diff --git a/docs/openapi_generator/generate.py b/docs/openapi_generator/generate.py index 3827311dec..1a59369cbb 100644 --- a/docs/openapi_generator/generate.py +++ b/docs/openapi_generator/generate.py @@ -14,7 +14,7 @@ from pathlib import Path import fire -import yaml +import ruamel.yaml as yaml from llama_models import schema_utils @@ -61,7 +61,19 @@ def main(output_dir: str): ) with open(output_dir / "llama-stack-spec.yaml", "w", encoding="utf-8") as fp: - yaml.dump(spec.get_json(), fp, allow_unicode=True) + y = yaml.YAML() + y.default_flow_style = False + y.block_seq_indent = 2 + y.map_indent = 2 + y.sequence_indent = 4 + y.sequence_dash_offset = 2 + y.width = 80 + y.allow_unicode = True + y.explicit_start = True + y.dump( + spec.get_json(), + fp, + ) with open(output_dir / "llama-stack-spec.html", "w") as fp: spec.write_html(fp, pretty_print=True) diff --git a/docs/openapi_generator/pyopenapi/generator.py b/docs/openapi_generator/pyopenapi/generator.py index 25b08f0711..d7e49fd314 100644 --- a/docs/openapi_generator/pyopenapi/generator.py +++ b/docs/openapi_generator/pyopenapi/generator.py @@ -403,14 +403,16 @@ def __init__(self, endpoint: type, options: Options) -> None: self.responses = {} def _build_type_tag(self, ref: str, schema: Schema) -> Tag: - definition = f'' + # Don't include schema definition in the tag description because for one, + # it is not very valuable and for another, it causes string formatting + # discrepancies via the Stainless Studio. + # + # definition = f'' title = typing.cast(str, schema.get("title")) description = typing.cast(str, schema.get("description")) return Tag( name=ref, - description="\n\n".join( - s for s in (title, description, definition) if s is not None - ), + description="\n\n".join(s for s in (title, description) if s is not None), ) def _build_extra_tag_groups( diff --git a/docs/resources/llama-stack-spec.html b/docs/resources/llama-stack-spec.html index 7108ee9a5b..2929972e8e 100644 --- a/docs/resources/llama-stack-spec.html +++ b/docs/resources/llama-stack-spec.html @@ -4781,6 +4781,9 @@ }, "enable_session_persistence": { "type": "boolean" + }, + "response_format": { + "$ref": "#/components/schemas/ResponseFormat" } }, "additionalProperties": false, @@ -9102,205 +9105,205 @@ "tags": [ { "name": "AgentCandidate", - "description": "" + "description": "" }, { "name": "AgentConfig", - "description": "" + "description": "" }, { "name": "AgentCreateResponse", - "description": "" + "description": "" }, { "name": "AgentSessionCreateResponse", - "description": "" + "description": "" }, { "name": "AgentStepResponse", - "description": "" + "description": "" }, { "name": "AgentTool", - "description": "" + "description": "" }, { "name": "AgentTurnInputType", - "description": "" + "description": "" }, { "name": "AgentTurnResponseEvent", - "description": "" + "description": "" }, { "name": "AgentTurnResponseEventPayload", - "description": "" + "description": "" }, { "name": "AgentTurnResponseStepCompletePayload", - "description": "" + "description": "" }, { "name": "AgentTurnResponseStepProgressPayload", - "description": "" + "description": "" }, { "name": "AgentTurnResponseStepStartPayload", - "description": "" + "description": "" }, { "name": "AgentTurnResponseStreamChunk", - "description": "streamed agent turn completion response.\n\n" + "description": "streamed agent turn completion response." }, { "name": "AgentTurnResponseTurnCompletePayload", - "description": "" + "description": "" }, { "name": "AgentTurnResponseTurnStartPayload", - "description": "" + "description": "" }, { "name": "Agents" }, { "name": "AggregationFunctionType", - "description": "" + "description": "" }, { "name": "AlgorithmConfig", - "description": "" + "description": "" }, { "name": "AppEvalTaskConfig", - "description": "" + "description": "" }, { "name": "AppendRowsRequest", - "description": "" + "description": "" }, { "name": "ArrayType", - "description": "" + "description": "" }, { "name": "BasicScoringFnParams", - "description": "" + "description": "" }, { "name": "BatchChatCompletionRequest", - "description": "" + "description": "" }, { "name": "BatchChatCompletionResponse", - "description": "" + "description": "" }, { "name": "BatchCompletionRequest", - "description": "" + "description": "" }, { "name": "BatchCompletionResponse", - "description": "" + "description": "" }, { "name": "BatchInference (Coming Soon)" }, { "name": "BenchmarkEvalTaskConfig", - "description": "" + "description": "" }, { "name": "BooleanType", - "description": "" + "description": "" }, { "name": "BuiltinTool", - "description": "" + "description": "" }, { "name": "CancelTrainingJobRequest", - "description": "" + "description": "" }, { "name": "ChatCompletionInputType", - "description": "" + "description": "" }, { "name": "ChatCompletionRequest", - "description": "" + "description": "" }, { "name": "ChatCompletionResponse", - "description": "Chat completion response.\n\n" + "description": "Chat completion response." }, { "name": "ChatCompletionResponseEvent", - "description": "Chat completion response event.\n\n" + "description": "Chat completion response event." }, { "name": "ChatCompletionResponseEventType", - "description": "" + "description": "" }, { "name": "ChatCompletionResponseStreamChunk", - "description": "SSE-stream of these events.\n\n" + "description": "SSE-stream of these events." }, { "name": "Checkpoint", - "description": "Checkpoint created during training runs\n\n" + "description": "Checkpoint created during training runs" }, { "name": "CompletionInputType", - "description": "" + "description": "" }, { "name": "CompletionMessage", - "description": "" + "description": "" }, { "name": "CompletionRequest", - "description": "" + "description": "" }, { "name": "CompletionResponse", - "description": "Completion response.\n\n" + "description": "Completion response." }, { "name": "CompletionResponseStreamChunk", - "description": "streamed completion response.\n\n" + "description": "streamed completion response." }, { "name": "ContentDelta", - "description": "" + "description": "" }, { "name": "CreateAgentRequest", - "description": "" + "description": "" }, { "name": "CreateAgentSessionRequest", - "description": "" + "description": "" }, { "name": "CreateAgentTurnRequest", - "description": "" + "description": "" }, { "name": "DPOAlignmentConfig", - "description": "" + "description": "" }, { "name": "DataConfig", - "description": "" + "description": "" }, { "name": "Dataset", - "description": "" + "description": "" }, { "name": "DatasetFormat", - "description": "" + "description": "" }, { "name": "DatasetIO" @@ -9310,601 +9313,601 @@ }, { "name": "DefaultRAGQueryGeneratorConfig", - "description": "" + "description": "" }, { "name": "EfficiencyConfig", - "description": "" + "description": "" }, { "name": "EmbeddingsRequest", - "description": "" + "description": "" }, { "name": "EmbeddingsResponse", - "description": "" + "description": "" }, { "name": "Eval" }, { "name": "EvalCandidate", - "description": "" + "description": "" }, { "name": "EvalTask", - "description": "" + "description": "" }, { "name": "EvalTaskConfig", - "description": "" + "description": "" }, { "name": "EvalTasks" }, { "name": "EvaluateResponse", - "description": "" + "description": "" }, { "name": "EvaluateRowsRequest", - "description": "" + "description": "" }, { "name": "Event", - "description": "" + "description": "" }, { "name": "GrammarResponseFormat", - "description": "" + "description": "" }, { "name": "GreedySamplingStrategy", - "description": "" + "description": "" }, { "name": "HealthInfo", - "description": "" + "description": "" }, { "name": "ImageContentItem", - "description": "" + "description": "" }, { "name": "ImageDelta", - "description": "" + "description": "" }, { "name": "Inference" }, { "name": "InferenceStep", - "description": "" + "description": "" }, { "name": "InsertChunksRequest", - "description": "" + "description": "" }, { "name": "InsertRequest", - "description": "" + "description": "" }, { "name": "Inspect" }, { "name": "InterleavedContent", - "description": "" + "description": "" }, { "name": "InterleavedContentItem", - "description": "" + "description": "" }, { "name": "InvokeToolRequest", - "description": "" + "description": "" }, { "name": "Job", - "description": "" + "description": "" }, { "name": "JobStatus", - "description": "" + "description": "" }, { "name": "JsonSchemaResponseFormat", - "description": "" + "description": "" }, { "name": "JsonType", - "description": "" + "description": "" }, { "name": "LLMAsJudgeScoringFnParams", - "description": "" + "description": "" }, { "name": "LLMRAGQueryGeneratorConfig", - "description": "" + "description": "" }, { "name": "ListDatasetsResponse", - "description": "" + "description": "" }, { "name": "ListEvalTasksResponse", - "description": "" + "description": "" }, { "name": "ListModelsResponse", - "description": "" + "description": "" }, { "name": "ListPostTrainingJobsResponse", - "description": "" + "description": "" }, { "name": "ListProvidersResponse", - "description": "" + "description": "" }, { "name": "ListRoutesResponse", - "description": "" + "description": "" }, { "name": "ListScoringFunctionsResponse", - "description": "" + "description": "" }, { "name": "ListShieldsResponse", - "description": "" + "description": "" }, { "name": "ListToolGroupsResponse", - "description": "" + "description": "" }, { "name": "ListToolsResponse", - "description": "" + "description": "" }, { "name": "ListVectorDBsResponse", - "description": "" + "description": "" }, { "name": "LogEventRequest", - "description": "" + "description": "" }, { "name": "LogSeverity", - "description": "" + "description": "" }, { "name": "LoraFinetuningConfig", - "description": "" + "description": "" }, { "name": "MemoryRetrievalStep", - "description": "" + "description": "" }, { "name": "Message", - "description": "" + "description": "" }, { "name": "MetricEvent", - "description": "" + "description": "" }, { "name": "Model", - "description": "" + "description": "" }, { "name": "ModelCandidate", - "description": "" + "description": "" }, { "name": "ModelType", - "description": "" + "description": "" }, { "name": "Models" }, { "name": "NumberType", - "description": "" + "description": "" }, { "name": "ObjectType", - "description": "" + "description": "" }, { "name": "OptimizerConfig", - "description": "" + "description": "" }, { "name": "OptimizerType", - "description": "" + "description": "" }, { "name": "PaginatedRowsResult", - "description": "" + "description": "" }, { "name": "ParamType", - "description": "" + "description": "" }, { "name": "PostTraining (Coming Soon)" }, { "name": "PostTrainingJob", - "description": "" + "description": "" }, { "name": "PostTrainingJobArtifactsResponse", - "description": "Artifacts of a finetuning job.\n\n" + "description": "Artifacts of a finetuning job." }, { "name": "PostTrainingJobStatusResponse", - "description": "Status of a finetuning job.\n\n" + "description": "Status of a finetuning job." }, { "name": "PreferenceOptimizeRequest", - "description": "" + "description": "" }, { "name": "ProviderInfo", - "description": "" + "description": "" }, { "name": "QATFinetuningConfig", - "description": "" + "description": "" }, { "name": "QueryChunksRequest", - "description": "" + "description": "" }, { "name": "QueryChunksResponse", - "description": "" + "description": "" }, { "name": "QueryCondition", - "description": "" + "description": "" }, { "name": "QueryConditionOp", - "description": "" + "description": "" }, { "name": "QueryRequest", - "description": "" + "description": "" }, { "name": "QuerySpanTreeResponse", - "description": "" + "description": "" }, { "name": "QuerySpansResponse", - "description": "" + "description": "" }, { "name": "QueryTracesResponse", - "description": "" + "description": "" }, { "name": "RAGDocument", - "description": "" + "description": "" }, { "name": "RAGQueryConfig", - "description": "" + "description": "" }, { "name": "RAGQueryGeneratorConfig", - "description": "" + "description": "" }, { "name": "RAGQueryResult", - "description": "" + "description": "" }, { "name": "RegexParserScoringFnParams", - "description": "" + "description": "" }, { "name": "RegisterDatasetRequest", - "description": "" + "description": "" }, { "name": "RegisterEvalTaskRequest", - "description": "" + "description": "" }, { "name": "RegisterModelRequest", - "description": "" + "description": "" }, { "name": "RegisterScoringFunctionRequest", - "description": "" + "description": "" }, { "name": "RegisterShieldRequest", - "description": "" + "description": "" }, { "name": "RegisterToolGroupRequest", - "description": "" + "description": "" }, { "name": "RegisterVectorDbRequest", - "description": "" + "description": "" }, { "name": "ResponseFormat", - "description": "" + "description": "" }, { "name": "RouteInfo", - "description": "" + "description": "" }, { "name": "RunEvalRequest", - "description": "" + "description": "" }, { "name": "RunShieldRequest", - "description": "" + "description": "" }, { "name": "RunShieldResponse", - "description": "" + "description": "" }, { "name": "Safety" }, { "name": "SafetyViolation", - "description": "" + "description": "" }, { "name": "SamplingParams", - "description": "" + "description": "" }, { "name": "SaveSpansToDatasetRequest", - "description": "" + "description": "" }, { "name": "ScoreBatchRequest", - "description": "" + "description": "" }, { "name": "ScoreBatchResponse", - "description": "" + "description": "" }, { "name": "ScoreRequest", - "description": "" + "description": "" }, { "name": "ScoreResponse", - "description": "" + "description": "" }, { "name": "Scoring" }, { "name": "ScoringFn", - "description": "" + "description": "" }, { "name": "ScoringFnParams", - "description": "" + "description": "" }, { "name": "ScoringFunctions" }, { "name": "ScoringResult", - "description": "" + "description": "" }, { "name": "Session", - "description": "A single session of an interaction with an Agentic System.\n\n" + "description": "A single session of an interaction with an Agentic System." }, { "name": "Shield", - "description": "A safety shield resource that can be used to check content\n\n" + "description": "A safety shield resource that can be used to check content" }, { "name": "ShieldCallStep", - "description": "" + "description": "" }, { "name": "Shields" }, { "name": "Span", - "description": "" + "description": "" }, { "name": "SpanEndPayload", - "description": "" + "description": "" }, { "name": "SpanStartPayload", - "description": "" + "description": "" }, { "name": "SpanStatus", - "description": "" + "description": "" }, { "name": "SpanWithStatus", - "description": "" + "description": "" }, { "name": "StopReason", - "description": "" + "description": "" }, { "name": "StringType", - "description": "" + "description": "" }, { "name": "StructuredLogEvent", - "description": "" + "description": "" }, { "name": "StructuredLogPayload", - "description": "" + "description": "" }, { "name": "SupervisedFineTuneRequest", - "description": "" + "description": "" }, { "name": "SyntheticDataGenerateRequest", - "description": "" + "description": "" }, { "name": "SyntheticDataGeneration (Coming Soon)" }, { "name": "SyntheticDataGenerationResponse", - "description": "Response from the synthetic data generation. Batch of (prompt, response, score) tuples that pass the threshold.\n\n" + "description": "Response from the synthetic data generation. Batch of (prompt, response, score) tuples that pass the threshold." }, { "name": "SystemMessage", - "description": "" + "description": "" }, { "name": "Telemetry" }, { "name": "TextContentItem", - "description": "" + "description": "" }, { "name": "TextDelta", - "description": "" + "description": "" }, { "name": "TokenLogProbs", - "description": "" + "description": "" }, { "name": "Tool", - "description": "" + "description": "" }, { "name": "ToolCall", - "description": "" + "description": "" }, { "name": "ToolCallDelta", - "description": "" + "description": "" }, { "name": "ToolCallParseStatus", - "description": "" + "description": "" }, { "name": "ToolChoice", - "description": "" + "description": "" }, { "name": "ToolDef", - "description": "" + "description": "" }, { "name": "ToolDefinition", - "description": "" + "description": "" }, { "name": "ToolExecutionStep", - "description": "" + "description": "" }, { "name": "ToolGroup", - "description": "" + "description": "" }, { "name": "ToolGroups" }, { "name": "ToolHost", - "description": "" + "description": "" }, { "name": "ToolInvocationResult", - "description": "" + "description": "" }, { "name": "ToolParamDefinition", - "description": "" + "description": "" }, { "name": "ToolParameter", - "description": "" + "description": "" }, { "name": "ToolPromptFormat", - "description": "This Enum refers to the prompt format for calling custom / zero shot tools\n\n`json` --\n Refers to the json format for calling tools.\n The json format takes the form like\n {\n \"type\": \"function\",\n \"function\" : {\n \"name\": \"function_name\",\n \"description\": \"function_description\",\n \"parameters\": {...}\n }\n }\n\n`function_tag` --\n This is an example of how you could define\n your own user defined format for making tool calls.\n The function_tag format looks like this,\n (parameters)\n\nThe detailed prompts for each of these formats are added to llama cli\n\n" + "description": "This Enum refers to the prompt format for calling custom / zero shot tools\n\n`json` --\n Refers to the json format for calling tools.\n The json format takes the form like\n {\n \"type\": \"function\",\n \"function\" : {\n \"name\": \"function_name\",\n \"description\": \"function_description\",\n \"parameters\": {...}\n }\n }\n\n`function_tag` --\n This is an example of how you could define\n your own user defined format for making tool calls.\n The function_tag format looks like this,\n (parameters)\n\nThe detailed prompts for each of these formats are added to llama cli" }, { "name": "ToolResponse", - "description": "" + "description": "" }, { "name": "ToolResponseMessage", - "description": "" + "description": "" }, { "name": "ToolRuntime" }, { "name": "TopKSamplingStrategy", - "description": "" + "description": "" }, { "name": "TopPSamplingStrategy", - "description": "" + "description": "" }, { "name": "Trace", - "description": "" + "description": "" }, { "name": "TrainingConfig", - "description": "" + "description": "" }, { "name": "Turn", - "description": "A single turn in an interaction with an Agentic System.\n\n" + "description": "A single turn in an interaction with an Agentic System." }, { "name": "URL", - "description": "" + "description": "" }, { "name": "UnionType", - "description": "" + "description": "" }, { "name": "UnstructuredLogEvent", - "description": "" + "description": "" }, { "name": "UserMessage", - "description": "" + "description": "" }, { "name": "VectorDB", - "description": "" + "description": "" }, { "name": "VectorDBs" @@ -9914,11 +9917,11 @@ }, { "name": "VersionInfo", - "description": "" + "description": "" }, { "name": "ViolationLevel", - "description": "" + "description": "" } ], "x-tagGroups": [ diff --git a/docs/resources/llama-stack-spec.yaml b/docs/resources/llama-stack-spec.yaml index a7095716cf..2b11c15370 100644 --- a/docs/resources/llama-stack-spec.yaml +++ b/docs/resources/llama-stack-spec.yaml @@ -1,6507 +1,6360 @@ -components: - responses: {} - schemas: - AgentCandidate: - additionalProperties: false - properties: - config: - $ref: '#/components/schemas/AgentConfig' - type: - const: agent - default: agent - type: string - required: - - type - - config - type: object - AgentConfig: - additionalProperties: false - properties: - client_tools: - items: - $ref: '#/components/schemas/ToolDef' - type: array - enable_session_persistence: - type: boolean - input_shields: - items: +--- +openapi: 3.1.0 +info: + title: Llama Stack Specification + version: v1 + description: "This is the specification of the Llama Stack that provides\n \ + \ a set of endpoints and their corresponding interfaces that are tailored + to\n best leverage Llama Models." +servers: + - url: http://any-hosted-llama-stack.com +paths: + /v1/datasetio/rows: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/PaginatedRowsResult' + tags: + - DatasetIO + parameters: + - name: dataset_id + in: query + required: true + schema: type: string - type: array - instructions: - type: string - max_infer_iters: - default: 10 - type: integer - model: - type: string - output_shields: - items: + - name: rows_in_page + in: query + required: true + schema: + type: integer + - name: page_token + in: query + required: false + schema: type: string - type: array - sampling_params: - $ref: '#/components/schemas/SamplingParams' - tool_choice: - $ref: '#/components/schemas/ToolChoice' - default: auto - tool_prompt_format: - $ref: '#/components/schemas/ToolPromptFormat' - toolgroups: - items: - $ref: '#/components/schemas/AgentTool' - type: array - required: - - max_infer_iters - - model - - instructions - - enable_session_persistence - type: object - AgentCreateResponse: - additionalProperties: false - properties: - agent_id: - type: string - required: - - agent_id - type: object - AgentSessionCreateResponse: - additionalProperties: false - properties: - session_id: - type: string - required: - - session_id - type: object - AgentStepResponse: - additionalProperties: false - properties: - step: - discriminator: - mapping: - inference: '#/components/schemas/InferenceStep' - memory_retrieval: '#/components/schemas/MemoryRetrievalStep' - shield_call: '#/components/schemas/ShieldCallStep' - tool_execution: '#/components/schemas/ToolExecutionStep' - propertyName: step_type - oneOf: - - $ref: '#/components/schemas/InferenceStep' - - $ref: '#/components/schemas/ToolExecutionStep' - - $ref: '#/components/schemas/ShieldCallStep' - - $ref: '#/components/schemas/MemoryRetrievalStep' - required: - - step - type: object - AgentTool: - oneOf: - - type: string - - additionalProperties: false - properties: - args: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - name: + - name: filter_condition + in: query + required: false + schema: type: string - required: - - name - - args - type: object - AgentTurnInputType: - additionalProperties: false - properties: - type: - const: agent_turn_input - default: agent_turn_input - type: string - required: - - type - type: object - AgentTurnResponseEvent: - additionalProperties: false - properties: - payload: - $ref: '#/components/schemas/AgentTurnResponseEventPayload' - required: - - payload - type: object - AgentTurnResponseEventPayload: - discriminator: - mapping: - step_complete: '#/components/schemas/AgentTurnResponseStepCompletePayload' - step_progress: '#/components/schemas/AgentTurnResponseStepProgressPayload' - step_start: '#/components/schemas/AgentTurnResponseStepStartPayload' - turn_complete: '#/components/schemas/AgentTurnResponseTurnCompletePayload' - turn_start: '#/components/schemas/AgentTurnResponseTurnStartPayload' - propertyName: event_type - oneOf: - - $ref: '#/components/schemas/AgentTurnResponseStepStartPayload' - - $ref: '#/components/schemas/AgentTurnResponseStepProgressPayload' - - $ref: '#/components/schemas/AgentTurnResponseStepCompletePayload' - - $ref: '#/components/schemas/AgentTurnResponseTurnStartPayload' - - $ref: '#/components/schemas/AgentTurnResponseTurnCompletePayload' - AgentTurnResponseStepCompletePayload: - additionalProperties: false - properties: - event_type: - const: step_complete - default: step_complete - type: string - step_details: - discriminator: - mapping: - inference: '#/components/schemas/InferenceStep' - memory_retrieval: '#/components/schemas/MemoryRetrievalStep' - shield_call: '#/components/schemas/ShieldCallStep' - tool_execution: '#/components/schemas/ToolExecutionStep' - propertyName: step_type - oneOf: - - $ref: '#/components/schemas/InferenceStep' - - $ref: '#/components/schemas/ToolExecutionStep' - - $ref: '#/components/schemas/ShieldCallStep' - - $ref: '#/components/schemas/MemoryRetrievalStep' - step_id: - type: string - step_type: - enum: - - inference - - tool_execution - - shield_call - - memory_retrieval - type: string - required: - - event_type - - step_type - - step_id - - step_details - type: object - AgentTurnResponseStepProgressPayload: - additionalProperties: false - properties: - delta: - $ref: '#/components/schemas/ContentDelta' - event_type: - const: step_progress - default: step_progress - type: string - step_id: - type: string - step_type: - enum: - - inference - - tool_execution - - shield_call - - memory_retrieval - type: string - required: - - event_type - - step_type - - step_id - - delta - type: object - AgentTurnResponseStepStartPayload: - additionalProperties: false - properties: - event_type: - const: step_start - default: step_start - type: string - metadata: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - step_id: - type: string - step_type: - enum: - - inference - - tool_execution - - shield_call - - memory_retrieval - type: string - required: - - event_type - - step_type - - step_id - type: object - AgentTurnResponseStreamChunk: - additionalProperties: false - properties: - event: - $ref: '#/components/schemas/AgentTurnResponseEvent' - required: - - event - title: streamed agent turn completion response. - type: object - AgentTurnResponseTurnCompletePayload: - additionalProperties: false - properties: - event_type: - const: turn_complete - default: turn_complete - type: string - turn: - $ref: '#/components/schemas/Turn' - required: - - event_type - - turn - type: object - AgentTurnResponseTurnStartPayload: - additionalProperties: false - properties: - event_type: - const: turn_start - default: turn_start - type: string - turn_id: - type: string - required: - - event_type - - turn_id - type: object - AggregationFunctionType: - enum: - - average - - median - - categorical_count - - accuracy - type: string - AlgorithmConfig: - discriminator: - mapping: - LoRA: '#/components/schemas/LoraFinetuningConfig' - QAT: '#/components/schemas/QATFinetuningConfig' - propertyName: type - oneOf: - - $ref: '#/components/schemas/LoraFinetuningConfig' - - $ref: '#/components/schemas/QATFinetuningConfig' - AppEvalTaskConfig: - additionalProperties: false - properties: - eval_candidate: - $ref: '#/components/schemas/EvalCandidate' - num_examples: - type: integer - scoring_params: - additionalProperties: - $ref: '#/components/schemas/ScoringFnParams' - type: object - type: - const: app - default: app - type: string - required: - - type - - eval_candidate - - scoring_params - type: object - AppendRowsRequest: - additionalProperties: false - properties: - dataset_id: - type: string - rows: - items: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - type: array - required: - - dataset_id - - rows - type: object - ArrayType: - additionalProperties: false - properties: - type: - const: array - default: array - type: string - required: - - type - type: object - BasicScoringFnParams: - additionalProperties: false - properties: - aggregation_functions: - items: - $ref: '#/components/schemas/AggregationFunctionType' - type: array - type: - const: basic - default: basic - type: string - required: - - type - type: object - BatchChatCompletionRequest: - additionalProperties: false - properties: - logprobs: - additionalProperties: false - properties: - top_k: - default: 0 - type: integer - type: object - messages_batch: - items: - items: - $ref: '#/components/schemas/Message' - type: array - type: array - model: - type: string - sampling_params: - $ref: '#/components/schemas/SamplingParams' - tool_choice: - $ref: '#/components/schemas/ToolChoice' - tool_prompt_format: - $ref: '#/components/schemas/ToolPromptFormat' - tools: - items: - $ref: '#/components/schemas/ToolDefinition' - type: array - required: - - model - - messages_batch - type: object - BatchChatCompletionResponse: - additionalProperties: false - properties: - completion_message_batch: - items: - $ref: '#/components/schemas/CompletionMessage' - type: array - required: - - completion_message_batch - type: object - BatchCompletionRequest: - additionalProperties: false - properties: - content_batch: - items: - $ref: '#/components/schemas/InterleavedContent' - type: array - logprobs: - additionalProperties: false - properties: - top_k: - default: 0 - type: integer - type: object - model: - type: string - sampling_params: - $ref: '#/components/schemas/SamplingParams' - required: - - model - - content_batch - type: object - BatchCompletionResponse: - additionalProperties: false - properties: - completion_message_batch: - items: - $ref: '#/components/schemas/CompletionMessage' - type: array - required: - - completion_message_batch - type: object - BenchmarkEvalTaskConfig: - additionalProperties: false - properties: - eval_candidate: - $ref: '#/components/schemas/EvalCandidate' - num_examples: - type: integer - type: - const: benchmark - default: benchmark - type: string - required: - - type - - eval_candidate - type: object - BooleanType: - additionalProperties: false - properties: - type: - const: boolean - default: boolean - type: string - required: - - type - type: object - BuiltinTool: - enum: - - brave_search - - wolfram_alpha - - photogen - - code_interpreter - type: string - CancelTrainingJobRequest: - additionalProperties: false - properties: - job_uuid: - type: string - required: - - job_uuid - type: object - ChatCompletionInputType: - additionalProperties: false - properties: - type: - const: chat_completion_input - default: chat_completion_input - type: string - required: - - type - type: object - ChatCompletionRequest: - additionalProperties: false - properties: - logprobs: - additionalProperties: false - properties: - top_k: - default: 0 - type: integer - type: object - messages: - items: - $ref: '#/components/schemas/Message' - type: array - model_id: - type: string - response_format: - $ref: '#/components/schemas/ResponseFormat' - sampling_params: - $ref: '#/components/schemas/SamplingParams' - stream: - type: boolean - tool_choice: - $ref: '#/components/schemas/ToolChoice' - tool_prompt_format: - $ref: '#/components/schemas/ToolPromptFormat' - tools: - items: - $ref: '#/components/schemas/ToolDefinition' - type: array - required: - - model_id - - messages - type: object - ChatCompletionResponse: - additionalProperties: false - properties: - completion_message: - $ref: '#/components/schemas/CompletionMessage' - logprobs: - items: - $ref: '#/components/schemas/TokenLogProbs' - type: array - required: - - completion_message - title: Chat completion response. - type: object - ChatCompletionResponseEvent: - additionalProperties: false - properties: - delta: - $ref: '#/components/schemas/ContentDelta' - event_type: - $ref: '#/components/schemas/ChatCompletionResponseEventType' - logprobs: - items: - $ref: '#/components/schemas/TokenLogProbs' - type: array - stop_reason: - $ref: '#/components/schemas/StopReason' - required: - - event_type - - delta - title: Chat completion response event. - type: object - ChatCompletionResponseEventType: - enum: - - start - - complete - - progress - type: string - ChatCompletionResponseStreamChunk: - additionalProperties: false - properties: - event: - $ref: '#/components/schemas/ChatCompletionResponseEvent' - required: - - event - title: SSE-stream of these events. - type: object - Checkpoint: - description: Checkpoint created during training runs - CompletionInputType: - additionalProperties: false - properties: - type: - const: completion_input - default: completion_input - type: string - required: - - type - type: object - CompletionMessage: - additionalProperties: false - properties: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + post: + responses: + '200': + description: OK + tags: + - DatasetIO + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: content: - $ref: '#/components/schemas/InterleavedContent' - role: - const: assistant - default: assistant - type: string - stop_reason: - $ref: '#/components/schemas/StopReason' - tool_calls: - items: - $ref: '#/components/schemas/ToolCall' - type: array - required: - - role - - content - - stop_reason - - tool_calls - type: object - CompletionRequest: - additionalProperties: false - properties: + application/json: + schema: + $ref: '#/components/schemas/AppendRowsRequest' + required: true + /v1/batch-inference/chat-completion: + post: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/BatchChatCompletionResponse' + tags: + - BatchInference (Coming Soon) + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: content: - $ref: '#/components/schemas/InterleavedContent' - logprobs: - additionalProperties: false - properties: - top_k: - default: 0 - type: integer - type: object - model_id: - type: string - response_format: - $ref: '#/components/schemas/ResponseFormat' - sampling_params: - $ref: '#/components/schemas/SamplingParams' - stream: - type: boolean - required: - - model_id - - content - type: object - CompletionResponse: - additionalProperties: false - properties: + application/json: + schema: + $ref: '#/components/schemas/BatchChatCompletionRequest' + required: true + /v1/batch-inference/completion: + post: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/BatchCompletionResponse' + tags: + - BatchInference (Coming Soon) + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: content: - type: string - logprobs: - items: - $ref: '#/components/schemas/TokenLogProbs' - type: array - stop_reason: - $ref: '#/components/schemas/StopReason' - required: - - content - - stop_reason - title: Completion response. - type: object - CompletionResponseStreamChunk: - additionalProperties: false - properties: - delta: - type: string - logprobs: - items: - $ref: '#/components/schemas/TokenLogProbs' - type: array - stop_reason: - $ref: '#/components/schemas/StopReason' - required: - - delta - title: streamed completion response. - type: object - ContentDelta: - discriminator: - mapping: - image: '#/components/schemas/ImageDelta' - text: '#/components/schemas/TextDelta' - tool_call: '#/components/schemas/ToolCallDelta' - propertyName: type - oneOf: - - $ref: '#/components/schemas/TextDelta' - - $ref: '#/components/schemas/ImageDelta' - - $ref: '#/components/schemas/ToolCallDelta' - CreateAgentRequest: - additionalProperties: false - properties: - agent_config: - $ref: '#/components/schemas/AgentConfig' - required: - - agent_config - type: object - CreateAgentSessionRequest: - additionalProperties: false - properties: - session_name: - type: string - required: - - session_name - type: object - CreateAgentTurnRequest: - additionalProperties: false - properties: - documents: - items: - additionalProperties: false - properties: - content: + application/json: + schema: + $ref: '#/components/schemas/BatchCompletionRequest' + required: true + /v1/post-training/job/cancel: + post: + responses: + '200': + description: OK + tags: + - PostTraining (Coming Soon) + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/CancelTrainingJobRequest' + required: true + /v1/inference/chat-completion: + post: + responses: + '200': + description: Chat completion response. **OR** SSE-stream of these events. + content: + text/event-stream: + schema: oneOf: - - type: string - - $ref: '#/components/schemas/InterleavedContentItem' - - items: - $ref: '#/components/schemas/InterleavedContentItem' - type: array - - $ref: '#/components/schemas/URL' - mime_type: - type: string - required: - - content - - mime_type - type: object - type: array - messages: - items: - oneOf: - - $ref: '#/components/schemas/UserMessage' - - $ref: '#/components/schemas/ToolResponseMessage' - type: array - stream: - type: boolean - toolgroups: - items: - $ref: '#/components/schemas/AgentTool' - type: array - required: - - messages - type: object - DPOAlignmentConfig: - additionalProperties: false - properties: - epsilon: - type: number - gamma: - type: number - reward_clip: - type: number - reward_scale: - type: number - required: - - reward_scale - - reward_clip - - epsilon - - gamma - type: object - DataConfig: - additionalProperties: false - properties: - batch_size: - type: integer - data_format: - $ref: '#/components/schemas/DatasetFormat' - dataset_id: - type: string - packed: - default: false - type: boolean - shuffle: - type: boolean - train_on_input: - default: false - type: boolean - validation_dataset_id: - type: string - required: - - dataset_id - - batch_size - - shuffle - - data_format - type: object - Dataset: - additionalProperties: false - properties: - dataset_schema: - additionalProperties: - $ref: '#/components/schemas/ParamType' - type: object - identifier: - type: string - metadata: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - provider_id: - type: string - provider_resource_id: - type: string - type: - const: dataset - default: dataset - type: string - url: - $ref: '#/components/schemas/URL' - required: - - identifier - - provider_resource_id - - provider_id - - type - - dataset_schema - - url - - metadata - type: object - DatasetFormat: - enum: - - instruct - - dialog - type: string - DefaultRAGQueryGeneratorConfig: - additionalProperties: false - properties: - separator: - default: ' ' - type: string - type: - const: default - default: default - type: string - required: - - type - - separator - type: object - EfficiencyConfig: - additionalProperties: false - properties: - enable_activation_checkpointing: - default: false - type: boolean - enable_activation_offloading: - default: false - type: boolean - fsdp_cpu_offload: - default: false - type: boolean - memory_efficient_fsdp_wrap: - default: false - type: boolean - type: object - EmbeddingsRequest: - additionalProperties: false - properties: - contents: - items: - $ref: '#/components/schemas/InterleavedContent' - type: array - model_id: - type: string - required: - - model_id - - contents - type: object - EmbeddingsResponse: - additionalProperties: false - properties: - embeddings: - items: - items: - type: number + - $ref: '#/components/schemas/ChatCompletionResponse' + - $ref: '#/components/schemas/ChatCompletionResponseStreamChunk' + tags: + - Inference + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/ChatCompletionRequest' + required: true + /v1/inference/completion: + post: + responses: + '200': + description: Completion response. **OR** streamed completion response. + content: + text/event-stream: + schema: + oneOf: + - $ref: '#/components/schemas/CompletionResponse' + - $ref: '#/components/schemas/CompletionResponseStreamChunk' + tags: + - Inference + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/CompletionRequest' + required: true + /v1/agents: + post: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/AgentCreateResponse' + tags: + - Agents + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/CreateAgentRequest' + required: true + /v1/agents/{agent_id}/session: + post: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/AgentSessionCreateResponse' + tags: + - Agents + parameters: + - name: agent_id + in: path + required: true + schema: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/CreateAgentSessionRequest' + required: true + /v1/agents/{agent_id}/session/{session_id}/turn: + post: + responses: + '200': + description: A single turn in an interaction with an Agentic System. **OR** + streamed agent turn completion response. + content: + text/event-stream: + schema: + oneOf: + - $ref: '#/components/schemas/Turn' + - $ref: '#/components/schemas/AgentTurnResponseStreamChunk' + tags: + - Agents + parameters: + - name: agent_id + in: path + required: true + schema: + type: string + - name: session_id + in: path + required: true + schema: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/CreateAgentTurnRequest' + required: true + /v1/agents/{agent_id}: + delete: + responses: + '200': + description: OK + tags: + - Agents + parameters: + - name: agent_id + in: path + required: true + schema: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + /v1/agents/{agent_id}/session/{session_id}: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/Session' + tags: + - Agents + parameters: + - name: session_id + in: path + required: true + schema: + type: string + - name: agent_id + in: path + required: true + schema: + type: string + - name: turn_ids + in: query + required: false + schema: type: array - type: array - required: - - embeddings - type: object - EvalCandidate: - discriminator: - mapping: - agent: '#/components/schemas/AgentCandidate' - model: '#/components/schemas/ModelCandidate' - propertyName: type - oneOf: - - $ref: '#/components/schemas/ModelCandidate' - - $ref: '#/components/schemas/AgentCandidate' - EvalTask: - additionalProperties: false - properties: - dataset_id: - type: string - identifier: - type: string - metadata: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - provider_id: - type: string - provider_resource_id: - type: string - scoring_functions: - items: + items: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + delete: + responses: + '200': + description: OK + tags: + - Agents + parameters: + - name: session_id + in: path + required: true + schema: + type: string + - name: agent_id + in: path + required: true + schema: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + /v1/inference/embeddings: + post: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/EmbeddingsResponse' + tags: + - Inference + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/EmbeddingsRequest' + required: true + /v1/eval/tasks/{task_id}/evaluations: + post: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/EvaluateResponse' + tags: + - Eval + parameters: + - name: task_id + in: path + required: true + schema: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/EvaluateRowsRequest' + required: true + /v1/agents/{agent_id}/session/{session_id}/turn/{turn_id}/step/{step_id}: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/AgentStepResponse' + tags: + - Agents + parameters: + - name: agent_id + in: path + required: true + schema: + type: string + - name: session_id + in: path + required: true + schema: + type: string + - name: turn_id + in: path + required: true + schema: + type: string + - name: step_id + in: path + required: true + schema: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + /v1/agents/{agent_id}/session/{session_id}/turn/{turn_id}: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/Turn' + tags: + - Agents + parameters: + - name: agent_id + in: path + required: true + schema: + type: string + - name: session_id + in: path + required: true + schema: + type: string + - name: turn_id + in: path + required: true + schema: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + /v1/datasets/{dataset_id}: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + oneOf: + - $ref: '#/components/schemas/Dataset' + - type: 'null' + tags: + - Datasets + parameters: + - name: dataset_id + in: path + required: true + schema: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + delete: + responses: + '200': + description: OK + tags: + - Datasets + parameters: + - name: dataset_id + in: path + required: true + schema: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + /v1/eval-tasks/{eval_task_id}: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + oneOf: + - $ref: '#/components/schemas/EvalTask' + - type: 'null' + tags: + - EvalTasks + parameters: + - name: eval_task_id + in: path + required: true + schema: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + /v1/models/{model_id}: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + oneOf: + - $ref: '#/components/schemas/Model' + - type: 'null' + tags: + - Models + parameters: + - name: model_id + in: path + required: true + schema: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + delete: + responses: + '200': + description: OK + tags: + - Models + parameters: + - name: model_id + in: path + required: true + schema: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + /v1/scoring-functions/{scoring_fn_id}: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + oneOf: + - $ref: '#/components/schemas/ScoringFn' + - type: 'null' + tags: + - ScoringFunctions + parameters: + - name: scoring_fn_id + in: path + required: true + schema: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + /v1/shields/{identifier}: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + oneOf: + - $ref: '#/components/schemas/Shield' + - type: 'null' + tags: + - Shields + parameters: + - name: identifier + in: path + required: true + schema: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + /v1/telemetry/traces/{trace_id}/spans/{span_id}: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/Span' + tags: + - Telemetry + parameters: + - name: trace_id + in: path + required: true + schema: + type: string + - name: span_id + in: path + required: true + schema: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + /v1/telemetry/spans/{span_id}/tree: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/QuerySpanTreeResponse' + tags: + - Telemetry + parameters: + - name: span_id + in: path + required: true + schema: + type: string + - name: attributes_to_return + in: query + required: false + schema: + type: array + items: + type: string + - name: max_depth + in: query + required: false + schema: + type: integer + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + /v1/tools/{tool_name}: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/Tool' + tags: + - ToolGroups + parameters: + - name: tool_name + in: path + required: true + schema: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + /v1/toolgroups/{toolgroup_id}: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/ToolGroup' + tags: + - ToolGroups + parameters: + - name: toolgroup_id + in: path + required: true + schema: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + delete: + responses: + '200': + description: OK + tags: + - ToolGroups + summary: Unregister a tool group + parameters: + - name: toolgroup_id + in: path + required: true + schema: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + /v1/telemetry/traces/{trace_id}: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/Trace' + tags: + - Telemetry + parameters: + - name: trace_id + in: path + required: true + schema: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + /v1/post-training/job/artifacts: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + oneOf: + - $ref: '#/components/schemas/PostTrainingJobArtifactsResponse' + - type: 'null' + tags: + - PostTraining (Coming Soon) + parameters: + - name: job_uuid + in: query + required: true + schema: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + /v1/post-training/job/status: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + oneOf: + - $ref: '#/components/schemas/PostTrainingJobStatusResponse' + - type: 'null' + tags: + - PostTraining (Coming Soon) + parameters: + - name: job_uuid + in: query + required: true + schema: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + /v1/post-training/jobs: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/ListPostTrainingJobsResponse' + tags: + - PostTraining (Coming Soon) + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + /v1/vector-dbs/{vector_db_id}: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + oneOf: + - $ref: '#/components/schemas/VectorDB' + - type: 'null' + tags: + - VectorDBs + parameters: + - name: vector_db_id + in: path + required: true + schema: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + delete: + responses: + '200': + description: OK + tags: + - VectorDBs + parameters: + - name: vector_db_id + in: path + required: true + schema: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + /v1/health: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/HealthInfo' + tags: + - Inspect + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + /v1/tool-runtime/rag-tool/insert: + post: + responses: + '200': + description: OK + tags: + - ToolRuntime + summary: Index documents so they can be used by the RAG system + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/InsertRequest' + required: true + /v1/vector-io/insert: + post: + responses: + '200': + description: OK + tags: + - VectorIO + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/InsertChunksRequest' + required: true + /v1/tool-runtime/invoke: + post: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/ToolInvocationResult' + tags: + - ToolRuntime + summary: Run a tool with the given arguments + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/InvokeToolRequest' + required: true + /v1/eval/tasks/{task_id}/jobs/{job_id}: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + oneOf: + - $ref: '#/components/schemas/JobStatus' + - type: 'null' + tags: + - Eval + parameters: + - name: task_id + in: path + required: true + schema: + type: string + - name: job_id + in: path + required: true + schema: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + delete: + responses: + '200': + description: OK + tags: + - Eval + parameters: + - name: task_id + in: path + required: true + schema: + type: string + - name: job_id + in: path + required: true + schema: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + /v1/eval/tasks/{task_id}/jobs/{job_id}/result: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/EvaluateResponse' + tags: + - Eval + parameters: + - name: job_id + in: path + required: true + schema: + type: string + - name: task_id + in: path + required: true + schema: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + /v1/datasets: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/ListDatasetsResponse' + tags: + - Datasets + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + post: + responses: + '200': + description: OK + tags: + - Datasets + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/RegisterDatasetRequest' + required: true + /v1/eval-tasks: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/ListEvalTasksResponse' + tags: + - EvalTasks + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + post: + responses: + '200': + description: OK + tags: + - EvalTasks + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/RegisterEvalTaskRequest' + required: true + /v1/models: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/ListModelsResponse' + tags: + - Models + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + post: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/Model' + tags: + - Models + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/RegisterModelRequest' + required: true + /v1/inspect/providers: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/ListProvidersResponse' + tags: + - Inspect + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + /v1/inspect/routes: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/ListRoutesResponse' + tags: + - Inspect + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + /v1/tool-runtime/list-tools: + get: + responses: + '200': + description: OK + content: + application/jsonl: + schema: + $ref: '#/components/schemas/ToolDef' + tags: + - ToolRuntime + parameters: + - name: tool_group_id + in: query + required: false + schema: + type: string + - name: mcp_endpoint + in: query + required: false + schema: + $ref: '#/components/schemas/URL' + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + /v1/scoring-functions: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/ListScoringFunctionsResponse' + tags: + - ScoringFunctions + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + post: + responses: + '200': + description: OK + tags: + - ScoringFunctions + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/RegisterScoringFunctionRequest' + required: true + /v1/shields: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/ListShieldsResponse' + tags: + - Shields + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: type: string - type: array - type: - const: eval_task - default: eval_task - type: string - required: - - identifier - - provider_resource_id - - provider_id - - type - - dataset_id - - scoring_functions - - metadata - type: object - EvalTaskConfig: - discriminator: - mapping: - app: '#/components/schemas/AppEvalTaskConfig' - benchmark: '#/components/schemas/BenchmarkEvalTaskConfig' - propertyName: type - oneOf: - - $ref: '#/components/schemas/BenchmarkEvalTaskConfig' - - $ref: '#/components/schemas/AppEvalTaskConfig' - EvaluateResponse: - additionalProperties: false - properties: - generations: - items: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - type: array - scores: - additionalProperties: - $ref: '#/components/schemas/ScoringResult' - type: object - required: - - generations - - scores - type: object - EvaluateRowsRequest: - additionalProperties: false - properties: - input_rows: - items: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - type: array - scoring_functions: - items: + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: type: string - type: array - task_config: - $ref: '#/components/schemas/EvalTaskConfig' - required: - - input_rows - - scoring_functions - - task_config - type: object - Event: - discriminator: - mapping: - metric: '#/components/schemas/MetricEvent' - structured_log: '#/components/schemas/StructuredLogEvent' - unstructured_log: '#/components/schemas/UnstructuredLogEvent' - propertyName: type - oneOf: - - $ref: '#/components/schemas/UnstructuredLogEvent' - - $ref: '#/components/schemas/MetricEvent' - - $ref: '#/components/schemas/StructuredLogEvent' - GrammarResponseFormat: - additionalProperties: false - properties: - bnf: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - type: - const: grammar - default: grammar - type: string - required: - - type - - bnf - type: object - GreedySamplingStrategy: - additionalProperties: false - properties: - type: - const: greedy - default: greedy - type: string - required: - - type - type: object - HealthInfo: - additionalProperties: false - properties: - status: - type: string - required: - - status - type: object - ImageContentItem: - additionalProperties: false - properties: - image: - additionalProperties: false - properties: - data: - contentEncoding: base64 + post: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/Shield' + tags: + - Shields + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/RegisterShieldRequest' + required: true + /v1/toolgroups: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/ListToolGroupsResponse' + tags: + - ToolGroups + summary: List tool groups with optional provider + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + post: + responses: + '200': + description: OK + tags: + - ToolGroups + summary: Register a tool group + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/RegisterToolGroupRequest' + required: true + /v1/tools: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/ListToolsResponse' + tags: + - ToolGroups + summary: List tools with optional tool group + parameters: + - name: toolgroup_id + in: query + required: false + schema: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + /v1/vector-dbs: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/ListVectorDBsResponse' + tags: + - VectorDBs + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + post: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/VectorDB' + tags: + - VectorDBs + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/RegisterVectorDbRequest' + required: true + /v1/telemetry/events: + post: + responses: + '200': + description: OK + tags: + - Telemetry + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/LogEventRequest' + required: true + /v1/post-training/preference-optimize: + post: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/PostTrainingJob' + tags: + - PostTraining (Coming Soon) + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/PreferenceOptimizeRequest' + required: true + /v1/tool-runtime/rag-tool/query: + post: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/RAGQueryResult' + tags: + - ToolRuntime + summary: Query the RAG system for context; typically invoked by the agent + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/QueryRequest' + required: true + /v1/vector-io/query: + post: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/QueryChunksResponse' + tags: + - VectorIO + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/QueryChunksRequest' + required: true + /v1/telemetry/spans: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/QuerySpansResponse' + tags: + - Telemetry + parameters: + - name: attribute_filters + in: query + required: true + schema: + type: array + items: + $ref: '#/components/schemas/QueryCondition' + - name: attributes_to_return + in: query + required: true + schema: + type: array + items: type: string - url: - $ref: '#/components/schemas/URL' - type: object - type: - const: image - default: image - type: string - required: - - type - - image - type: object - ImageDelta: - additionalProperties: false - properties: - image: - contentEncoding: base64 - type: string - type: - const: image - default: image - type: string - required: - - type - - image - type: object - InferenceStep: - additionalProperties: false - properties: - completed_at: - format: date-time - type: string - model_response: - $ref: '#/components/schemas/CompletionMessage' - started_at: - format: date-time - type: string - step_id: - type: string - step_type: - const: inference - default: inference - type: string - turn_id: - type: string - required: - - turn_id - - step_id - - step_type - - model_response - type: object - InsertChunksRequest: - additionalProperties: false - properties: - chunks: - items: - additionalProperties: false - properties: - content: - $ref: '#/components/schemas/InterleavedContent' - metadata: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - required: - - content - - metadata - type: object - type: array - ttl_seconds: - type: integer - vector_db_id: - type: string - required: - - vector_db_id - - chunks - type: object - InsertRequest: - additionalProperties: false - properties: - chunk_size_in_tokens: - type: integer - documents: - items: - $ref: '#/components/schemas/RAGDocument' - type: array - vector_db_id: - type: string - required: - - documents - - vector_db_id - - chunk_size_in_tokens - type: object - InterleavedContent: - oneOf: - - type: string - - $ref: '#/components/schemas/InterleavedContentItem' - - items: - $ref: '#/components/schemas/InterleavedContentItem' - type: array - InterleavedContentItem: - discriminator: - mapping: - image: '#/components/schemas/ImageContentItem' - text: '#/components/schemas/TextContentItem' - propertyName: type - oneOf: - - $ref: '#/components/schemas/ImageContentItem' - - $ref: '#/components/schemas/TextContentItem' - InvokeToolRequest: - additionalProperties: false - properties: - kwargs: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - tool_name: - type: string - required: - - tool_name - - kwargs - type: object - Job: - additionalProperties: false - properties: - job_id: - type: string - required: - - job_id - type: object - JobStatus: - enum: - - completed - - in_progress - - failed - - scheduled - type: string - JsonSchemaResponseFormat: - additionalProperties: false - properties: - json_schema: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - type: - const: json_schema - default: json_schema - type: string - required: - - type - - json_schema - type: object - JsonType: - additionalProperties: false - properties: - type: - const: json - default: json - type: string - required: - - type - type: object - LLMAsJudgeScoringFnParams: - additionalProperties: false - properties: - aggregation_functions: - items: - $ref: '#/components/schemas/AggregationFunctionType' - type: array - judge_model: - type: string - judge_score_regexes: - items: + - name: max_depth + in: query + required: false + schema: + type: integer + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + /v1/telemetry/traces: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/QueryTracesResponse' + tags: + - Telemetry + parameters: + - name: attribute_filters + in: query + required: false + schema: + type: array + items: + $ref: '#/components/schemas/QueryCondition' + - name: limit + in: query + required: false + schema: + type: integer + - name: offset + in: query + required: false + schema: + type: integer + - name: order_by + in: query + required: false + schema: + type: array + items: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + /v1/eval/tasks/{task_id}/jobs: + post: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/Job' + tags: + - Eval + parameters: + - name: task_id + in: path + required: true + schema: + type: string + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/RunEvalRequest' + required: true + /v1/safety/run-shield: + post: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/RunShieldResponse' + tags: + - Safety + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: type: string - type: array - prompt_template: - type: string - type: - const: llm_as_judge - default: llm_as_judge - type: string - required: - - type - - judge_model - type: object - LLMRAGQueryGeneratorConfig: - additionalProperties: false - properties: - model: - type: string - template: - type: string - type: - const: llm - default: llm - type: string - required: - - type - - model - - template - type: object - ListDatasetsResponse: - additionalProperties: false - properties: - data: - items: - $ref: '#/components/schemas/Dataset' - type: array - required: - - data - type: object - ListEvalTasksResponse: - additionalProperties: false - properties: - data: - items: - $ref: '#/components/schemas/EvalTask' - type: array - required: - - data - type: object - ListModelsResponse: - additionalProperties: false - properties: - data: - items: - $ref: '#/components/schemas/Model' - type: array - required: - - data - type: object - ListPostTrainingJobsResponse: - additionalProperties: false - properties: - data: - items: - additionalProperties: false - properties: - job_uuid: - type: string - required: - - job_uuid - type: object - type: array - required: - - data - type: object - ListProvidersResponse: - additionalProperties: false - properties: - data: - items: - $ref: '#/components/schemas/ProviderInfo' - type: array - required: - - data - type: object - ListRoutesResponse: - additionalProperties: false - properties: - data: - items: - $ref: '#/components/schemas/RouteInfo' - type: array - required: - - data - type: object - ListScoringFunctionsResponse: - additionalProperties: false - properties: - data: - items: - $ref: '#/components/schemas/ScoringFn' - type: array - required: - - data - type: object - ListShieldsResponse: - additionalProperties: false - properties: - data: - items: - $ref: '#/components/schemas/Shield' - type: array - required: - - data - type: object - ListToolGroupsResponse: - additionalProperties: false - properties: - data: - items: - $ref: '#/components/schemas/ToolGroup' - type: array - required: - - data - type: object - ListToolsResponse: - additionalProperties: false - properties: - data: - items: - $ref: '#/components/schemas/Tool' - type: array - required: - - data - type: object - ListVectorDBsResponse: - additionalProperties: false - properties: - data: - items: - $ref: '#/components/schemas/VectorDB' - type: array - required: - - data - type: object - LogEventRequest: - additionalProperties: false - properties: - event: - $ref: '#/components/schemas/Event' - ttl_seconds: - type: integer - required: - - event - - ttl_seconds - type: object - LogSeverity: - enum: - - verbose - - debug - - info - - warn - - error - - critical - type: string - LoraFinetuningConfig: - additionalProperties: false - properties: - alpha: - type: integer - apply_lora_to_mlp: - type: boolean - apply_lora_to_output: - type: boolean - lora_attn_modules: - items: + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/RunShieldRequest' + required: true + /v1/telemetry/spans/export: + post: + responses: + '200': + description: OK + tags: + - Telemetry + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/SaveSpansToDatasetRequest' + required: true + /v1/scoring/score: + post: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/ScoreResponse' + tags: + - Scoring + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/ScoreRequest' + required: true + /v1/scoring/score-batch: + post: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/ScoreBatchResponse' + tags: + - Scoring + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/ScoreBatchRequest' + required: true + /v1/post-training/supervised-fine-tune: + post: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/PostTrainingJob' + tags: + - PostTraining (Coming Soon) + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/SupervisedFineTuneRequest' + required: true + /v1/synthetic-data-generation/generate: + post: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/SyntheticDataGenerationResponse' + tags: + - SyntheticDataGeneration (Coming Soon) + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: + type: string + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/SyntheticDataGenerateRequest' + required: true + /v1/version: + get: + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: '#/components/schemas/VersionInfo' + tags: + - Inspect + parameters: + - name: X-LlamaStack-Provider-Data + in: header + description: JSON-encoded provider data which will be made available to + the adapter servicing the API + required: false + schema: type: string - type: array - quantize_base: - default: false - type: boolean - rank: - type: integer - type: - const: LoRA - default: LoRA - type: string - use_dora: - default: false - type: boolean - required: - - type - - lora_attn_modules - - apply_lora_to_mlp - - apply_lora_to_output - - rank - - alpha + - name: X-LlamaStack-Client-Version + in: header + description: Version of the client making the request. This is used to ensure + that the client and server are compatible. + required: false + schema: + type: string +jsonSchemaDialect: https://json-schema.org/draft/2020-12/schema +components: + schemas: + AppendRowsRequest: type: object - MemoryRetrievalStep: - additionalProperties: false properties: - completed_at: - format: date-time - type: string - inserted_context: - $ref: '#/components/schemas/InterleavedContent' - started_at: - format: date-time - type: string - step_id: - type: string - step_type: - const: memory_retrieval - default: memory_retrieval - type: string - turn_id: - type: string - vector_db_ids: + dataset_id: type: string - required: - - turn_id - - step_id - - step_type - - vector_db_ids - - inserted_context - type: object - Message: - discriminator: - mapping: - assistant: '#/components/schemas/CompletionMessage' - system: '#/components/schemas/SystemMessage' - tool: '#/components/schemas/ToolResponseMessage' - user: '#/components/schemas/UserMessage' - propertyName: role - oneOf: - - $ref: '#/components/schemas/UserMessage' - - $ref: '#/components/schemas/SystemMessage' - - $ref: '#/components/schemas/ToolResponseMessage' - - $ref: '#/components/schemas/CompletionMessage' - MetricEvent: + rows: + type: array + items: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object additionalProperties: false - properties: - attributes: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - metric: - type: string - span_id: - type: string - timestamp: - format: date-time - type: string - trace_id: - type: string - type: - const: metric - default: metric - type: string - unit: - type: string - value: - oneOf: - - type: integer - - type: number required: - - trace_id - - span_id - - timestamp - - type - - metric - - value - - unit + - dataset_id + - rows + BuiltinTool: + type: string + enum: + - brave_search + - wolfram_alpha + - photogen + - code_interpreter + CompletionMessage: type: object - Model: - additionalProperties: false properties: - identifier: - type: string - metadata: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - model_type: - $ref: '#/components/schemas/ModelType' - default: llm - provider_id: - type: string - provider_resource_id: - type: string - type: - const: model - default: model + role: type: string - required: - - identifier - - provider_resource_id - - provider_id - - type - - metadata - - model_type - type: object - ModelCandidate: + const: assistant + default: assistant + content: + $ref: '#/components/schemas/InterleavedContent' + stop_reason: + $ref: '#/components/schemas/StopReason' + tool_calls: + type: array + items: + $ref: '#/components/schemas/ToolCall' additionalProperties: false - properties: - model: - type: string - sampling_params: - $ref: '#/components/schemas/SamplingParams' - system_message: - $ref: '#/components/schemas/SystemMessage' - type: - const: model - default: model - type: string required: - - type - - model - - sampling_params + - role + - content + - stop_reason + - tool_calls + GreedySamplingStrategy: type: object - ModelType: - enum: - - llm - - embedding - type: string - NumberType: - additionalProperties: false properties: type: - const: number - default: number type: string + const: greedy + default: greedy + additionalProperties: false required: - - type + - type + ImageContentItem: type: object - ObjectType: - additionalProperties: false properties: type: - const: object - default: object type: string - required: - - type - type: object - OptimizerConfig: + const: image + default: image + image: + type: object + properties: + url: + $ref: '#/components/schemas/URL' + data: + type: string + contentEncoding: base64 + additionalProperties: false additionalProperties: false - properties: - lr: - type: number - num_warmup_steps: - type: integer - optimizer_type: - $ref: '#/components/schemas/OptimizerType' - weight_decay: - type: number required: - - optimizer_type - - lr - - weight_decay - - num_warmup_steps - type: object - OptimizerType: - enum: - - adam - - adamw - - sgd - type: string - PaginatedRowsResult: - additionalProperties: false - properties: - next_page_token: - type: string - rows: + - type + - image + InterleavedContent: + oneOf: + - type: string + - $ref: '#/components/schemas/InterleavedContentItem' + - type: array items: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - type: array - total_count: - type: integer - required: - - rows - - total_count - type: object - ParamType: + $ref: '#/components/schemas/InterleavedContentItem' + InterleavedContentItem: + oneOf: + - $ref: '#/components/schemas/ImageContentItem' + - $ref: '#/components/schemas/TextContentItem' discriminator: - mapping: - agent_turn_input: '#/components/schemas/AgentTurnInputType' - array: '#/components/schemas/ArrayType' - boolean: '#/components/schemas/BooleanType' - chat_completion_input: '#/components/schemas/ChatCompletionInputType' - completion_input: '#/components/schemas/CompletionInputType' - json: '#/components/schemas/JsonType' - number: '#/components/schemas/NumberType' - object: '#/components/schemas/ObjectType' - string: '#/components/schemas/StringType' - union: '#/components/schemas/UnionType' propertyName: type + mapping: + image: '#/components/schemas/ImageContentItem' + text: '#/components/schemas/TextContentItem' + Message: oneOf: - - $ref: '#/components/schemas/StringType' - - $ref: '#/components/schemas/NumberType' - - $ref: '#/components/schemas/BooleanType' - - $ref: '#/components/schemas/ArrayType' - - $ref: '#/components/schemas/ObjectType' - - $ref: '#/components/schemas/JsonType' - - $ref: '#/components/schemas/UnionType' - - $ref: '#/components/schemas/ChatCompletionInputType' - - $ref: '#/components/schemas/CompletionInputType' - - $ref: '#/components/schemas/AgentTurnInputType' - PostTrainingJob: + - $ref: '#/components/schemas/UserMessage' + - $ref: '#/components/schemas/SystemMessage' + - $ref: '#/components/schemas/ToolResponseMessage' + - $ref: '#/components/schemas/CompletionMessage' + discriminator: + propertyName: role + mapping: + user: '#/components/schemas/UserMessage' + system: '#/components/schemas/SystemMessage' + tool: '#/components/schemas/ToolResponseMessage' + assistant: '#/components/schemas/CompletionMessage' + SamplingParams: + type: object + properties: + strategy: + oneOf: + - $ref: '#/components/schemas/GreedySamplingStrategy' + - $ref: '#/components/schemas/TopPSamplingStrategy' + - $ref: '#/components/schemas/TopKSamplingStrategy' + discriminator: + propertyName: type + mapping: + greedy: '#/components/schemas/GreedySamplingStrategy' + top_p: '#/components/schemas/TopPSamplingStrategy' + top_k: '#/components/schemas/TopKSamplingStrategy' + max_tokens: + type: integer + default: 0 + repetition_penalty: + type: number + default: 1.0 additionalProperties: false + required: + - strategy + StopReason: + type: string + enum: + - end_of_turn + - end_of_message + - out_of_tokens + SystemMessage: + type: object properties: - job_uuid: + role: type: string + const: system + default: system + content: + $ref: '#/components/schemas/InterleavedContent' + additionalProperties: false required: - - job_uuid + - role + - content + TextContentItem: type: object - PostTrainingJobArtifactsResponse: - additionalProperties: false properties: - checkpoints: - items: - $ref: '#/components/schemas/Checkpoint' - type: array - job_uuid: + type: + type: string + const: text + default: text + text: type: string + additionalProperties: false required: - - job_uuid - - checkpoints - title: Artifacts of a finetuning job. + - type + - text + ToolCall: type: object - PostTrainingJobStatusResponse: - additionalProperties: false properties: - checkpoints: - items: - $ref: '#/components/schemas/Checkpoint' - type: array - completed_at: - format: date-time - type: string - job_uuid: + call_id: type: string - resources_allocated: + tool_name: + oneOf: + - $ref: '#/components/schemas/BuiltinTool' + - type: string + arguments: + type: object additionalProperties: oneOf: - - type: 'null' - - type: boolean - - type: number + - type: string + - type: integer + - type: number + - type: boolean + - type: 'null' + - type: array + items: + oneOf: + - type: string + - type: integer + - type: number + - type: boolean + - type: 'null' + - type: object + additionalProperties: + oneOf: + - type: string + - type: integer + - type: number + - type: boolean + - type: 'null' + additionalProperties: false + required: + - call_id + - tool_name + - arguments + ToolChoice: + type: string + enum: + - auto + - required + ToolDefinition: + type: object + properties: + tool_name: + oneOf: + - $ref: '#/components/schemas/BuiltinTool' - type: string - - type: array - - type: object - type: object - scheduled_at: - format: date-time - type: string - started_at: - format: date-time + description: type: string - status: - $ref: '#/components/schemas/JobStatus' + parameters: + type: object + additionalProperties: + $ref: '#/components/schemas/ToolParamDefinition' + additionalProperties: false required: - - job_uuid - - status - - checkpoints - title: Status of a finetuning job. + - tool_name + ToolParamDefinition: type: object - PreferenceOptimizeRequest: - additionalProperties: false properties: - algorithm_config: - $ref: '#/components/schemas/DPOAlignmentConfig' - finetuned_model: + param_type: type: string - hyperparam_search_config: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - job_uuid: + description: type: string - logger_config: - additionalProperties: - oneOf: + required: + type: boolean + default: true + default: + oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object - type: object - training_config: - $ref: '#/components/schemas/TrainingConfig' + additionalProperties: false required: - - job_uuid - - finetuned_model - - algorithm_config - - training_config - - hyperparam_search_config - - logger_config + - param_type + ToolPromptFormat: + type: string + enum: + - json + - function_tag + - python_list + title: This Enum refers to the prompt format for calling custom / zero shot + tools + description: "`json` --\n Refers to the json format for calling tools.