, 0x61, 0x63,
+	0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x44, 0x65, 0x6c, 0x65, 0x74,
+	0x65, 0x4f, 0x70, 0x74, 0x69, 0x6f, 0x6e, 0x73, 0x1a, 0x0f, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65,
+	0x6e, 0x64, 0x2e, 0x52, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x22, 0x00, 0x12, 0x42, 0x0a, 0x09, 0x53,
+	0x74, 0x6f, 0x72, 0x65, 0x73, 0x47, 0x65, 0x74, 0x12, 0x19, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65,
+	0x6e, 0x64, 0x2e, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x47, 0x65, 0x74, 0x4f, 0x70, 0x74, 0x69,
+	0x6f, 0x6e, 0x73, 0x1a, 0x18, 0x2e, 0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x53, 0x74,
+	0x6f, 0x72, 0x65, 0x73, 0x47, 0x65, 0x74, 0x52, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x22, 0x00, 0x12,
+	0x45, 0x0a, 0x0a, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x46, 0x69, 0x6e, 0x64, 0x12, 0x1a, 0x2e,
 	0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x2e, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x46, 0x69,
-	0x6e, 0x64, 0x52, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x22, 0x00, 0x42, 0x5a, 0x0a, 0x19, 0x69, 0x6f,
-	0x2e, 0x73, 0x6b, 0x79, 0x6e, 0x65, 0x74, 0x2e, 0x6c, 0x6f, 0x63, 0x61, 0x6c, 0x61, 0x69, 0x2e,
-	0x62, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x42, 0x0e, 0x4c, 0x6f, 0x63, 0x61, 0x6c, 0x41, 0x49,
-	0x42, 0x61, 0x63, 0x6b, 0x65, 0x6e, 0x64, 0x50, 0x01, 0x5a, 0x2b, 0x67, 0x69, 0x74, 0x68, 0x75,
-	0x62, 0x2e, 0x63, 0x6f, 0x6d, 0x2f, 0x67, 0x6f, 0x2d, 0x73, 0x6b, 0x79, 0x6e, 0x65, 0x74, 0x2f,
-	0x4c, 0x6f, 0x63, 0x61, 0x6c, 0x41, 0x49, 0x2f, 0x70, 0x6b, 0x67, 0x2f, 0x67, 0x72, 0x70, 0x63,
-	0x2f, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x62, 0x06, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x33,
+	0x6e, 0x64, 0x4f, 0x70, 0x74, 0x69, 0x6f, 0x6e, 0x73, 0x1a, 0x19, 0x2e, 0x62, 0x61, 0x63, 0x6b,
+	0x65, 0x6e, 0x64, 0x2e, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x73, 0x46, 0x69, 0x6e, 0x64, 0x52, 0x65,
+	0x73, 0x75, 0x6c, 0x74, 0x22, 0x00, 0x42, 0x5a, 0x0a, 0x19, 0x69, 0x6f, 0x2e, 0x73, 0x6b, 0x79,
+	0x6e, 0x65, 0x74, 0x2e, 0x6c, 0x6f, 0x63, 0x61, 0x6c, 0x61, 0x69, 0x2e, 0x62, 0x61, 0x63, 0x6b,
+	0x65, 0x6e, 0x64, 0x42, 0x0e, 0x4c, 0x6f, 0x63, 0x61, 0x6c, 0x41, 0x49, 0x42, 0x61, 0x63, 0x6b,
+	0x65, 0x6e, 0x64, 0x50, 0x01, 0x5a, 0x2b, 0x67, 0x69, 0x74, 0x68, 0x75, 0x62, 0x2e, 0x63, 0x6f,
+	0x6d, 0x2f, 0x67, 0x6f, 0x2d, 0x73, 0x6b, 0x79, 0x6e, 0x65, 0x74, 0x2f, 0x4c, 0x6f, 0x63, 0x61,
+	0x6c, 0x41, 0x49, 0x2f, 0x70, 0x6b, 0x67, 0x2f, 0x67, 0x72, 0x70, 0x63, 0x2f, 0x70, 0x72, 0x6f,
+	0x74, 0x6f, 0x62, 0x06, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x33,
 }
 
 var (
@@ -2470,7 +2555,7 @@ func file_backend_proto_rawDescGZIP() []byte {
 }
 
 var file_backend_proto_enumTypes = make([]protoimpl.EnumInfo, 1)
-var file_backend_proto_msgTypes = make([]protoimpl.MessageInfo, 23)
+var file_backend_proto_msgTypes = make([]protoimpl.MessageInfo, 24)
 var file_backend_proto_goTypes = []interface{}{
 	(StatusResponse_State)(0),    // 0: backend.StatusResponse.State
 	(*StoresKey)(nil),            // 1: backend.StoresKey
@@ -2495,7 +2580,9 @@ var file_backend_proto_goTypes = []interface{}{
 	(*TokenizationResponse)(nil), // 20: backend.TokenizationResponse
 	(*MemoryUsageData)(nil),      // 21: backend.MemoryUsageData
 	(*StatusResponse)(nil),       // 22: backend.StatusResponse
-	nil,                          // 23: backend.MemoryUsageData.BreakdownEntry
+	(*Message)(nil),              // 23: backend.Message
+	nil,                          // 24: backend.MemoryUsageData.BreakdownEntry
+	(*anypb.Any)(nil),            // 25: google.protobuf.Any
 }
 var file_backend_proto_depIdxs = []int32{
 	1,  // 0: backend.StoresSetOptions.Keys:type_name -> backend.StoresKey
@@ -2507,43 +2594,45 @@ var file_backend_proto_depIdxs = []int32{
 	1,  // 6: backend.StoresFindOptions.Key:type_name -> backend.StoresKey
 	1,  // 7: backend.StoresFindResult.Keys:type_name -> backend.StoresKey
 	2,  // 8: backend.StoresFindResult.Values:type_name -> backend.StoresValue
-	17, // 9: backend.TranscriptResult.segments:type_name -> backend.TranscriptSegment
-	23, // 10: backend.MemoryUsageData.breakdown:type_name -> backend.MemoryUsageData.BreakdownEntry
-	0,  // 11: backend.StatusResponse.state:type_name -> backend.StatusResponse.State
-	21, // 12: backend.StatusResponse.memory:type_name -> backend.MemoryUsageData
-	9,  // 13: backend.Backend.Health:input_type -> backend.HealthMessage
-	10, // 14: backend.Backend.Predict:input_type -> backend.PredictOptions
-	12, // 15: backend.Backend.LoadModel:input_type -> backend.ModelOptions
-	10, // 16: backend.Backend.PredictStream:input_type -> backend.PredictOptions
-	10, // 17: backend.Backend.Embedding:input_type -> backend.PredictOptions
-	18, // 18: backend.Backend.GenerateImage:input_type -> backend.GenerateImageRequest
-	15, // 19: backend.Backend.AudioTranscription:input_type -> backend.TranscriptRequest
-	19, // 20: backend.Backend.TTS:input_type -> backend.TTSRequest
-	10, // 21: backend.Backend.TokenizeString:input_type -> backend.PredictOptions
-	9,  // 22: backend.Backend.Status:input_type -> backend.HealthMessage
-	3,  // 23: backend.Backend.StoresSet:input_type -> backend.StoresSetOptions
-	4,  // 24: backend.Backend.StoresDelete:input_type -> backend.StoresDeleteOptions
-	5,  // 25: backend.Backend.StoresGet:input_type -> backend.StoresGetOptions
-	7,  // 26: backend.Backend.StoresFind:input_type -> backend.StoresFindOptions
-	11, // 27: backend.Backend.Health:output_type -> backend.Reply
-	11, // 28: backend.Backend.Predict:output_type -> backend.Reply
-	13, // 29: backend.Backend.LoadModel:output_type -> backend.Result
-	11, // 30: backend.Backend.PredictStream:output_type -> backend.Reply
-	14, // 31: backend.Backend.Embedding:output_type -> backend.EmbeddingResult
-	13, // 32: backend.Backend.GenerateImage:output_type -> backend.Result
-	16, // 33: backend.Backend.AudioTranscription:output_type -> backend.TranscriptResult
-	13, // 34: backend.Backend.TTS:output_type -> backend.Result
-	20, // 35: backend.Backend.TokenizeString:output_type -> backend.TokenizationResponse
-	22, // 36: backend.Backend.Status:output_type -> backend.StatusResponse
-	13, // 37: backend.Backend.StoresSet:output_type -> backend.Result
-	13, // 38: backend.Backend.StoresDelete:output_type -> backend.Result
-	6,  // 39: backend.Backend.StoresGet:output_type -> backend.StoresGetResult
-	8,  // 40: backend.Backend.StoresFind:output_type -> backend.StoresFindResult
-	27, // [27:41] is the sub-list for method output_type
-	13, // [13:27] is the sub-list for method input_type
-	13, // [13:13] is the sub-list for extension type_name
-	13, // [13:13] is the sub-list for extension extendee
-	0,  // [0:13] is the sub-list for field type_name
+	23, // 9: backend.PredictOptions.Messages:type_name -> backend.Message
+	17, // 10: backend.TranscriptResult.segments:type_name -> backend.TranscriptSegment
+	24, // 11: backend.MemoryUsageData.breakdown:type_name -> backend.MemoryUsageData.BreakdownEntry
+	0,  // 12: backend.StatusResponse.state:type_name -> backend.StatusResponse.State
+	21, // 13: backend.StatusResponse.memory:type_name -> backend.MemoryUsageData
+	25, // 14: backend.Message.Content:type_name -> google.protobuf.Any
+	9,  // 15: backend.Backend.Health:input_type -> backend.HealthMessage
+	10, // 16: backend.Backend.Predict:input_type -> backend.PredictOptions
+	12, // 17: backend.Backend.LoadModel:input_type -> backend.ModelOptions
+	10, // 18: backend.Backend.PredictStream:input_type -> backend.PredictOptions
+	10, // 19: backend.Backend.Embedding:input_type -> backend.PredictOptions
+	18, // 20: backend.Backend.GenerateImage:input_type -> backend.GenerateImageRequest
+	15, // 21: backend.Backend.AudioTranscription:input_type -> backend.TranscriptRequest
+	19, // 22: backend.Backend.TTS:input_type -> backend.TTSRequest
+	10, // 23: backend.Backend.TokenizeString:input_type -> backend.PredictOptions
+	9,  // 24: backend.Backend.Status:input_type -> backend.HealthMessage
+	3,  // 25: backend.Backend.StoresSet:input_type -> backend.StoresSetOptions
+	4,  // 26: backend.Backend.StoresDelete:input_type -> backend.StoresDeleteOptions
+	5,  // 27: backend.Backend.StoresGet:input_type -> backend.StoresGetOptions
+	7,  // 28: backend.Backend.StoresFind:input_type -> backend.StoresFindOptions
+	11, // 29: backend.Backend.Health:output_type -> backend.Reply
+	11, // 30: backend.Backend.Predict:output_type -> backend.Reply
+	13, // 31: backend.Backend.LoadModel:output_type -> backend.Result
+	11, // 32: backend.Backend.PredictStream:output_type -> backend.Reply
+	14, // 33: backend.Backend.Embedding:output_type -> backend.EmbeddingResult
+	13, // 34: backend.Backend.GenerateImage:output_type -> backend.Result
+	16, // 35: backend.Backend.AudioTranscription:output_type -> backend.TranscriptResult
+	13, // 36: backend.Backend.TTS:output_type -> backend.Result
+	20, // 37: backend.Backend.TokenizeString:output_type -> backend.TokenizationResponse
+	22, // 38: backend.Backend.Status:output_type -> backend.StatusResponse
+	13, // 39: backend.Backend.StoresSet:output_type -> backend.Result
+	13, // 40: backend.Backend.StoresDelete:output_type -> backend.Result
+	6,  // 41: backend.Backend.StoresGet:output_type -> backend.StoresGetResult
+	8,  // 42: backend.Backend.StoresFind:output_type -> backend.StoresFindResult
+	29, // [29:43] is the sub-list for method output_type
+	15, // [15:29] is the sub-list for method input_type
+	15, // [15:15] is the sub-list for extension type_name
+	15, // [15:15] is the sub-list for extension extendee
+	0,  // [0:15] is the sub-list for field type_name
 }
 
 func init() { file_backend_proto_init() }
@@ -2816,6 +2905,18 @@ func file_backend_proto_init() {
 				return nil
 			}
 		}
+		file_backend_proto_msgTypes[22].Exporter = func(v interface{}, i int) interface{} {
+			switch v := v.(*Message); i {
+			case 0:
+				return &v.state
+			case 1:
+				return &v.sizeCache
+			case 2:
+				return &v.unknownFields
+			default:
+				return nil
+			}
+		}
 	}
 	type x struct{}
 	out := protoimpl.TypeBuilder{
@@ -2823,7 +2924,7 @@ func file_backend_proto_init() {
 			GoPackagePath: reflect.TypeOf(x{}).PkgPath(),
 			RawDescriptor: file_backend_proto_rawDesc,
 			NumEnums:      1,
-			NumMessages:   23,
+			NumMessages:   24,
 			NumExtensions: 0,
 			NumServices:   1,
 		},
diff --git a/pkg/grpc/proto/backend_grpc.pb.go b/pkg/grpc/proto/backend_grpc.pb.go
index 0314cd4ea8eb..a1f442e01ffe 100644
--- a/pkg/grpc/proto/backend_grpc.pb.go
+++ b/pkg/grpc/proto/backend_grpc.pb.go
@@ -1,7 +1,7 @@
 // Code generated by protoc-gen-go-grpc. DO NOT EDIT.
 // versions:
 // - protoc-gen-go-grpc v1.3.0
-// - protoc             v4.23.4
+// - protoc             v5.26.1
 // source: backend.proto
 
 package proto