\n\ + \ The json format takes the form like\n {\n \"type\": \"function\"\ + ,\n \"function\" : {\n \"name\": \"function_name\",\n \ + \ \"description\": \"function_description\",\n \"parameters\"\ + : {...}\n }\n }\n\n`function_tag` --\n This is an example of + how you could define\n your own user defined format for making tool calls.\n\ + \ The function_tag format looks like this,\n (parameters)\n + \nThe detailed prompts for each of these formats are added to llama cli" + ToolResponseMessage: type: object - ProviderInfo: - additionalProperties: false properties: - api: - type: string - provider_id: + role: type: string - provider_type: + const: tool + default: tool + call_id: type: string + tool_name: + oneOf: + - $ref: '#/components/schemas/BuiltinTool' + - type: string + content: + $ref: '#/components/schemas/InterleavedContent' + additionalProperties: false required: - - api - - provider_id - - provider_type + - role + - call_id + - tool_name + - content + TopKSamplingStrategy: type: object - QATFinetuningConfig: - additionalProperties: false properties: - group_size: - type: integer - quantizer_name: - type: string type: - const: QAT - default: QAT type: string + const: top_k + default: top_k + top_k: + type: integer + additionalProperties: false required: - - type - - quantizer_name - - group_size + - type + - top_k + TopPSamplingStrategy: type: object - QueryChunksRequest: - additionalProperties: false properties: - params: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - query: - $ref: '#/components/schemas/InterleavedContent' - vector_db_id: + type: type: string + const: top_p + default: top_p + temperature: + type: number + top_p: + type: number + default: 0.95 + additionalProperties: false required: - - vector_db_id - - query + - type + URL: type: object - QueryChunksResponse: - additionalProperties: false properties: - chunks: - items: - additionalProperties: false - properties: - content: - $ref: '#/components/schemas/InterleavedContent' - metadata: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - required: - - content - - metadata - type: object - type: array - scores: - items: - type: number - type: array + uri: + type: string + additionalProperties: false required: - - chunks - - scores + - uri + UserMessage: type: object - QueryCondition: - additionalProperties: false properties: - key: + role: type: string - op: - $ref: '#/components/schemas/QueryConditionOp' - value: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object + const: user + default: user + content: + $ref: '#/components/schemas/InterleavedContent' + context: + $ref: '#/components/schemas/InterleavedContent' + additionalProperties: false required: - - key - - op - - value + - role + - content + BatchChatCompletionRequest: type: object - QueryConditionOp: - enum: - - eq - - ne - - gt - - lt - type: string - QueryRequest: + properties: + model: + type: string + messages_batch: + type: array + items: + type: array + items: + $ref: '#/components/schemas/Message' + sampling_params: + $ref: '#/components/schemas/SamplingParams' + tools: + type: array + items: + $ref: '#/components/schemas/ToolDefinition' + tool_choice: + $ref: '#/components/schemas/ToolChoice' + tool_prompt_format: + $ref: '#/components/schemas/ToolPromptFormat' + logprobs: + type: object + properties: + top_k: + type: integer + default: 0 + additionalProperties: false additionalProperties: false + required: + - model + - messages_batch + BatchChatCompletionResponse: + type: object properties: - content: - $ref: '#/components/schemas/InterleavedContent' - query_config: - $ref: '#/components/schemas/RAGQueryConfig' - vector_db_ids: - items: - type: string + completion_message_batch: type: array + items: + $ref: '#/components/schemas/CompletionMessage' + additionalProperties: false required: - - content - - vector_db_ids + - completion_message_batch + BatchCompletionRequest: type: object - QuerySpanTreeResponse: - additionalProperties: false properties: - data: - additionalProperties: - $ref: '#/components/schemas/SpanWithStatus' + model: + type: string + content_batch: + type: array + items: + $ref: '#/components/schemas/InterleavedContent' + sampling_params: + $ref: '#/components/schemas/SamplingParams' + logprobs: type: object + properties: + top_k: + type: integer + default: 0 + additionalProperties: false + additionalProperties: false required: - - data + - model + - content_batch + BatchCompletionResponse: type: object - QuerySpansResponse: - additionalProperties: false properties: - data: - items: - $ref: '#/components/schemas/Span' + completion_message_batch: type: array + items: + $ref: '#/components/schemas/CompletionMessage' + additionalProperties: false required: - - data + - completion_message_batch + CancelTrainingJobRequest: type: object - QueryTracesResponse: - additionalProperties: false properties: - data: - items: - $ref: '#/components/schemas/Trace' - type: array + job_uuid: + type: string + additionalProperties: false required: - - data + - job_uuid + GrammarResponseFormat: type: object - RAGDocument: - additionalProperties: false properties: - content: - oneOf: - - type: string - - $ref: '#/components/schemas/InterleavedContentItem' - - items: - $ref: '#/components/schemas/InterleavedContentItem' - type: array - - $ref: '#/components/schemas/URL' - document_id: + type: type: string - metadata: + const: grammar + default: grammar + bnf: + type: object additionalProperties: oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - mime_type: - type: string + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + additionalProperties: false required: - - document_id - - content - - metadata + - type + - bnf + JsonSchemaResponseFormat: type: object - RAGQueryConfig: - additionalProperties: false properties: - max_chunks: - default: 5 - type: integer - max_tokens_in_context: - default: 4096 - type: integer - query_generator_config: - $ref: '#/components/schemas/RAGQueryGeneratorConfig' + type: + type: string + const: json_schema + default: json_schema + json_schema: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + additionalProperties: false required: - - query_generator_config - - max_tokens_in_context - - max_chunks - type: object - RAGQueryGeneratorConfig: + - type + - json_schema + ResponseFormat: + oneOf: + - $ref: '#/components/schemas/JsonSchemaResponseFormat' + - $ref: '#/components/schemas/GrammarResponseFormat' discriminator: - mapping: - default: '#/components/schemas/DefaultRAGQueryGeneratorConfig' - llm: '#/components/schemas/LLMRAGQueryGeneratorConfig' propertyName: type - oneOf: - - $ref: '#/components/schemas/DefaultRAGQueryGeneratorConfig' - - $ref: '#/components/schemas/LLMRAGQueryGeneratorConfig' - RAGQueryResult: - additionalProperties: false - properties: - content: - $ref: '#/components/schemas/InterleavedContent' + mapping: + json_schema: '#/components/schemas/JsonSchemaResponseFormat' + grammar: '#/components/schemas/GrammarResponseFormat' + ChatCompletionRequest: type: object - RegexParserScoringFnParams: - additionalProperties: false properties: - aggregation_functions: - items: - $ref: '#/components/schemas/AggregationFunctionType' + model_id: + type: string + messages: type: array - parsing_regexes: items: - type: string + $ref: '#/components/schemas/Message' + sampling_params: + $ref: '#/components/schemas/SamplingParams' + tools: type: array - type: - const: regex_parser - default: regex_parser - type: string + items: + $ref: '#/components/schemas/ToolDefinition' + tool_choice: + $ref: '#/components/schemas/ToolChoice' + tool_prompt_format: + $ref: '#/components/schemas/ToolPromptFormat' + response_format: + $ref: '#/components/schemas/ResponseFormat' + stream: + type: boolean + logprobs: + type: object + properties: + top_k: + type: integer + default: 0 + additionalProperties: false + additionalProperties: false required: - - type + - model_id + - messages + ChatCompletionResponse: type: object - RegisterDatasetRequest: - additionalProperties: false properties: - dataset_id: - type: string - dataset_schema: - additionalProperties: - $ref: '#/components/schemas/ParamType' - type: object - metadata: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - provider_dataset_id: - type: string - provider_id: - type: string - url: - $ref: '#/components/schemas/URL' + completion_message: + $ref: '#/components/schemas/CompletionMessage' + logprobs: + type: array + items: + $ref: '#/components/schemas/TokenLogProbs' + additionalProperties: false required: - - dataset_id - - dataset_schema - - url + - completion_message + title: Chat completion response. + ChatCompletionResponseEvent: type: object - RegisterEvalTaskRequest: - additionalProperties: false properties: - dataset_id: - type: string - eval_task_id: - type: string - metadata: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - provider_eval_task_id: - type: string - provider_id: - type: string - scoring_functions: - items: - type: string + event_type: + $ref: '#/components/schemas/ChatCompletionResponseEventType' + delta: + $ref: '#/components/schemas/ContentDelta' + logprobs: type: array + items: + $ref: '#/components/schemas/TokenLogProbs' + stop_reason: + $ref: '#/components/schemas/StopReason' + additionalProperties: false required: - - eval_task_id - - dataset_id - - scoring_functions + - event_type + - delta + title: Chat completion response event. + ChatCompletionResponseEventType: + type: string + enum: + - start + - complete + - progress + ChatCompletionResponseStreamChunk: type: object - RegisterModelRequest: - additionalProperties: false properties: - metadata: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - model_id: - type: string - model_type: - $ref: '#/components/schemas/ModelType' - provider_id: - type: string - provider_model_id: - type: string + event: + $ref: '#/components/schemas/ChatCompletionResponseEvent' + additionalProperties: false required: - - model_id + - event + title: SSE-stream of these events. + ContentDelta: + oneOf: + - $ref: '#/components/schemas/TextDelta' + - $ref: '#/components/schemas/ImageDelta' + - $ref: '#/components/schemas/ToolCallDelta' + discriminator: + propertyName: type + mapping: + text: '#/components/schemas/TextDelta' + image: '#/components/schemas/ImageDelta' + tool_call: '#/components/schemas/ToolCallDelta' + ImageDelta: type: object - RegisterScoringFunctionRequest: - additionalProperties: false properties: - description: - type: string - params: - $ref: '#/components/schemas/ScoringFnParams' - provider_id: - type: string - provider_scoring_fn_id: + type: type: string - return_type: - $ref: '#/components/schemas/ParamType' - scoring_fn_id: + const: image + default: image + image: type: string + contentEncoding: base64 + additionalProperties: false required: - - scoring_fn_id - - description - - return_type + - type + - image + TextDelta: type: object - RegisterShieldRequest: - additionalProperties: false properties: - params: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - provider_id: - type: string - provider_shield_id: + type: type: string - shield_id: + const: text + default: text + text: type: string + additionalProperties: false required: - - shield_id + - type + - text + TokenLogProbs: type: object - RegisterToolGroupRequest: - additionalProperties: false properties: - args: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object + logprobs_by_token: type: object - mcp_endpoint: - $ref: '#/components/schemas/URL' - provider_id: - type: string - toolgroup_id: - type: string + additionalProperties: + type: number + additionalProperties: false required: - - toolgroup_id - - provider_id + - logprobs_by_token + ToolCallDelta: type: object - RegisterVectorDbRequest: - additionalProperties: false properties: - embedding_dimension: - type: integer - embedding_model: - type: string - provider_id: - type: string - provider_vector_db_id: - type: string - vector_db_id: + type: type: string + const: tool_call + default: tool_call + tool_call: + oneOf: + - type: string + - $ref: '#/components/schemas/ToolCall' + parse_status: + $ref: '#/components/schemas/ToolCallParseStatus' + additionalProperties: false required: - - vector_db_id - - embedding_model + - type + - tool_call + - parse_status + ToolCallParseStatus: + type: string + enum: + - started + - in_progress + - failed + - succeeded + CompletionRequest: type: object - ResponseFormat: - discriminator: - mapping: - grammar: '#/components/schemas/GrammarResponseFormat' - json_schema: '#/components/schemas/JsonSchemaResponseFormat' - propertyName: type - oneOf: - - $ref: '#/components/schemas/JsonSchemaResponseFormat' - - $ref: '#/components/schemas/GrammarResponseFormat' - RouteInfo: + properties: + model_id: + type: string + content: + $ref: '#/components/schemas/InterleavedContent' + sampling_params: + $ref: '#/components/schemas/SamplingParams' + response_format: + $ref: '#/components/schemas/ResponseFormat' + stream: + type: boolean + logprobs: + type: object + properties: + top_k: + type: integer + default: 0 + additionalProperties: false additionalProperties: false + required: + - model_id + - content + CompletionResponse: + type: object properties: - method: + content: type: string - provider_types: - items: - type: string + stop_reason: + $ref: '#/components/schemas/StopReason' + logprobs: type: array - route: - type: string + items: + $ref: '#/components/schemas/TokenLogProbs' + additionalProperties: false required: - - route - - method - - provider_types + - content + - stop_reason + title: Completion response. + CompletionResponseStreamChunk: type: object - RunEvalRequest: - additionalProperties: false properties: - task_config: - $ref: '#/components/schemas/EvalTaskConfig' + delta: + type: string + stop_reason: + $ref: '#/components/schemas/StopReason' + logprobs: + type: array + items: + $ref: '#/components/schemas/TokenLogProbs' + additionalProperties: false required: - - task_config + - delta + title: streamed completion response. + AgentConfig: type: object - RunShieldRequest: - additionalProperties: false properties: - messages: + sampling_params: + $ref: '#/components/schemas/SamplingParams' + input_shields: + type: array items: - $ref: '#/components/schemas/Message' + type: string + output_shields: type: array - params: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - shield_id: + items: + type: string + toolgroups: + type: array + items: + $ref: '#/components/schemas/AgentTool' + client_tools: + type: array + items: + $ref: '#/components/schemas/ToolDef' + tool_choice: + $ref: '#/components/schemas/ToolChoice' + default: auto + tool_prompt_format: + $ref: '#/components/schemas/ToolPromptFormat' + max_infer_iters: + type: integer + default: 10 + model: type: string - required: - - shield_id - - messages - - params - type: object - RunShieldResponse: + instructions: + type: string + enable_session_persistence: + type: boolean + response_format: + $ref: '#/components/schemas/ResponseFormat' additionalProperties: false - properties: - violation: - $ref: '#/components/schemas/SafetyViolation' + required: + - max_infer_iters + - model + - instructions + - enable_session_persistence + AgentTool: + oneOf: + - type: string + - type: object + properties: + name: + type: string + args: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + additionalProperties: false + required: + - name + - args + ToolDef: type: object - SafetyViolation: - additionalProperties: false properties: + name: + type: string + description: + type: string + parameters: + type: array + items: + $ref: '#/components/schemas/ToolParameter' metadata: + type: object additionalProperties: oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + additionalProperties: false + required: + - name + ToolParameter: + type: object + properties: + name: + type: string + parameter_type: + type: string + description: + type: string + required: + type: boolean + default: true + default: + oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object - type: object - user_message: - type: string - violation_level: - $ref: '#/components/schemas/ViolationLevel' + additionalProperties: false required: - - violation_level - - metadata + - name + - parameter_type + - description + - required + CreateAgentRequest: type: object - SamplingParams: - additionalProperties: false properties: - max_tokens: - default: 0 - type: integer - repetition_penalty: - default: 1.0 - type: number - strategy: - discriminator: - mapping: - greedy: '#/components/schemas/GreedySamplingStrategy' - top_k: '#/components/schemas/TopKSamplingStrategy' - top_p: '#/components/schemas/TopPSamplingStrategy' - propertyName: type - oneOf: - - $ref: '#/components/schemas/GreedySamplingStrategy' - - $ref: '#/components/schemas/TopPSamplingStrategy' - - $ref: '#/components/schemas/TopKSamplingStrategy' + agent_config: + $ref: '#/components/schemas/AgentConfig' + additionalProperties: false required: - - strategy + - agent_config + AgentCreateResponse: type: object - SaveSpansToDatasetRequest: - additionalProperties: false properties: - attribute_filters: - items: - $ref: '#/components/schemas/QueryCondition' - type: array - attributes_to_save: - items: - type: string - type: array - dataset_id: + agent_id: type: string - max_depth: - type: integer + additionalProperties: false required: - - attribute_filters - - attributes_to_save - - dataset_id + - agent_id + CreateAgentSessionRequest: type: object - ScoreBatchRequest: - additionalProperties: false properties: - dataset_id: + session_name: type: string - save_results_dataset: - type: boolean - scoring_functions: - additionalProperties: - oneOf: - - $ref: '#/components/schemas/ScoringFnParams' - - type: 'null' - type: object + additionalProperties: false required: - - dataset_id - - scoring_functions - - save_results_dataset + - session_name + AgentSessionCreateResponse: type: object - ScoreBatchResponse: - additionalProperties: false properties: - dataset_id: + session_id: type: string - results: - additionalProperties: - $ref: '#/components/schemas/ScoringResult' - type: object + additionalProperties: false required: - - results + - session_id + CreateAgentTurnRequest: type: object - ScoreRequest: - additionalProperties: false properties: - input_rows: + messages: + type: array + items: + oneOf: + - $ref: '#/components/schemas/UserMessage' + - $ref: '#/components/schemas/ToolResponseMessage' + stream: + type: boolean + documents: + type: array items: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object type: object + properties: + content: + oneOf: + - type: string + - $ref: '#/components/schemas/InterleavedContentItem' + - type: array + items: + $ref: '#/components/schemas/InterleavedContentItem' + - $ref: '#/components/schemas/URL' + mime_type: + type: string + additionalProperties: false + required: + - content + - mime_type + toolgroups: type: array - scoring_functions: - additionalProperties: - oneOf: - - $ref: '#/components/schemas/ScoringFnParams' - - type: 'null' - type: object + items: + $ref: '#/components/schemas/AgentTool' + additionalProperties: false required: - - input_rows - - scoring_functions + - messages + AgentTurnResponseEvent: type: object - ScoreResponse: - additionalProperties: false properties: - results: - additionalProperties: - $ref: '#/components/schemas/ScoringResult' - type: object + payload: + $ref: '#/components/schemas/AgentTurnResponseEventPayload' + additionalProperties: false required: - - results + - payload + AgentTurnResponseEventPayload: + oneOf: + - $ref: '#/components/schemas/AgentTurnResponseStepStartPayload' + - $ref: '#/components/schemas/AgentTurnResponseStepProgressPayload' + - $ref: '#/components/schemas/AgentTurnResponseStepCompletePayload' + - $ref: '#/components/schemas/AgentTurnResponseTurnStartPayload' + - $ref: '#/components/schemas/AgentTurnResponseTurnCompletePayload' + discriminator: + propertyName: event_type + mapping: + step_start: '#/components/schemas/AgentTurnResponseStepStartPayload' + step_progress: '#/components/schemas/AgentTurnResponseStepProgressPayload' + step_complete: '#/components/schemas/AgentTurnResponseStepCompletePayload' + turn_start: '#/components/schemas/AgentTurnResponseTurnStartPayload' + turn_complete: '#/components/schemas/AgentTurnResponseTurnCompletePayload' + AgentTurnResponseStepCompletePayload: type: object - ScoringFn: - additionalProperties: false properties: - description: + event_type: type: string - identifier: + const: step_complete + default: step_complete + step_type: type: string - metadata: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - params: - $ref: '#/components/schemas/ScoringFnParams' - provider_id: + enum: + - inference + - tool_execution + - shield_call + - memory_retrieval + step_id: type: string - provider_resource_id: + step_details: + oneOf: + - $ref: '#/components/schemas/InferenceStep' + - $ref: '#/components/schemas/ToolExecutionStep' + - $ref: '#/components/schemas/ShieldCallStep' + - $ref: '#/components/schemas/MemoryRetrievalStep' + discriminator: + propertyName: step_type + mapping: + inference: '#/components/schemas/InferenceStep' + tool_execution: '#/components/schemas/ToolExecutionStep' + shield_call: '#/components/schemas/ShieldCallStep' + memory_retrieval: '#/components/schemas/MemoryRetrievalStep' + additionalProperties: false + required: + - event_type + - step_type + - step_id + - step_details + AgentTurnResponseStepProgressPayload: + type: object + properties: + event_type: type: string - return_type: - $ref: '#/components/schemas/ParamType' - type: - const: scoring_function - default: scoring_function + const: step_progress + default: step_progress + step_type: + type: string + enum: + - inference + - tool_execution + - shield_call + - memory_retrieval + step_id: type: string + delta: + $ref: '#/components/schemas/ContentDelta' + additionalProperties: false required: - - identifier - - provider_resource_id - - provider_id - - type - - metadata - - return_type + - event_type + - step_type + - step_id + - delta + AgentTurnResponseStepStartPayload: type: object - ScoringFnParams: - discriminator: - mapping: - basic: '#/components/schemas/BasicScoringFnParams' - llm_as_judge: '#/components/schemas/LLMAsJudgeScoringFnParams' - regex_parser: '#/components/schemas/RegexParserScoringFnParams' - propertyName: type - oneOf: - - $ref: '#/components/schemas/LLMAsJudgeScoringFnParams' - - $ref: '#/components/schemas/RegexParserScoringFnParams' - - $ref: '#/components/schemas/BasicScoringFnParams' - ScoringResult: - additionalProperties: false properties: - aggregated_results: + event_type: + type: string + const: step_start + default: step_start + step_type: + type: string + enum: + - inference + - tool_execution + - shield_call + - memory_retrieval + step_id: + type: string + metadata: + type: object additionalProperties: oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - score_rows: - items: - additionalProperties: - oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array - type: object - type: object - type: array - required: - - score_rows - - aggregated_results - type: object - Session: additionalProperties: false - properties: - session_id: - type: string - session_name: - type: string - started_at: - format: date-time - type: string - turns: - items: - $ref: '#/components/schemas/Turn' - type: array required: - - session_id - - session_name - - turns - - started_at - title: A single session of an interaction with an Agentic System. + - event_type + - step_type + - step_id + AgentTurnResponseStreamChunk: type: object - Shield: - additionalProperties: false properties: - identifier: - type: string - params: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - provider_id: + event: + $ref: '#/components/schemas/AgentTurnResponseEvent' + additionalProperties: false + required: + - event + title: streamed agent turn completion response. + AgentTurnResponseTurnCompletePayload: + type: object + properties: + event_type: type: string - provider_resource_id: + const: turn_complete + default: turn_complete + turn: + $ref: '#/components/schemas/Turn' + additionalProperties: false + required: + - event_type + - turn + AgentTurnResponseTurnStartPayload: + type: object + properties: + event_type: type: string - type: - const: shield - default: shield + const: turn_start + default: turn_start + turn_id: type: string + additionalProperties: false required: - - identifier - - provider_resource_id - - provider_id - - type - title: A safety shield resource that can be used to check content + - event_type + - turn_id + InferenceStep: type: object - ShieldCallStep: - additionalProperties: false properties: - completed_at: - format: date-time + turn_id: + type: string + step_id: type: string started_at: - format: date-time type: string - step_id: + format: date-time + completed_at: type: string + format: date-time step_type: - const: shield_call - default: shield_call type: string - turn_id: - type: string - violation: - $ref: '#/components/schemas/SafetyViolation' + const: inference + default: inference + model_response: + $ref: '#/components/schemas/CompletionMessage' + additionalProperties: false required: - - turn_id - - step_id - - step_type + - turn_id + - step_id + - step_type + - model_response + MemoryRetrievalStep: type: object - Span: - additionalProperties: false properties: - attributes: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - end_time: - format: date-time + turn_id: type: string - name: + step_id: type: string - parent_span_id: + started_at: type: string - span_id: + format: date-time + completed_at: type: string - start_time: format: date-time + step_type: type: string - trace_id: + const: memory_retrieval + default: memory_retrieval + vector_db_ids: type: string + inserted_context: + $ref: '#/components/schemas/InterleavedContent' + additionalProperties: false required: - - span_id - - trace_id - - name - - start_time + - turn_id + - step_id + - step_type + - vector_db_ids + - inserted_context + SafetyViolation: type: object - SpanEndPayload: - additionalProperties: false properties: - status: - $ref: '#/components/schemas/SpanStatus' - type: - const: span_end - default: span_end + violation_level: + $ref: '#/components/schemas/ViolationLevel' + user_message: type: string + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + additionalProperties: false required: - - type - - status + - violation_level + - metadata + ShieldCallStep: type: object - SpanStartPayload: - additionalProperties: false properties: - name: + turn_id: type: string - parent_span_id: + step_id: type: string - type: - const: span_start - default: span_start + started_at: + type: string + format: date-time + completed_at: + type: string + format: date-time + step_type: type: string + const: shield_call + default: shield_call + violation: + $ref: '#/components/schemas/SafetyViolation' + additionalProperties: false required: - - type - - name + - turn_id + - step_id + - step_type + ToolExecutionStep: type: object - SpanStatus: - enum: - - ok - - error - type: string - SpanWithStatus: - additionalProperties: false properties: - attributes: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - end_time: - format: date-time - type: string - name: + turn_id: type: string - parent_span_id: + step_id: type: string - span_id: + started_at: type: string - start_time: format: date-time + completed_at: type: string - status: - $ref: '#/components/schemas/SpanStatus' - trace_id: + format: date-time + step_type: type: string - required: - - span_id - - trace_id - - name - - start_time - type: object - StopReason: - enum: - - end_of_turn - - end_of_message - - out_of_tokens - type: string - StringType: + const: tool_execution + default: tool_execution + tool_calls: + type: array + items: + $ref: '#/components/schemas/ToolCall' + tool_responses: + type: array + items: + $ref: '#/components/schemas/ToolResponse' additionalProperties: false - properties: - type: - const: string - default: string - type: string required: - - type + - turn_id + - step_id + - step_type + - tool_calls + - tool_responses + ToolResponse: type: object - StructuredLogEvent: - additionalProperties: false properties: - attributes: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - payload: - $ref: '#/components/schemas/StructuredLogPayload' - span_id: - type: string - timestamp: - format: date-time - type: string - trace_id: - type: string - type: - const: structured_log - default: structured_log + call_id: type: string + tool_name: + oneOf: + - $ref: '#/components/schemas/BuiltinTool' + - type: string + content: + $ref: '#/components/schemas/InterleavedContent' + additionalProperties: false required: - - trace_id - - span_id - - timestamp - - type - - payload + - call_id + - tool_name + - content + Turn: type: object - StructuredLogPayload: - discriminator: - mapping: - span_end: '#/components/schemas/SpanEndPayload' - span_start: '#/components/schemas/SpanStartPayload' - propertyName: type - oneOf: - - $ref: '#/components/schemas/SpanStartPayload' - - $ref: '#/components/schemas/SpanEndPayload' - SupervisedFineTuneRequest: - additionalProperties: false properties: - algorithm_config: - $ref: '#/components/schemas/AlgorithmConfig' - checkpoint_dir: + turn_id: type: string - hyperparam_search_config: - additionalProperties: + session_id: + type: string + input_messages: + type: array + items: oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - job_uuid: + - $ref: '#/components/schemas/UserMessage' + - $ref: '#/components/schemas/ToolResponseMessage' + steps: + type: array + items: + oneOf: + - $ref: '#/components/schemas/InferenceStep' + - $ref: '#/components/schemas/ToolExecutionStep' + - $ref: '#/components/schemas/ShieldCallStep' + - $ref: '#/components/schemas/MemoryRetrievalStep' + discriminator: + propertyName: step_type + mapping: + inference: '#/components/schemas/InferenceStep' + tool_execution: '#/components/schemas/ToolExecutionStep' + shield_call: '#/components/schemas/ShieldCallStep' + memory_retrieval: '#/components/schemas/MemoryRetrievalStep' + output_message: + $ref: '#/components/schemas/CompletionMessage' + output_attachments: + type: array + items: + type: object + properties: + content: + oneOf: + - type: string + - $ref: '#/components/schemas/InterleavedContentItem' + - type: array + items: + $ref: '#/components/schemas/InterleavedContentItem' + - $ref: '#/components/schemas/URL' + mime_type: + type: string + additionalProperties: false + required: + - content + - mime_type + started_at: type: string - logger_config: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - model: + format: date-time + completed_at: type: string - training_config: - $ref: '#/components/schemas/TrainingConfig' + format: date-time + additionalProperties: false required: - - job_uuid - - training_config - - hyperparam_search_config - - logger_config - - model + - turn_id + - session_id + - input_messages + - steps + - output_message + - output_attachments + - started_at + title: A single turn in an interaction with an Agentic System. + ViolationLevel: + type: string + enum: + - info + - warn + - error + EmbeddingsRequest: type: object - SyntheticDataGenerateRequest: - additionalProperties: false properties: - dialogs: - items: - $ref: '#/components/schemas/Message' - type: array - filtering_function: - enum: - - none - - random - - top_k - - top_p - - top_k_top_p - - sigmoid - title: The type of filtering function. - type: string - model: + model_id: type: string + contents: + type: array + items: + $ref: '#/components/schemas/InterleavedContent' + additionalProperties: false required: - - dialogs - - filtering_function + - model_id + - contents + EmbeddingsResponse: type: object - SyntheticDataGenerationResponse: - additionalProperties: false properties: - statistics: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - synthetic_data: - items: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object + embeddings: type: array + items: + type: array + items: + type: number + additionalProperties: false required: - - synthetic_data - title: Response from the synthetic data generation. Batch of (prompt, response, - score) tuples that pass the threshold. + - embeddings + AgentCandidate: type: object - SystemMessage: - additionalProperties: false properties: - content: - $ref: '#/components/schemas/InterleavedContent' - role: - const: system - default: system + type: type: string + const: agent + default: agent + config: + $ref: '#/components/schemas/AgentConfig' + additionalProperties: false required: - - role - - content + - type + - config + AggregationFunctionType: + type: string + enum: + - average + - median + - categorical_count + - accuracy + AppEvalTaskConfig: type: object - TextContentItem: - additionalProperties: false properties: - text: - type: string type: - const: text - default: text type: string + const: app + default: app + eval_candidate: + $ref: '#/components/schemas/EvalCandidate' + scoring_params: + type: object + additionalProperties: + $ref: '#/components/schemas/ScoringFnParams' + num_examples: + type: integer + additionalProperties: false required: - - type - - text + - type + - eval_candidate + - scoring_params + BasicScoringFnParams: type: object - TextDelta: - additionalProperties: false properties: - text: - type: string type: - const: text - default: text type: string + const: basic + default: basic + aggregation_functions: + type: array + items: + $ref: '#/components/schemas/AggregationFunctionType' + additionalProperties: false required: - - type - - text + - type + BenchmarkEvalTaskConfig: type: object - TokenLogProbs: - additionalProperties: false properties: - logprobs_by_token: - additionalProperties: - type: number - type: object + type: + type: string + const: benchmark + default: benchmark + eval_candidate: + $ref: '#/components/schemas/EvalCandidate' + num_examples: + type: integer + additionalProperties: false required: - - logprobs_by_token + - type + - eval_candidate + EvalCandidate: + oneOf: + - $ref: '#/components/schemas/ModelCandidate' + - $ref: '#/components/schemas/AgentCandidate' + discriminator: + propertyName: type + mapping: + model: '#/components/schemas/ModelCandidate' + agent: '#/components/schemas/AgentCandidate' + EvalTaskConfig: + oneOf: + - $ref: '#/components/schemas/BenchmarkEvalTaskConfig' + - $ref: '#/components/schemas/AppEvalTaskConfig' + discriminator: + propertyName: type + mapping: + benchmark: '#/components/schemas/BenchmarkEvalTaskConfig' + app: '#/components/schemas/AppEvalTaskConfig' + LLMAsJudgeScoringFnParams: type: object - Tool: - additionalProperties: false properties: - description: + type: type: string - identifier: + const: llm_as_judge + default: llm_as_judge + judge_model: type: string - metadata: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - parameters: + prompt_template: + type: string + judge_score_regexes: + type: array items: - $ref: '#/components/schemas/ToolParameter' + type: string + aggregation_functions: type: array - provider_id: - type: string - provider_resource_id: + items: + $ref: '#/components/schemas/AggregationFunctionType' + additionalProperties: false + required: + - type + - judge_model + ModelCandidate: + type: object + properties: + type: type: string - tool_host: - $ref: '#/components/schemas/ToolHost' - toolgroup_id: + const: model + default: model + model: type: string + sampling_params: + $ref: '#/components/schemas/SamplingParams' + system_message: + $ref: '#/components/schemas/SystemMessage' + additionalProperties: false + required: + - type + - model + - sampling_params + RegexParserScoringFnParams: + type: object + properties: type: - const: tool - default: tool type: string + const: regex_parser + default: regex_parser + parsing_regexes: + type: array + items: + type: string + aggregation_functions: + type: array + items: + $ref: '#/components/schemas/AggregationFunctionType' + additionalProperties: false + required: + - type + ScoringFnParams: + oneOf: + - $ref: '#/components/schemas/LLMAsJudgeScoringFnParams' + - $ref: '#/components/schemas/RegexParserScoringFnParams' + - $ref: '#/components/schemas/BasicScoringFnParams' + discriminator: + propertyName: type + mapping: + llm_as_judge: '#/components/schemas/LLMAsJudgeScoringFnParams' + regex_parser: '#/components/schemas/RegexParserScoringFnParams' + basic: '#/components/schemas/BasicScoringFnParams' + EvaluateRowsRequest: + type: object + properties: + input_rows: + type: array + items: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + scoring_functions: + type: array + items: + type: string + task_config: + $ref: '#/components/schemas/EvalTaskConfig' + additionalProperties: false required: - - identifier - - provider_resource_id - - provider_id - - type - - toolgroup_id - - tool_host - - description - - parameters + - input_rows + - scoring_functions + - task_config + EvaluateResponse: type: object - ToolCall: - additionalProperties: false properties: - arguments: - additionalProperties: - oneOf: - - type: string - - type: integer - - type: number - - type: boolean - - type: 'null' - - items: - oneOf: - - type: string - - type: integer - - type: number - - type: boolean + generations: + type: array + items: + type: object + additionalProperties: + oneOf: - type: 'null' - type: array - - additionalProperties: - oneOf: - - type: string - - type: integer - - type: number - type: boolean - - type: 'null' - type: object + - type: number + - type: string + - type: array + - type: object + scores: type: object - call_id: - type: string - tool_name: - oneOf: - - $ref: '#/components/schemas/BuiltinTool' - - type: string - required: - - call_id - - tool_name - - arguments - type: object - ToolCallDelta: + additionalProperties: + $ref: '#/components/schemas/ScoringResult' additionalProperties: false - properties: - parse_status: - $ref: '#/components/schemas/ToolCallParseStatus' - tool_call: - oneOf: - - type: string - - $ref: '#/components/schemas/ToolCall' - type: - const: tool_call - default: tool_call - type: string required: - - type - - tool_call - - parse_status + - generations + - scores + ScoringResult: type: object - ToolCallParseStatus: - enum: - - started - - in_progress - - failed - - succeeded - type: string - ToolChoice: - enum: - - auto - - required - type: string - ToolDef: - additionalProperties: false properties: - description: - type: string - metadata: + score_rows: + type: array + items: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + aggregated_results: + type: object additionalProperties: oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - name: - type: string - parameters: - items: - $ref: '#/components/schemas/ToolParameter' - type: array - required: - - name - type: object - ToolDefinition: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object additionalProperties: false - properties: - description: - type: string - parameters: - additionalProperties: - $ref: '#/components/schemas/ToolParamDefinition' - type: object - tool_name: - oneOf: - - $ref: '#/components/schemas/BuiltinTool' - - type: string required: - - tool_name + - score_rows + - aggregated_results + Session: type: object - ToolExecutionStep: - additionalProperties: false properties: - completed_at: - format: date-time - type: string - started_at: - format: date-time - type: string - step_id: + session_id: type: string - step_type: - const: tool_execution - default: tool_execution + session_name: type: string - tool_calls: - items: - $ref: '#/components/schemas/ToolCall' + turns: type: array - tool_responses: items: - $ref: '#/components/schemas/ToolResponse' - type: array - turn_id: + $ref: '#/components/schemas/Turn' + started_at: type: string + format: date-time + additionalProperties: false required: - - turn_id - - step_id - - step_type - - tool_calls - - tool_responses + - session_id + - session_name + - turns + - started_at + title: A single session of an interaction with an Agentic System. + AgentStepResponse: type: object - ToolGroup: + properties: + step: + oneOf: + - $ref: '#/components/schemas/InferenceStep' + - $ref: '#/components/schemas/ToolExecutionStep' + - $ref: '#/components/schemas/ShieldCallStep' + - $ref: '#/components/schemas/MemoryRetrievalStep' + discriminator: + propertyName: step_type + mapping: + inference: '#/components/schemas/InferenceStep' + tool_execution: '#/components/schemas/ToolExecutionStep' + shield_call: '#/components/schemas/ShieldCallStep' + memory_retrieval: '#/components/schemas/MemoryRetrievalStep' additionalProperties: false + required: + - step + AgentTurnInputType: + type: object properties: - args: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - identifier: - type: string - mcp_endpoint: - $ref: '#/components/schemas/URL' - provider_id: - type: string - provider_resource_id: - type: string type: - const: tool_group - default: tool_group type: string + const: agent_turn_input + default: agent_turn_input + additionalProperties: false required: - - identifier - - provider_resource_id - - provider_id - - type + - type + ArrayType: type: object - ToolHost: - enum: - - distribution - - client - - model_context_protocol - type: string - ToolInvocationResult: - additionalProperties: false properties: - content: - $ref: '#/components/schemas/InterleavedContent' - error_code: - type: integer - error_message: + type: type: string + const: array + default: array + additionalProperties: false required: - - content + - type + BooleanType: type: object - ToolParamDefinition: - additionalProperties: false properties: - default: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: + type: type: string - param_type: + const: boolean + default: boolean + additionalProperties: false + required: + - type + ChatCompletionInputType: + type: object + properties: + type: type: string - required: - default: true - type: boolean + const: chat_completion_input + default: chat_completion_input + additionalProperties: false required: - - param_type + - type + CompletionInputType: type: object - ToolParameter: + properties: + type: + type: string + const: completion_input + default: completion_input additionalProperties: false + required: + - type + Dataset: + type: object properties: - default: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - description: + identifier: type: string - name: + provider_resource_id: type: string - parameter_type: + provider_id: type: string - required: - default: true - type: boolean - required: - - name - - parameter_type - - description - - required - type: object - ToolPromptFormat: - description: "`json` --\n Refers to the json format for calling tools.\n\ - \ The json format takes the form like\n {\n \"type\": \"function\"\ - ,\n \"function\" : {\n \"name\": \"function_name\",\n \ - \ \"description\": \"function_description\",\n \"parameters\"\ - : {...}\n }\n }\n\n`function_tag` --\n This is an example of\ - \ how you could define\n your own user defined format for making tool calls.\n\ - \ The function_tag format looks like this,\n (parameters)\n\ - \nThe detailed prompts for each of these formats are added to llama cli" - enum: - - json - - function_tag - - python_list - title: This Enum refers to the prompt format for calling custom / zero shot - tools - type: string - ToolResponse: + type: + type: string + const: dataset + default: dataset + dataset_schema: + type: object + additionalProperties: + $ref: '#/components/schemas/ParamType' + url: + $ref: '#/components/schemas/URL' + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object additionalProperties: false + required: + - identifier + - provider_resource_id + - provider_id + - type + - dataset_schema + - url + - metadata + JsonType: + type: object properties: - call_id: + type: type: string - content: - $ref: '#/components/schemas/InterleavedContent' - tool_name: - oneOf: - - $ref: '#/components/schemas/BuiltinTool' - - type: string + const: json + default: json + additionalProperties: false required: - - call_id - - tool_name - - content + - type + NumberType: type: object - ToolResponseMessage: - additionalProperties: false properties: - call_id: - type: string - content: - $ref: '#/components/schemas/InterleavedContent' - role: - const: tool - default: tool + type: type: string - tool_name: - oneOf: - - $ref: '#/components/schemas/BuiltinTool' - - type: string + const: number + default: number + additionalProperties: false required: - - role - - call_id - - tool_name - - content + - type + ObjectType: type: object - TopKSamplingStrategy: - additionalProperties: false properties: - top_k: - type: integer type: - const: top_k - default: top_k type: string + const: object + default: object + additionalProperties: false required: - - type - - top_k + - type + ParamType: + oneOf: + - $ref: '#/components/schemas/StringType' + - $ref: '#/components/schemas/NumberType' + - $ref: '#/components/schemas/BooleanType' + - $ref: '#/components/schemas/ArrayType' + - $ref: '#/components/schemas/ObjectType' + - $ref: '#/components/schemas/JsonType' + - $ref: '#/components/schemas/UnionType' + - $ref: '#/components/schemas/ChatCompletionInputType' + - $ref: '#/components/schemas/CompletionInputType' + - $ref: '#/components/schemas/AgentTurnInputType' + discriminator: + propertyName: type + mapping: + string: '#/components/schemas/StringType' + number: '#/components/schemas/NumberType' + boolean: '#/components/schemas/BooleanType' + array: '#/components/schemas/ArrayType' + object: '#/components/schemas/ObjectType' + json: '#/components/schemas/JsonType' + union: '#/components/schemas/UnionType' + chat_completion_input: '#/components/schemas/ChatCompletionInputType' + completion_input: '#/components/schemas/CompletionInputType' + agent_turn_input: '#/components/schemas/AgentTurnInputType' + StringType: type: object - TopPSamplingStrategy: - additionalProperties: false properties: - temperature: - type: number - top_p: - default: 0.95 - type: number type: - const: top_p - default: top_p type: string + const: string + default: string + additionalProperties: false required: - - type + - type + UnionType: type: object - Trace: + properties: + type: + type: string + const: union + default: union additionalProperties: false + required: + - type + EvalTask: + type: object properties: - end_time: - format: date-time + identifier: type: string - root_span_id: + provider_resource_id: type: string - start_time: - format: date-time + provider_id: type: string - trace_id: + type: + type: string + const: eval_task + default: eval_task + dataset_id: type: string + scoring_functions: + type: array + items: + type: string + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + additionalProperties: false required: - - trace_id - - root_span_id - - start_time + - identifier + - provider_resource_id + - provider_id + - type + - dataset_id + - scoring_functions + - metadata + Model: type: object - TrainingConfig: - additionalProperties: false properties: - data_config: - $ref: '#/components/schemas/DataConfig' - dtype: - default: bf16 + identifier: type: string - efficiency_config: - $ref: '#/components/schemas/EfficiencyConfig' - gradient_accumulation_steps: - type: integer - max_steps_per_epoch: - type: integer - max_validation_steps: - type: integer - n_epochs: - type: integer - optimizer_config: - $ref: '#/components/schemas/OptimizerConfig' + provider_resource_id: + type: string + provider_id: + type: string + type: + type: string + const: model + default: model + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + model_type: + $ref: '#/components/schemas/ModelType' + default: llm + additionalProperties: false required: - - n_epochs - - max_steps_per_epoch - - gradient_accumulation_steps - - max_validation_steps - - data_config - - optimizer_config + - identifier + - provider_resource_id + - provider_id + - type + - metadata + - model_type + ModelType: + type: string + enum: + - llm + - embedding + PaginatedRowsResult: type: object - Turn: - additionalProperties: false properties: - completed_at: - format: date-time - type: string - input_messages: - items: - oneOf: - - $ref: '#/components/schemas/UserMessage' - - $ref: '#/components/schemas/ToolResponseMessage' + rows: type: array - output_attachments: items: - additionalProperties: false - properties: - content: - oneOf: - - type: string - - $ref: '#/components/schemas/InterleavedContentItem' - - items: - $ref: '#/components/schemas/InterleavedContentItem' - type: array - - $ref: '#/components/schemas/URL' - mime_type: - type: string - required: - - content - - mime_type type: object - type: array - output_message: - $ref: '#/components/schemas/CompletionMessage' - session_id: + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + total_count: + type: integer + next_page_token: type: string - started_at: - format: date-time + additionalProperties: false + required: + - rows + - total_count + ScoringFn: + type: object + properties: + identifier: type: string - steps: - items: - discriminator: - mapping: - inference: '#/components/schemas/InferenceStep' - memory_retrieval: '#/components/schemas/MemoryRetrievalStep' - shield_call: '#/components/schemas/ShieldCallStep' - tool_execution: '#/components/schemas/ToolExecutionStep' - propertyName: step_type - oneOf: - - $ref: '#/components/schemas/InferenceStep' - - $ref: '#/components/schemas/ToolExecutionStep' - - $ref: '#/components/schemas/ShieldCallStep' - - $ref: '#/components/schemas/MemoryRetrievalStep' - type: array - turn_id: + provider_resource_id: + type: string + provider_id: + type: string + type: + type: string + const: scoring_function + default: scoring_function + description: type: string + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + return_type: + $ref: '#/components/schemas/ParamType' + params: + $ref: '#/components/schemas/ScoringFnParams' + additionalProperties: false required: - - turn_id - - session_id - - input_messages - - steps - - output_message - - output_attachments - - started_at - title: A single turn in an interaction with an Agentic System. + - identifier + - provider_resource_id + - provider_id + - type + - metadata + - return_type + Shield: type: object - URL: + properties: + identifier: + type: string + provider_resource_id: + type: string + provider_id: + type: string + type: + type: string + const: shield + default: shield + params: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object additionalProperties: false - properties: - uri: - type: string required: - - uri + - identifier + - provider_resource_id + - provider_id + - type + title: A safety shield resource that can be used to check content + Span: type: object - UnionType: - additionalProperties: false properties: - type: - const: union - default: union + span_id: type: string - required: - - type - type: object - UnstructuredLogEvent: - additionalProperties: false - properties: - attributes: - additionalProperties: - oneOf: - - type: 'null' - - type: boolean - - type: number - - type: string - - type: array - - type: object - type: object - message: + trace_id: type: string - severity: - $ref: '#/components/schemas/LogSeverity' - span_id: + parent_span_id: type: string - timestamp: - format: date-time + name: type: string - trace_id: + start_time: type: string - type: - const: unstructured_log - default: unstructured_log + format: date-time + end_time: type: string - required: - - trace_id - - span_id - - timestamp - - type - - message - - severity - type: object - UserMessage: + format: date-time + attributes: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object additionalProperties: false - properties: - content: - $ref: '#/components/schemas/InterleavedContent' - context: - $ref: '#/components/schemas/InterleavedContent' - role: - const: user - default: user - type: string required: - - role - - content + - span_id + - trace_id + - name + - start_time + SpanStatus: + type: string + enum: + - ok + - error + SpanWithStatus: type: object - VectorDB: - additionalProperties: false properties: - embedding_dimension: - type: integer - embedding_model: + span_id: type: string - identifier: + trace_id: type: string - provider_id: + parent_span_id: type: string - provider_resource_id: + name: type: string - type: - const: vector_db - default: vector_db + start_time: + type: string + format: date-time + end_time: type: string + format: date-time + attributes: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + status: + $ref: '#/components/schemas/SpanStatus' + additionalProperties: false required: - - identifier - - provider_resource_id - - provider_id - - type - - embedding_model - - embedding_dimension + - span_id + - trace_id + - name + - start_time + QuerySpanTreeResponse: type: object - VersionInfo: - additionalProperties: false properties: - version: - type: string + data: + type: object + additionalProperties: + $ref: '#/components/schemas/SpanWithStatus' + additionalProperties: false required: - - version + - data + Tool: type: object - ViolationLevel: - enum: - - info - - warn - - error - type: string -info: - description: "This is the specification of the Llama Stack that provides\n \ - \ a set of endpoints and their corresponding interfaces that are tailored\ - \ to\n best leverage Llama Models." - title: Llama Stack Specification - version: v1 -jsonSchemaDialect: https://json-schema.org/draft/2020-12/schema -openapi: 3.1.0 -paths: - /v1/agents: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: - type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/CreateAgentRequest' - required: true - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/AgentCreateResponse' - description: OK - tags: - - Agents - /v1/agents/{agent_id}: - delete: - parameters: - - in: path - name: agent_id - required: true - schema: - type: string - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + properties: + identifier: type: string - responses: - '200': - description: OK - tags: - - Agents - /v1/agents/{agent_id}/session: - post: - parameters: - - in: path - name: agent_id - required: true - schema: - type: string - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + provider_resource_id: type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/CreateAgentSessionRequest' - required: true - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/AgentSessionCreateResponse' - description: OK - tags: - - Agents - /v1/agents/{agent_id}/session/{session_id}: - delete: - parameters: - - in: path - name: session_id - required: true - schema: + provider_id: type: string - - in: path - name: agent_id - required: true - schema: - type: string - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + type: type: string - responses: - '200': - description: OK - tags: - - Agents - get: - parameters: - - in: path - name: session_id - required: true - schema: + const: tool + default: tool + toolgroup_id: type: string - - in: path - name: agent_id - required: true - schema: + tool_host: + $ref: '#/components/schemas/ToolHost' + description: type: string - - in: query - name: turn_ids - required: false - schema: - items: - type: string + parameters: type: array - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + items: + $ref: '#/components/schemas/ToolParameter' + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + additionalProperties: false + required: + - identifier + - provider_resource_id + - provider_id + - type + - toolgroup_id + - tool_host + - description + - parameters + ToolHost: + type: string + enum: + - distribution + - client + - model_context_protocol + ToolGroup: + type: object + properties: + identifier: type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/Session' - description: OK - tags: - - Agents - /v1/agents/{agent_id}/session/{session_id}/turn: - post: - parameters: - - in: path - name: agent_id - required: true - schema: + provider_resource_id: + type: string + provider_id: + type: string + type: + type: string + const: tool_group + default: tool_group + mcp_endpoint: + $ref: '#/components/schemas/URL' + args: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + additionalProperties: false + required: + - identifier + - provider_resource_id + - provider_id + - type + Trace: + type: object + properties: + trace_id: type: string - - in: path - name: session_id - required: true - schema: - type: string - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + root_span_id: type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/CreateAgentTurnRequest' - required: true - responses: - '200': - content: - text/event-stream: - schema: - oneOf: - - $ref: '#/components/schemas/Turn' - - $ref: '#/components/schemas/AgentTurnResponseStreamChunk' - description: A single turn in an interaction with an Agentic System. **OR** - streamed agent turn completion response. - tags: - - Agents - /v1/agents/{agent_id}/session/{session_id}/turn/{turn_id}: - get: - parameters: - - in: path - name: agent_id - required: true - schema: + start_time: type: string - - in: path - name: session_id - required: true - schema: + format: date-time + end_time: type: string - - in: path - name: turn_id - required: true - schema: - type: string - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + format: date-time + additionalProperties: false + required: + - trace_id + - root_span_id + - start_time + Checkpoint: + description: Checkpoint created during training runs + PostTrainingJobArtifactsResponse: + type: object + properties: + job_uuid: type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/Turn' - description: OK - tags: - - Agents - /v1/agents/{agent_id}/session/{session_id}/turn/{turn_id}/step/{step_id}: - get: - parameters: - - in: path - name: agent_id - required: true - schema: + checkpoints: + type: array + items: + $ref: '#/components/schemas/Checkpoint' + additionalProperties: false + required: + - job_uuid + - checkpoints + title: Artifacts of a finetuning job. + JobStatus: + type: string + enum: + - completed + - in_progress + - failed + - scheduled + PostTrainingJobStatusResponse: + type: object + properties: + job_uuid: type: string - - in: path - name: session_id - required: true - schema: + status: + $ref: '#/components/schemas/JobStatus' + scheduled_at: type: string - - in: path - name: turn_id - required: true - schema: + format: date-time + started_at: type: string - - in: path - name: step_id - required: true - schema: - type: string - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + format: date-time + completed_at: type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/AgentStepResponse' - description: OK - tags: - - Agents - /v1/batch-inference/chat-completion: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + format: date-time + resources_allocated: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + checkpoints: + type: array + items: + $ref: '#/components/schemas/Checkpoint' + additionalProperties: false + required: + - job_uuid + - status + - checkpoints + title: Status of a finetuning job. + ListPostTrainingJobsResponse: + type: object + properties: + data: + type: array + items: + type: object + properties: + job_uuid: + type: string + additionalProperties: false + required: + - job_uuid + additionalProperties: false + required: + - data + VectorDB: + type: object + properties: + identifier: type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/BatchChatCompletionRequest' - required: true - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/BatchChatCompletionResponse' - description: OK - tags: - - BatchInference (Coming Soon) - /v1/batch-inference/completion: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + provider_resource_id: type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/BatchCompletionRequest' - required: true - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/BatchCompletionResponse' - description: OK - tags: - - BatchInference (Coming Soon) - /v1/datasetio/rows: - get: - parameters: - - in: query - name: dataset_id - required: true - schema: + provider_id: type: string - - in: query - name: rows_in_page - required: true - schema: - type: integer - - in: query - name: page_token - required: false - schema: - type: string - - in: query - name: filter_condition - required: false - schema: - type: string - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + type: type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/PaginatedRowsResult' - description: OK - tags: - - DatasetIO - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + const: vector_db + default: vector_db + embedding_model: type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/AppendRowsRequest' - required: true - responses: - '200': - description: OK - tags: - - DatasetIO - /v1/datasets: - get: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + embedding_dimension: + type: integer + additionalProperties: false + required: + - identifier + - provider_resource_id + - provider_id + - type + - embedding_model + - embedding_dimension + HealthInfo: + type: object + properties: + status: type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/ListDatasetsResponse' - description: OK - tags: - - Datasets - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + additionalProperties: false + required: + - status + RAGDocument: + type: object + properties: + document_id: type: string - requestBody: content: - application/json: - schema: - $ref: '#/components/schemas/RegisterDatasetRequest' - required: true - responses: - '200': - description: OK - tags: - - Datasets - /v1/datasets/{dataset_id}: - delete: - parameters: - - in: path - name: dataset_id - required: true - schema: - type: string - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + oneOf: + - type: string + - $ref: '#/components/schemas/InterleavedContentItem' + - type: array + items: + $ref: '#/components/schemas/InterleavedContentItem' + - $ref: '#/components/schemas/URL' + mime_type: type: string - responses: - '200': - description: OK - tags: - - Datasets - get: - parameters: - - in: path - name: dataset_id - required: true - schema: - type: string - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + additionalProperties: false + required: + - document_id + - content + - metadata + InsertRequest: + type: object + properties: + documents: + type: array + items: + $ref: '#/components/schemas/RAGDocument' + vector_db_id: type: string - responses: - '200': - content: - application/json: - schema: - oneOf: - - $ref: '#/components/schemas/Dataset' - - type: 'null' - description: OK - tags: - - Datasets - /v1/eval-tasks: - get: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + chunk_size_in_tokens: + type: integer + additionalProperties: false + required: + - documents + - vector_db_id + - chunk_size_in_tokens + InsertChunksRequest: + type: object + properties: + vector_db_id: type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/ListEvalTasksResponse' - description: OK - tags: - - EvalTasks - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + chunks: + type: array + items: + type: object + properties: + content: + $ref: '#/components/schemas/InterleavedContent' + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + additionalProperties: false + required: + - content + - metadata + ttl_seconds: + type: integer + additionalProperties: false + required: + - vector_db_id + - chunks + InvokeToolRequest: + type: object + properties: + tool_name: type: string - requestBody: + kwargs: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + additionalProperties: false + required: + - tool_name + - kwargs + ToolInvocationResult: + type: object + properties: content: - application/json: - schema: - $ref: '#/components/schemas/RegisterEvalTaskRequest' - required: true - responses: - '200': - description: OK - tags: - - EvalTasks - /v1/eval-tasks/{eval_task_id}: - get: - parameters: - - in: path - name: eval_task_id - required: true - schema: - type: string - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + $ref: '#/components/schemas/InterleavedContent' + error_message: type: string - responses: - '200': - content: - application/json: - schema: - oneOf: - - $ref: '#/components/schemas/EvalTask' - - type: 'null' - description: OK - tags: - - EvalTasks - /v1/eval/tasks/{task_id}/evaluations: - post: - parameters: - - in: path - name: task_id - required: true - schema: - type: string - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + error_code: + type: integer + additionalProperties: false + required: + - content + ListDatasetsResponse: + type: object + properties: + data: + type: array + items: + $ref: '#/components/schemas/Dataset' + additionalProperties: false + required: + - data + ListEvalTasksResponse: + type: object + properties: + data: + type: array + items: + $ref: '#/components/schemas/EvalTask' + additionalProperties: false + required: + - data + ListModelsResponse: + type: object + properties: + data: + type: array + items: + $ref: '#/components/schemas/Model' + additionalProperties: false + required: + - data + ProviderInfo: + type: object + properties: + api: type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/EvaluateRowsRequest' - required: true - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/EvaluateResponse' - description: OK - tags: - - Eval - /v1/eval/tasks/{task_id}/jobs: - post: - parameters: - - in: path - name: task_id - required: true - schema: - type: string - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + provider_id: type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/RunEvalRequest' - required: true - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/Job' - description: OK - tags: - - Eval - /v1/eval/tasks/{task_id}/jobs/{job_id}: - delete: - parameters: - - in: path - name: task_id - required: true - schema: + provider_type: type: string - - in: path - name: job_id - required: true - schema: - type: string - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + additionalProperties: false + required: + - api + - provider_id + - provider_type + ListProvidersResponse: + type: object + properties: + data: + type: array + items: + $ref: '#/components/schemas/ProviderInfo' + additionalProperties: false + required: + - data + RouteInfo: + type: object + properties: + route: type: string - responses: - '200': - description: OK - tags: - - Eval - get: - parameters: - - in: path - name: task_id - required: true - schema: + method: type: string - - in: path - name: job_id - required: true - schema: - type: string - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + provider_types: + type: array + items: + type: string + additionalProperties: false + required: + - route + - method + - provider_types + ListRoutesResponse: + type: object + properties: + data: + type: array + items: + $ref: '#/components/schemas/RouteInfo' + additionalProperties: false + required: + - data + ListScoringFunctionsResponse: + type: object + properties: + data: + type: array + items: + $ref: '#/components/schemas/ScoringFn' + additionalProperties: false + required: + - data + ListShieldsResponse: + type: object + properties: + data: + type: array + items: + $ref: '#/components/schemas/Shield' + additionalProperties: false + required: + - data + ListToolGroupsResponse: + type: object + properties: + data: + type: array + items: + $ref: '#/components/schemas/ToolGroup' + additionalProperties: false + required: + - data + ListToolsResponse: + type: object + properties: + data: + type: array + items: + $ref: '#/components/schemas/Tool' + additionalProperties: false + required: + - data + ListVectorDBsResponse: + type: object + properties: + data: + type: array + items: + $ref: '#/components/schemas/VectorDB' + additionalProperties: false + required: + - data + Event: + oneOf: + - $ref: '#/components/schemas/UnstructuredLogEvent' + - $ref: '#/components/schemas/MetricEvent' + - $ref: '#/components/schemas/StructuredLogEvent' + discriminator: + propertyName: type + mapping: + unstructured_log: '#/components/schemas/UnstructuredLogEvent' + metric: '#/components/schemas/MetricEvent' + structured_log: '#/components/schemas/StructuredLogEvent' + LogSeverity: + type: string + enum: + - verbose + - debug + - info + - warn + - error + - critical + MetricEvent: + type: object + properties: + trace_id: type: string - responses: - '200': - content: - application/json: - schema: - oneOf: - - $ref: '#/components/schemas/JobStatus' - - type: 'null' - description: OK - tags: - - Eval - /v1/eval/tasks/{task_id}/jobs/{job_id}/result: - get: - parameters: - - in: path - name: job_id - required: true - schema: + span_id: type: string - - in: path - name: task_id - required: true - schema: - type: string - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + timestamp: type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/EvaluateResponse' - description: OK - tags: - - Eval - /v1/health: - get: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + format: date-time + attributes: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + type: type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/HealthInfo' - description: OK - tags: - - Inspect - /v1/inference/chat-completion: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + const: metric + default: metric + metric: type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/ChatCompletionRequest' - required: true - responses: - '200': - content: - text/event-stream: - schema: - oneOf: - - $ref: '#/components/schemas/ChatCompletionResponse' - - $ref: '#/components/schemas/ChatCompletionResponseStreamChunk' - description: Chat completion response. **OR** SSE-stream of these events. - tags: - - Inference - /v1/inference/completion: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + value: + oneOf: + - type: integer + - type: number + unit: type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/CompletionRequest' - required: true - responses: - '200': - content: - text/event-stream: - schema: - oneOf: - - $ref: '#/components/schemas/CompletionResponse' - - $ref: '#/components/schemas/CompletionResponseStreamChunk' - description: Completion response. **OR** streamed completion response. - tags: - - Inference - /v1/inference/embeddings: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + additionalProperties: false + required: + - trace_id + - span_id + - timestamp + - type + - metric + - value + - unit + SpanEndPayload: + type: object + properties: + type: type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/EmbeddingsRequest' - required: true - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/EmbeddingsResponse' - description: OK - tags: - - Inference - /v1/inspect/providers: - get: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + const: span_end + default: span_end + status: + $ref: '#/components/schemas/SpanStatus' + additionalProperties: false + required: + - type + - status + SpanStartPayload: + type: object + properties: + type: type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/ListProvidersResponse' - description: OK - tags: - - Inspect - /v1/inspect/routes: - get: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + const: span_start + default: span_start + name: type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/ListRoutesResponse' - description: OK - tags: - - Inspect - /v1/models: - get: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + parent_span_id: type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/ListModelsResponse' - description: OK - tags: - - Models - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + additionalProperties: false + required: + - type + - name + StructuredLogEvent: + type: object + properties: + trace_id: type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/RegisterModelRequest' - required: true - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/Model' - description: OK - tags: - - Models - /v1/models/{model_id}: - delete: - parameters: - - in: path - name: model_id - required: true - schema: - type: string - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + span_id: type: string - responses: - '200': - description: OK - tags: - - Models - get: - parameters: - - in: path - name: model_id - required: true - schema: - type: string - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + timestamp: type: string - responses: - '200': - content: - application/json: - schema: - oneOf: - - $ref: '#/components/schemas/Model' - - type: 'null' - description: OK - tags: - - Models - /v1/post-training/job/artifacts: - get: - parameters: - - in: query - name: job_uuid - required: true - schema: - type: string - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + format: date-time + attributes: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + type: type: string - responses: - '200': - content: - application/json: - schema: - oneOf: - - $ref: '#/components/schemas/PostTrainingJobArtifactsResponse' - - type: 'null' - description: OK - tags: - - PostTraining (Coming Soon) - /v1/post-training/job/cancel: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + const: structured_log + default: structured_log + payload: + $ref: '#/components/schemas/StructuredLogPayload' + additionalProperties: false + required: + - trace_id + - span_id + - timestamp + - type + - payload + StructuredLogPayload: + oneOf: + - $ref: '#/components/schemas/SpanStartPayload' + - $ref: '#/components/schemas/SpanEndPayload' + discriminator: + propertyName: type + mapping: + span_start: '#/components/schemas/SpanStartPayload' + span_end: '#/components/schemas/SpanEndPayload' + UnstructuredLogEvent: + type: object + properties: + trace_id: type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/CancelTrainingJobRequest' - required: true - responses: - '200': - description: OK - tags: - - PostTraining (Coming Soon) - /v1/post-training/job/status: - get: - parameters: - - in: query - name: job_uuid - required: true - schema: - type: string - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + span_id: type: string - responses: - '200': - content: - application/json: - schema: - oneOf: - - $ref: '#/components/schemas/PostTrainingJobStatusResponse' - - type: 'null' - description: OK - tags: - - PostTraining (Coming Soon) - /v1/post-training/jobs: - get: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + timestamp: type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/ListPostTrainingJobsResponse' - description: OK - tags: - - PostTraining (Coming Soon) - /v1/post-training/preference-optimize: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + format: date-time + attributes: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + type: type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/PreferenceOptimizeRequest' - required: true - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/PostTrainingJob' - description: OK - tags: - - PostTraining (Coming Soon) - /v1/post-training/supervised-fine-tune: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + const: unstructured_log + default: unstructured_log + message: type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/SupervisedFineTuneRequest' - required: true - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/PostTrainingJob' - description: OK - tags: - - PostTraining (Coming Soon) - /v1/safety/run-shield: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + severity: + $ref: '#/components/schemas/LogSeverity' + additionalProperties: false + required: + - trace_id + - span_id + - timestamp + - type + - message + - severity + LogEventRequest: + type: object + properties: + event: + $ref: '#/components/schemas/Event' + ttl_seconds: + type: integer + additionalProperties: false + required: + - event + - ttl_seconds + DPOAlignmentConfig: + type: object + properties: + reward_scale: + type: number + reward_clip: + type: number + epsilon: + type: number + gamma: + type: number + additionalProperties: false + required: + - reward_scale + - reward_clip + - epsilon + - gamma + DataConfig: + type: object + properties: + dataset_id: type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/RunShieldRequest' - required: true - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/RunShieldResponse' - description: OK - tags: - - Safety - /v1/scoring-functions: - get: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + batch_size: + type: integer + shuffle: + type: boolean + data_format: + $ref: '#/components/schemas/DatasetFormat' + validation_dataset_id: type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/ListScoringFunctionsResponse' - description: OK - tags: - - ScoringFunctions - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + packed: + type: boolean + default: false + train_on_input: + type: boolean + default: false + additionalProperties: false + required: + - dataset_id + - batch_size + - shuffle + - data_format + DatasetFormat: + type: string + enum: + - instruct + - dialog + EfficiencyConfig: + type: object + properties: + enable_activation_checkpointing: + type: boolean + default: false + enable_activation_offloading: + type: boolean + default: false + memory_efficient_fsdp_wrap: + type: boolean + default: false + fsdp_cpu_offload: + type: boolean + default: false + additionalProperties: false + OptimizerConfig: + type: object + properties: + optimizer_type: + $ref: '#/components/schemas/OptimizerType' + lr: + type: number + weight_decay: + type: number + num_warmup_steps: + type: integer + additionalProperties: false + required: + - optimizer_type + - lr + - weight_decay + - num_warmup_steps + OptimizerType: + type: string + enum: + - adam + - adamw + - sgd + TrainingConfig: + type: object + properties: + n_epochs: + type: integer + max_steps_per_epoch: + type: integer + gradient_accumulation_steps: + type: integer + max_validation_steps: + type: integer + data_config: + $ref: '#/components/schemas/DataConfig' + optimizer_config: + $ref: '#/components/schemas/OptimizerConfig' + efficiency_config: + $ref: '#/components/schemas/EfficiencyConfig' + dtype: type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/RegisterScoringFunctionRequest' - required: true - responses: - '200': - description: OK - tags: - - ScoringFunctions - /v1/scoring-functions/{scoring_fn_id}: - get: - parameters: - - in: path - name: scoring_fn_id - required: true - schema: - type: string - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + default: bf16 + additionalProperties: false + required: + - n_epochs + - max_steps_per_epoch + - gradient_accumulation_steps + - max_validation_steps + - data_config + - optimizer_config + PreferenceOptimizeRequest: + type: object + properties: + job_uuid: type: string - responses: - '200': - content: - application/json: - schema: - oneOf: - - $ref: '#/components/schemas/ScoringFn' - - type: 'null' - description: OK - tags: - - ScoringFunctions - /v1/scoring/score: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + finetuned_model: type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/ScoreRequest' - required: true - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/ScoreResponse' - description: OK - tags: - - Scoring - /v1/scoring/score-batch: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + algorithm_config: + $ref: '#/components/schemas/DPOAlignmentConfig' + training_config: + $ref: '#/components/schemas/TrainingConfig' + hyperparam_search_config: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + logger_config: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + additionalProperties: false + required: + - job_uuid + - finetuned_model + - algorithm_config + - training_config + - hyperparam_search_config + - logger_config + PostTrainingJob: + type: object + properties: + job_uuid: type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/ScoreBatchRequest' - required: true - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/ScoreBatchResponse' - description: OK - tags: - - Scoring - /v1/shields: - get: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + additionalProperties: false + required: + - job_uuid + DefaultRAGQueryGeneratorConfig: + type: object + properties: + type: type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/ListShieldsResponse' - description: OK - tags: - - Shields - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + const: default + default: default + separator: type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/RegisterShieldRequest' - required: true - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/Shield' - description: OK - tags: - - Shields - /v1/shields/{identifier}: - get: - parameters: - - in: path - name: identifier - required: true - schema: - type: string - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + default: ' ' + additionalProperties: false + required: + - type + - separator + LLMRAGQueryGeneratorConfig: + type: object + properties: + type: type: string - responses: - '200': - content: - application/json: - schema: - oneOf: - - $ref: '#/components/schemas/Shield' - - type: 'null' - description: OK - tags: - - Shields - /v1/synthetic-data-generation/generate: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + const: llm + default: llm + model: type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/SyntheticDataGenerateRequest' - required: true - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/SyntheticDataGenerationResponse' - description: OK - tags: - - SyntheticDataGeneration (Coming Soon) - /v1/telemetry/events: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + template: type: string - requestBody: + additionalProperties: false + required: + - type + - model + - template + RAGQueryConfig: + type: object + properties: + query_generator_config: + $ref: '#/components/schemas/RAGQueryGeneratorConfig' + max_tokens_in_context: + type: integer + default: 4096 + max_chunks: + type: integer + default: 5 + additionalProperties: false + required: + - query_generator_config + - max_tokens_in_context + - max_chunks + RAGQueryGeneratorConfig: + oneOf: + - $ref: '#/components/schemas/DefaultRAGQueryGeneratorConfig' + - $ref: '#/components/schemas/LLMRAGQueryGeneratorConfig' + discriminator: + propertyName: type + mapping: + default: '#/components/schemas/DefaultRAGQueryGeneratorConfig' + llm: '#/components/schemas/LLMRAGQueryGeneratorConfig' + QueryRequest: + type: object + properties: content: - application/json: - schema: - $ref: '#/components/schemas/LogEventRequest' - required: true - responses: - '200': - description: OK - tags: - - Telemetry - /v1/telemetry/spans: - get: - parameters: - - in: query - name: attribute_filters - required: true - schema: + $ref: '#/components/schemas/InterleavedContent' + vector_db_ids: + type: array + items: + type: string + query_config: + $ref: '#/components/schemas/RAGQueryConfig' + additionalProperties: false + required: + - content + - vector_db_ids + RAGQueryResult: + type: object + properties: + content: + $ref: '#/components/schemas/InterleavedContent' + additionalProperties: false + QueryChunksRequest: + type: object + properties: + vector_db_id: + type: string + query: + $ref: '#/components/schemas/InterleavedContent' + params: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + additionalProperties: false + required: + - vector_db_id + - query + QueryChunksResponse: + type: object + properties: + chunks: + type: array items: - $ref: '#/components/schemas/QueryCondition' + type: object + properties: + content: + $ref: '#/components/schemas/InterleavedContent' + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + additionalProperties: false + required: + - content + - metadata + scores: type: array - - in: query - name: attributes_to_return - required: true - schema: items: - type: string + type: number + additionalProperties: false + required: + - chunks + - scores + QueryCondition: + type: object + properties: + key: + type: string + op: + $ref: '#/components/schemas/QueryConditionOp' + value: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + additionalProperties: false + required: + - key + - op + - value + QueryConditionOp: + type: string + enum: + - eq + - ne + - gt + - lt + QuerySpansResponse: + type: object + properties: + data: type: array - - in: query - name: max_depth - required: false - schema: - type: integer - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + items: + $ref: '#/components/schemas/Span' + additionalProperties: false + required: + - data + QueryTracesResponse: + type: object + properties: + data: + type: array + items: + $ref: '#/components/schemas/Trace' + additionalProperties: false + required: + - data + RegisterDatasetRequest: + type: object + properties: + dataset_id: type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/QuerySpansResponse' - description: OK - tags: - - Telemetry - /v1/telemetry/spans/export: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + dataset_schema: + type: object + additionalProperties: + $ref: '#/components/schemas/ParamType' + url: + $ref: '#/components/schemas/URL' + provider_dataset_id: type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/SaveSpansToDatasetRequest' - required: true - responses: - '200': - description: OK - tags: - - Telemetry - /v1/telemetry/spans/{span_id}/tree: - get: - parameters: - - in: path - name: span_id - required: true - schema: + provider_id: type: string - - in: query - name: attributes_to_return - required: false - schema: - items: - type: string - type: array - - in: query - name: max_depth - required: false - schema: - type: integer - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + additionalProperties: false + required: + - dataset_id + - dataset_schema + - url + RegisterEvalTaskRequest: + type: object + properties: + eval_task_id: type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/QuerySpanTreeResponse' - description: OK - tags: - - Telemetry - /v1/telemetry/traces: - get: - parameters: - - in: query - name: attribute_filters - required: false - schema: - items: - $ref: '#/components/schemas/QueryCondition' + dataset_id: + type: string + scoring_functions: type: array - - in: query - name: limit - required: false - schema: - type: integer - - in: query - name: offset - required: false - schema: - type: integer - - in: query - name: order_by - required: false - schema: items: type: string - type: array - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + provider_eval_task_id: type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/QueryTracesResponse' - description: OK - tags: - - Telemetry - /v1/telemetry/traces/{trace_id}: - get: - parameters: - - in: path - name: trace_id - required: true - schema: - type: string - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + provider_id: type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/Trace' - description: OK - tags: - - Telemetry - /v1/telemetry/traces/{trace_id}/spans/{span_id}: - get: - parameters: - - in: path - name: trace_id - required: true - schema: + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + additionalProperties: false + required: + - eval_task_id + - dataset_id + - scoring_functions + RegisterModelRequest: + type: object + properties: + model_id: type: string - - in: path - name: span_id - required: true - schema: - type: string - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + provider_model_id: type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/Span' - description: OK - tags: - - Telemetry - /v1/tool-runtime/invoke: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + provider_id: + type: string + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + model_type: + $ref: '#/components/schemas/ModelType' + additionalProperties: false + required: + - model_id + RegisterScoringFunctionRequest: + type: object + properties: + scoring_fn_id: + type: string + description: + type: string + return_type: + $ref: '#/components/schemas/ParamType' + provider_scoring_fn_id: + type: string + provider_id: + type: string + params: + $ref: '#/components/schemas/ScoringFnParams' + additionalProperties: false + required: + - scoring_fn_id + - description + - return_type + RegisterShieldRequest: + type: object + properties: + shield_id: + type: string + provider_shield_id: + type: string + provider_id: + type: string + params: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + additionalProperties: false + required: + - shield_id + RegisterToolGroupRequest: + type: object + properties: + toolgroup_id: type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/InvokeToolRequest' - required: true - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/ToolInvocationResult' - description: OK - summary: Run a tool with the given arguments - tags: - - ToolRuntime - /v1/tool-runtime/list-tools: - get: - parameters: - - in: query - name: tool_group_id - required: false - schema: - type: string - - in: query - name: mcp_endpoint - required: false - schema: + provider_id: + type: string + mcp_endpoint: $ref: '#/components/schemas/URL' - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + args: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + additionalProperties: false + required: + - toolgroup_id + - provider_id + RegisterVectorDbRequest: + type: object + properties: + vector_db_id: type: string - responses: - '200': - content: - application/jsonl: - schema: - $ref: '#/components/schemas/ToolDef' - description: OK - tags: - - ToolRuntime - /v1/tool-runtime/rag-tool/insert: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + embedding_model: type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/InsertRequest' - required: true - responses: - '200': - description: OK - summary: Index documents so they can be used by the RAG system - tags: - - ToolRuntime - /v1/tool-runtime/rag-tool/query: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + embedding_dimension: + type: integer + provider_id: type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/QueryRequest' - required: true - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/RAGQueryResult' - description: OK - summary: Query the RAG system for context; typically invoked by the agent - tags: - - ToolRuntime - /v1/toolgroups: - get: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + provider_vector_db_id: type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/ListToolGroupsResponse' - description: OK - summary: List tool groups with optional provider - tags: - - ToolGroups - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + additionalProperties: false + required: + - vector_db_id + - embedding_model + RunEvalRequest: + type: object + properties: + task_config: + $ref: '#/components/schemas/EvalTaskConfig' + additionalProperties: false + required: + - task_config + Job: + type: object + properties: + job_id: type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/RegisterToolGroupRequest' - required: true - responses: - '200': - description: OK - summary: Register a tool group - tags: - - ToolGroups - /v1/toolgroups/{toolgroup_id}: - delete: - parameters: - - in: path - name: toolgroup_id - required: true - schema: - type: string - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + additionalProperties: false + required: + - job_id + RunShieldRequest: + type: object + properties: + shield_id: type: string - responses: - '200': - description: OK - summary: Unregister a tool group - tags: - - ToolGroups - get: - parameters: - - in: path - name: toolgroup_id - required: true - schema: - type: string - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + messages: + type: array + items: + $ref: '#/components/schemas/Message' + params: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + additionalProperties: false + required: + - shield_id + - messages + - params + RunShieldResponse: + type: object + properties: + violation: + $ref: '#/components/schemas/SafetyViolation' + additionalProperties: false + SaveSpansToDatasetRequest: + type: object + properties: + attribute_filters: + type: array + items: + $ref: '#/components/schemas/QueryCondition' + attributes_to_save: + type: array + items: + type: string + dataset_id: type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/ToolGroup' - description: OK - tags: - - ToolGroups - /v1/tools: - get: - parameters: - - in: query - name: toolgroup_id - required: false - schema: - type: string - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + max_depth: + type: integer + additionalProperties: false + required: + - attribute_filters + - attributes_to_save + - dataset_id + ScoreRequest: + type: object + properties: + input_rows: + type: array + items: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + scoring_functions: + type: object + additionalProperties: + oneOf: + - $ref: '#/components/schemas/ScoringFnParams' + - type: 'null' + additionalProperties: false + required: + - input_rows + - scoring_functions + ScoreResponse: + type: object + properties: + results: + type: object + additionalProperties: + $ref: '#/components/schemas/ScoringResult' + additionalProperties: false + required: + - results + ScoreBatchRequest: + type: object + properties: + dataset_id: + type: string + scoring_functions: + type: object + additionalProperties: + oneOf: + - $ref: '#/components/schemas/ScoringFnParams' + - type: 'null' + save_results_dataset: + type: boolean + additionalProperties: false + required: + - dataset_id + - scoring_functions + - save_results_dataset + ScoreBatchResponse: + type: object + properties: + dataset_id: + type: string + results: + type: object + additionalProperties: + $ref: '#/components/schemas/ScoringResult' + additionalProperties: false + required: + - results + AlgorithmConfig: + oneOf: + - $ref: '#/components/schemas/LoraFinetuningConfig' + - $ref: '#/components/schemas/QATFinetuningConfig' + discriminator: + propertyName: type + mapping: + LoRA: '#/components/schemas/LoraFinetuningConfig' + QAT: '#/components/schemas/QATFinetuningConfig' + LoraFinetuningConfig: + type: object + properties: + type: type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/ListToolsResponse' - description: OK - summary: List tools with optional tool group - tags: - - ToolGroups - /v1/tools/{tool_name}: - get: - parameters: - - in: path - name: tool_name - required: true - schema: - type: string - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + const: LoRA + default: LoRA + lora_attn_modules: + type: array + items: + type: string + apply_lora_to_mlp: + type: boolean + apply_lora_to_output: + type: boolean + rank: + type: integer + alpha: + type: integer + use_dora: + type: boolean + default: false + quantize_base: + type: boolean + default: false + additionalProperties: false + required: + - type + - lora_attn_modules + - apply_lora_to_mlp + - apply_lora_to_output + - rank + - alpha + QATFinetuningConfig: + type: object + properties: + type: type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/Tool' - description: OK - tags: - - ToolGroups - /v1/vector-dbs: - get: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + const: QAT + default: QAT + quantizer_name: type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/ListVectorDBsResponse' - description: OK - tags: - - VectorDBs - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + group_size: + type: integer + additionalProperties: false + required: + - type + - quantizer_name + - group_size + SupervisedFineTuneRequest: + type: object + properties: + job_uuid: type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/RegisterVectorDbRequest' - required: true - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/VectorDB' - description: OK - tags: - - VectorDBs - /v1/vector-dbs/{vector_db_id}: - delete: - parameters: - - in: path - name: vector_db_id - required: true - schema: - type: string - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + training_config: + $ref: '#/components/schemas/TrainingConfig' + hyperparam_search_config: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + logger_config: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + model: type: string - responses: - '200': - description: OK - tags: - - VectorDBs - get: - parameters: - - in: path - name: vector_db_id - required: true - schema: - type: string - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + checkpoint_dir: type: string - responses: - '200': - content: - application/json: - schema: - oneOf: - - $ref: '#/components/schemas/VectorDB' - - type: 'null' - description: OK - tags: - - VectorDBs - /v1/vector-io/insert: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + algorithm_config: + $ref: '#/components/schemas/AlgorithmConfig' + additionalProperties: false + required: + - job_uuid + - training_config + - hyperparam_search_config + - logger_config + - model + SyntheticDataGenerateRequest: + type: object + properties: + dialogs: + type: array + items: + $ref: '#/components/schemas/Message' + filtering_function: type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/InsertChunksRequest' - required: true - responses: - '200': - description: OK - tags: - - VectorIO - /v1/vector-io/query: - post: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + enum: + - none + - random + - top_k + - top_p + - top_k_top_p + - sigmoid + title: The type of filtering function. + model: type: string - requestBody: - content: - application/json: - schema: - $ref: '#/components/schemas/QueryChunksRequest' - required: true - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/QueryChunksResponse' - description: OK - tags: - - VectorIO - /v1/version: - get: - parameters: - - description: JSON-encoded provider data which will be made available to the - adapter servicing the API - in: header - name: X-LlamaStack-Provider-Data - required: false - schema: - type: string - - description: Version of the client making the request. This is used to ensure - that the client and server are compatible. - in: header - name: X-LlamaStack-Client-Version - required: false - schema: + additionalProperties: false + required: + - dialogs + - filtering_function + SyntheticDataGenerationResponse: + type: object + properties: + synthetic_data: + type: array + items: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + statistics: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + additionalProperties: false + required: + - synthetic_data + title: Response from the synthetic data generation. Batch of (prompt, response, + score) tuples that pass the threshold. + VersionInfo: + type: object + properties: + version: type: string - responses: - '200': - content: - application/json: - schema: - $ref: '#/components/schemas/VersionInfo' - description: OK - tags: - - Inspect + additionalProperties: false + required: + - version + responses: {} security: -- Default: [] -servers: -- url: http://any-hosted-llama-stack.com + - Default: [] tags: -- description: - name: AgentCandidate -- description: - name: AgentConfig -- description: - name: AgentCreateResponse -- description: - name: AgentSessionCreateResponse -- description: - name: AgentStepResponse -- description: - name: AgentTool -- description: - name: AgentTurnInputType -- description: - name: AgentTurnResponseEvent -- description: - name: AgentTurnResponseEventPayload -- description: - name: AgentTurnResponseStepCompletePayload -- description: - name: AgentTurnResponseStepProgressPayload -- description: - name: AgentTurnResponseStepStartPayload -- description: 'streamed agent turn completion response. - - - ' - name: AgentTurnResponseStreamChunk -- description: - name: AgentTurnResponseTurnCompletePayload -- description: - name: AgentTurnResponseTurnStartPayload -- name: Agents -- description: - name: AggregationFunctionType -- description: - name: AlgorithmConfig -- description: - name: AppEvalTaskConfig -- description: - name: AppendRowsRequest -- description: - name: ArrayType -- description: - name: BasicScoringFnParams -- description: - name: BatchChatCompletionRequest -- description: - name: BatchChatCompletionResponse -- description: - name: BatchCompletionRequest -- description: - name: BatchCompletionResponse -- name: BatchInference (Coming Soon) -- description: - name: BenchmarkEvalTaskConfig -- description: - name: BooleanType -- description: - name: BuiltinTool -- description: - name: CancelTrainingJobRequest -- description: - name: ChatCompletionInputType -- description: - name: ChatCompletionRequest -- description: 'Chat completion response. - - - ' - name: ChatCompletionResponse -- description: 'Chat completion response event. - - - ' - name: ChatCompletionResponseEvent -- description: - name: ChatCompletionResponseEventType -- description: 'SSE-stream of these events. - - - ' - name: ChatCompletionResponseStreamChunk -- description: 'Checkpoint created during training runs - - - ' - name: Checkpoint -- description: - name: CompletionInputType -- description: - name: CompletionMessage -- description: - name: CompletionRequest -- description: 'Completion response. - - - ' - name: CompletionResponse -- description: 'streamed completion response. - - - ' - name: CompletionResponseStreamChunk -- description: - name: ContentDelta -- description: - name: CreateAgentRequest -- description: - name: CreateAgentSessionRequest -- description: - name: CreateAgentTurnRequest -- description: - name: DPOAlignmentConfig -- description: - name: DataConfig -- description: - name: Dataset -- description: - name: DatasetFormat -- name: DatasetIO -- name: Datasets -- description: - name: DefaultRAGQueryGeneratorConfig -- description: - name: EfficiencyConfig -- description: - name: EmbeddingsRequest -- description: - name: EmbeddingsResponse -- name: Eval -- description: - name: EvalCandidate -- description: - name: EvalTask -- description: - name: EvalTaskConfig -- name: EvalTasks -- description: - name: EvaluateResponse -- description: - name: EvaluateRowsRequest -- description: - name: Event -- description: - name: GrammarResponseFormat -- description: - name: GreedySamplingStrategy -- description: - name: HealthInfo -- description: - name: ImageContentItem -- description: - name: ImageDelta -- name: Inference -- description: - name: InferenceStep -- description: - name: InsertChunksRequest -- description: - name: InsertRequest -- name: Inspect -- description: - name: InterleavedContent -- description: - name: InterleavedContentItem -- description: - name: InvokeToolRequest -- description: - name: Job -- description: - name: JobStatus -- description: - name: JsonSchemaResponseFormat -- description: - name: JsonType -- description: - name: LLMAsJudgeScoringFnParams -- description: - name: LLMRAGQueryGeneratorConfig -- description: - name: ListDatasetsResponse -- description: - name: ListEvalTasksResponse -- description: - name: ListModelsResponse -- description: - name: ListPostTrainingJobsResponse -- description: - name: ListProvidersResponse -- description: - name: ListRoutesResponse -- description: - name: ListScoringFunctionsResponse -- description: - name: ListShieldsResponse -- description: - name: ListToolGroupsResponse -- description: - name: ListToolsResponse -- description: - name: ListVectorDBsResponse -- description: - name: LogEventRequest -- description: - name: LogSeverity -- description: - name: LoraFinetuningConfig -- description: - name: MemoryRetrievalStep -- description: - name: Message -- description: - name: MetricEvent -- description: - name: Model -- description: - name: ModelCandidate -- description: - name: ModelType -- name: Models -- description: - name: NumberType -- description: - name: ObjectType -- description: - name: OptimizerConfig -- description: - name: OptimizerType -- description: - name: PaginatedRowsResult -- description: - name: ParamType -- name: PostTraining (Coming Soon) -- description: - name: PostTrainingJob -- description: 'Artifacts of a finetuning job. - - - ' - name: PostTrainingJobArtifactsResponse -- description: 'Status of a finetuning job. - - - ' - name: PostTrainingJobStatusResponse -- description: - name: PreferenceOptimizeRequest -- description: - name: ProviderInfo -- description: - name: QATFinetuningConfig -- description: - name: QueryChunksRequest -- description: - name: QueryChunksResponse -- description: - name: QueryCondition -- description: - name: QueryConditionOp -- description: - name: QueryRequest -- description: - name: QuerySpanTreeResponse -- description: - name: QuerySpansResponse -- description: - name: QueryTracesResponse -- description: - name: RAGDocument -- description: - name: RAGQueryConfig -- description: - name: RAGQueryGeneratorConfig -- description: - name: RAGQueryResult -- description: - name: RegexParserScoringFnParams -- description: - name: RegisterDatasetRequest -- description: - name: RegisterEvalTaskRequest -- description: - name: RegisterModelRequest -- description: - name: RegisterScoringFunctionRequest -- description: - name: RegisterShieldRequest -- description: - name: RegisterToolGroupRequest -- description: - name: RegisterVectorDbRequest -- description: - name: ResponseFormat -- description: - name: RouteInfo -- description: - name: RunEvalRequest -- description: - name: RunShieldRequest -- description: - name: RunShieldResponse -- name: Safety -- description: - name: SafetyViolation -- description: - name: SamplingParams -- description: - name: SaveSpansToDatasetRequest -- description: - name: ScoreBatchRequest -- description: - name: ScoreBatchResponse -- description: - name: ScoreRequest -- description: - name: ScoreResponse -- name: Scoring -- description: - name: ScoringFn -- description: - name: ScoringFnParams -- name: ScoringFunctions -- description: - name: ScoringResult -- description: 'A single session of an interaction with an Agentic System. - - - ' - name: Session -- description: 'A safety shield resource that can be used to check content - - - ' - name: Shield -- description: - name: ShieldCallStep -- name: Shields -- description: - name: Span -- description: - name: SpanEndPayload -- description: - name: SpanStartPayload -- description: - name: SpanStatus -- description: - name: SpanWithStatus -- description: - name: StopReason -- description: - name: StringType -- description: - name: StructuredLogEvent -- description: - name: StructuredLogPayload -- description: - name: SupervisedFineTuneRequest -- description: - name: SyntheticDataGenerateRequest -- name: SyntheticDataGeneration (Coming Soon) -- description: 'Response from the synthetic data generation. Batch of (prompt, response, - score) tuples that pass the threshold. - - - ' - name: SyntheticDataGenerationResponse -- description: - name: SystemMessage -- name: Telemetry -- description: - name: TextContentItem -- description: - name: TextDelta -- description: - name: TokenLogProbs -- description: - name: Tool -- description: - name: ToolCall -- description: - name: ToolCallDelta -- description: - name: ToolCallParseStatus -- description: - name: ToolChoice -- description: - name: ToolDef -- description: - name: ToolDefinition -- description: - name: ToolExecutionStep -- description: - name: ToolGroup -- name: ToolGroups -- description: - name: ToolHost -- description: - name: ToolInvocationResult -- description: - name: ToolParamDefinition -- description: - name: ToolParameter -- description: "This Enum refers to the prompt format for calling custom / zero shot\ - \ tools\n\n`json` --\n Refers to the json format for calling tools.\n The\ - \ json format takes the form like\n {\n \"type\": \"function\",\n \ - \ \"function\" : {\n \"name\": \"function_name\",\n \ - \ \"description\": \"function_description\",\n \"parameters\": {...}\n\ - \ }\n }\n\n`function_tag` --\n This is an example of how you could\ - \ define\n your own user defined format for making tool calls.\n The function_tag\ - \ format looks like this,\n (parameters)\n\ - \nThe detailed prompts for each of these formats are added to llama cli\n\n" - name: ToolPromptFormat -- description: - name: ToolResponse -- description: - name: ToolResponseMessage -- name: ToolRuntime -- description: - name: TopKSamplingStrategy -- description: - name: TopPSamplingStrategy -- description: - name: Trace -- description: - name: TrainingConfig -- description: 'A single turn in an interaction with an Agentic System. - - - ' - name: Turn -- description: - name: URL -- description: - name: UnionType -- description: - name: UnstructuredLogEvent -- description: - name: UserMessage -- description: - name: VectorDB -- name: VectorDBs -- name: VectorIO -- description: - name: VersionInfo -- description: - name: ViolationLevel + - name: AgentCandidate + description: '' + - name: AgentConfig + description: '' + - name: AgentCreateResponse + description: '' + - name: AgentSessionCreateResponse + description: '' + - name: AgentStepResponse + description: '' + - name: AgentTool + description: '' + - name: AgentTurnInputType + description: '' + - name: AgentTurnResponseEvent + description: '' + - name: AgentTurnResponseEventPayload + description: '' + - name: AgentTurnResponseStepCompletePayload + description: '' + - name: AgentTurnResponseStepProgressPayload + description: '' + - name: AgentTurnResponseStepStartPayload + description: '' + - name: AgentTurnResponseStreamChunk + description: streamed agent turn completion response. + - name: AgentTurnResponseTurnCompletePayload + description: '' + - name: AgentTurnResponseTurnStartPayload + description: '' + - name: Agents + - name: AggregationFunctionType + description: '' + - name: AlgorithmConfig + description: '' + - name: AppEvalTaskConfig + description: '' + - name: AppendRowsRequest + description: '' + - name: ArrayType + description: '' + - name: BasicScoringFnParams + description: '' + - name: BatchChatCompletionRequest + description: '' + - name: BatchChatCompletionResponse + description: '' + - name: BatchCompletionRequest + description: '' + - name: BatchCompletionResponse + description: '' + - name: BatchInference (Coming Soon) + - name: BenchmarkEvalTaskConfig + description: '' + - name: BooleanType + description: '' + - name: BuiltinTool + description: '' + - name: CancelTrainingJobRequest + description: '' + - name: ChatCompletionInputType + description: '' + - name: ChatCompletionRequest + description: '' + - name: ChatCompletionResponse + description: Chat completion response. + - name: ChatCompletionResponseEvent + description: Chat completion response event. + - name: ChatCompletionResponseEventType + description: '' + - name: ChatCompletionResponseStreamChunk + description: SSE-stream of these events. + - name: Checkpoint + description: Checkpoint created during training runs + - name: CompletionInputType + description: '' + - name: CompletionMessage + description: '' + - name: CompletionRequest + description: '' + - name: CompletionResponse + description: Completion response. + - name: CompletionResponseStreamChunk + description: streamed completion response. + - name: ContentDelta + description: '' + - name: CreateAgentRequest + description: '' + - name: CreateAgentSessionRequest + description: '' + - name: CreateAgentTurnRequest + description: '' + - name: DPOAlignmentConfig + description: '' + - name: DataConfig + description: '' + - name: Dataset + description: '' + - name: DatasetFormat + description: '' + - name: DatasetIO + - name: Datasets + - name: DefaultRAGQueryGeneratorConfig + description: '' + - name: EfficiencyConfig + description: '' + - name: EmbeddingsRequest + description: '' + - name: EmbeddingsResponse + description: '' + - name: Eval + - name: EvalCandidate + description: '' + - name: EvalTask + description: '' + - name: EvalTaskConfig + description: '' + - name: EvalTasks + - name: EvaluateResponse + description: '' + - name: EvaluateRowsRequest + description: '' + - name: Event + description: '' + - name: GrammarResponseFormat + description: '' + - name: GreedySamplingStrategy + description: '' + - name: HealthInfo + description: '' + - name: ImageContentItem + description: '' + - name: ImageDelta + description: '' + - name: Inference + - name: InferenceStep + description: '' + - name: InsertChunksRequest + description: '' + - name: InsertRequest + description: '' + - name: Inspect + - name: InterleavedContent + description: '' + - name: InterleavedContentItem + description: '' + - name: InvokeToolRequest + description: '' + - name: Job + description: '' + - name: JobStatus + description: '' + - name: JsonSchemaResponseFormat + description: '' + - name: JsonType + description: '' + - name: LLMAsJudgeScoringFnParams + description: '' + - name: LLMRAGQueryGeneratorConfig + description: '' + - name: ListDatasetsResponse + description: '' + - name: ListEvalTasksResponse + description: '' + - name: ListModelsResponse + description: '' + - name: ListPostTrainingJobsResponse + description: '' + - name: ListProvidersResponse + description: '' + - name: ListRoutesResponse + description: '' + - name: ListScoringFunctionsResponse + description: '' + - name: ListShieldsResponse + description: '' + - name: ListToolGroupsResponse + description: '' + - name: ListToolsResponse + description: '' + - name: ListVectorDBsResponse + description: '' + - name: LogEventRequest + description: '' + - name: LogSeverity + description: '' + - name: LoraFinetuningConfig + description: '' + - name: MemoryRetrievalStep + description: '' + - name: Message + description: '' + - name: MetricEvent + description: '' + - name: Model + description: '' + - name: ModelCandidate + description: '' + - name: ModelType + description: '' + - name: Models + - name: NumberType + description: '' + - name: ObjectType + description: '' + - name: OptimizerConfig + description: '' + - name: OptimizerType + description: '' + - name: PaginatedRowsResult + description: '' + - name: ParamType + description: '' + - name: PostTraining (Coming Soon) + - name: PostTrainingJob + description: '' + - name: PostTrainingJobArtifactsResponse + description: Artifacts of a finetuning job. + - name: PostTrainingJobStatusResponse + description: Status of a finetuning job. + - name: PreferenceOptimizeRequest + description: '' + - name: ProviderInfo + description: '' + - name: QATFinetuningConfig + description: '' + - name: QueryChunksRequest + description: '' + - name: QueryChunksResponse + description: '' + - name: QueryCondition + description: '' + - name: QueryConditionOp + description: '' + - name: QueryRequest + description: '' + - name: QuerySpanTreeResponse + description: '' + - name: QuerySpansResponse + description: '' + - name: QueryTracesResponse + description: '' + - name: RAGDocument + description: '' + - name: RAGQueryConfig + description: '' + - name: RAGQueryGeneratorConfig + description: '' + - name: RAGQueryResult + description: '' + - name: RegexParserScoringFnParams + description: '' + - name: RegisterDatasetRequest + description: '' + - name: RegisterEvalTaskRequest + description: '' + - name: RegisterModelRequest + description: '' + - name: RegisterScoringFunctionRequest + description: '' + - name: RegisterShieldRequest + description: '' + - name: RegisterToolGroupRequest + description: '' + - name: RegisterVectorDbRequest + description: '' + - name: ResponseFormat + description: '' + - name: RouteInfo + description: '' + - name: RunEvalRequest + description: '' + - name: RunShieldRequest + description: '' + - name: RunShieldResponse + description: '' + - name: Safety + - name: SafetyViolation + description: '' + - name: SamplingParams + description: '' + - name: SaveSpansToDatasetRequest + description: '' + - name: ScoreBatchRequest + description: '' + - name: ScoreBatchResponse + description: '' + - name: ScoreRequest + description: '' + - name: ScoreResponse + description: '' + - name: Scoring + - name: ScoringFn + description: '' + - name: ScoringFnParams + description: '' + - name: ScoringFunctions + - name: ScoringResult + description: '' + - name: Session + description: A single session of an interaction with an Agentic System. + - name: Shield + description: A safety shield resource that can be used to check content + - name: ShieldCallStep + description: '' + - name: Shields + - name: Span + description: '' + - name: SpanEndPayload + description: '' + - name: SpanStartPayload + description: '' + - name: SpanStatus + description: '' + - name: SpanWithStatus + description: '' + - name: StopReason + description: '' + - name: StringType + description: '' + - name: StructuredLogEvent + description: '' + - name: StructuredLogPayload + description: '' + - name: SupervisedFineTuneRequest + description: '' + - name: SyntheticDataGenerateRequest + description: '' + - name: SyntheticDataGeneration (Coming Soon) + - name: SyntheticDataGenerationResponse + description: Response from the synthetic data generation. Batch of (prompt, response, + score) tuples that pass the threshold. + - name: SystemMessage + description: '' + - name: Telemetry + - name: TextContentItem + description: '' + - name: TextDelta + description: '' + - name: TokenLogProbs + description: '' + - name: Tool + description: '' + - name: ToolCall + description: '' + - name: ToolCallDelta + description: '' + - name: ToolCallParseStatus + description: '' + - name: ToolChoice + description: '' + - name: ToolDef + description: '' + - name: ToolDefinition + description: '' + - name: ToolExecutionStep + description: '' + - name: ToolGroup + description: '' + - name: ToolGroups + - name: ToolHost + description: '' + - name: ToolInvocationResult + description: '' + - name: ToolParamDefinition + description: '' + - name: ToolParameter + description: '' + - name: ToolPromptFormat + description: "This Enum refers to the prompt format for calling custom / zero + shot tools\n\n`json` --\n Refers to the json format for calling tools.\n\ + \ The json format takes the form like\n {\n \"type\": \"function\"\ + ,\n \"function\" : {\n \"name\": \"function_name\",\n \ + \ \"description\": \"function_description\",\n \"parameters\"\ + : {...}\n }\n }\n\n`function_tag` --\n This is an example of how + you could define\n your own user defined format for making tool calls.\n\ + \ The function_tag format looks like this,\n (parameters)\n + \nThe detailed prompts for each of these formats are added to llama cli" + - name: ToolResponse + description: '' + - name: ToolResponseMessage + description: '' + - name: ToolRuntime + - name: TopKSamplingStrategy + description: '' + - name: TopPSamplingStrategy + description: '' + - name: Trace + description: '' + - name: TrainingConfig + description: '' + - name: Turn + description: A single turn in an interaction with an Agentic System. + - name: URL + description: '' + - name: UnionType + description: '' + - name: UnstructuredLogEvent + description: '' + - name: UserMessage + description: '' + - name: VectorDB + description: '' + - name: VectorDBs + - name: VectorIO + - name: VersionInfo + description: '' + - name: ViolationLevel + description: '' x-tagGroups: -- name: Operations - tags: - - Agents - - BatchInference (Coming Soon) - - DatasetIO - - Datasets - - Eval - - EvalTasks - - Inference - - Inspect - - Models - - PostTraining (Coming Soon) - - Safety - - Scoring - - ScoringFunctions - - Shields - - SyntheticDataGeneration (Coming Soon) - - Telemetry - - ToolGroups - - ToolRuntime - - VectorDBs - - VectorIO -- name: Types - tags: - - AgentCandidate - - AgentConfig - - AgentCreateResponse - - AgentSessionCreateResponse - - AgentStepResponse - - AgentTool - - AgentTurnInputType - - AgentTurnResponseEvent - - AgentTurnResponseEventPayload - - AgentTurnResponseStepCompletePayload - - AgentTurnResponseStepProgressPayload - - AgentTurnResponseStepStartPayload - - AgentTurnResponseStreamChunk - - AgentTurnResponseTurnCompletePayload - - AgentTurnResponseTurnStartPayload - - AggregationFunctionType - - AlgorithmConfig - - AppEvalTaskConfig - - AppendRowsRequest - - ArrayType - - BasicScoringFnParams - - BatchChatCompletionRequest - - BatchChatCompletionResponse - - BatchCompletionRequest - - BatchCompletionResponse - - BenchmarkEvalTaskConfig - - BooleanType - - BuiltinTool - - CancelTrainingJobRequest - - ChatCompletionInputType - - ChatCompletionRequest - - ChatCompletionResponse - - ChatCompletionResponseEvent - - ChatCompletionResponseEventType - - ChatCompletionResponseStreamChunk - - Checkpoint - - CompletionInputType - - CompletionMessage - - CompletionRequest - - CompletionResponse - - CompletionResponseStreamChunk - - ContentDelta - - CreateAgentRequest - - CreateAgentSessionRequest - - CreateAgentTurnRequest - - DPOAlignmentConfig - - DataConfig - - Dataset - - DatasetFormat - - DefaultRAGQueryGeneratorConfig - - EfficiencyConfig - - EmbeddingsRequest - - EmbeddingsResponse - - EvalCandidate - - EvalTask - - EvalTaskConfig - - EvaluateResponse - - EvaluateRowsRequest - - Event - - GrammarResponseFormat - - GreedySamplingStrategy - - HealthInfo - - ImageContentItem - - ImageDelta - - InferenceStep - - InsertChunksRequest - - InsertRequest - - InterleavedContent - - InterleavedContentItem - - InvokeToolRequest - - Job - - JobStatus - - JsonSchemaResponseFormat - - JsonType - - LLMAsJudgeScoringFnParams - - LLMRAGQueryGeneratorConfig - - ListDatasetsResponse - - ListEvalTasksResponse - - ListModelsResponse - - ListPostTrainingJobsResponse - - ListProvidersResponse - - ListRoutesResponse - - ListScoringFunctionsResponse - - ListShieldsResponse - - ListToolGroupsResponse - - ListToolsResponse - - ListVectorDBsResponse - - LogEventRequest - - LogSeverity - - LoraFinetuningConfig - - MemoryRetrievalStep - - Message - - MetricEvent - - Model - - ModelCandidate - - ModelType - - NumberType - - ObjectType - - OptimizerConfig - - OptimizerType - - PaginatedRowsResult - - ParamType - - PostTrainingJob - - PostTrainingJobArtifactsResponse - - PostTrainingJobStatusResponse - - PreferenceOptimizeRequest - - ProviderInfo - - QATFinetuningConfig - - QueryChunksRequest - - QueryChunksResponse - - QueryCondition - - QueryConditionOp - - QueryRequest - - QuerySpanTreeResponse - - QuerySpansResponse - - QueryTracesResponse - - RAGDocument - - RAGQueryConfig - - RAGQueryGeneratorConfig - - RAGQueryResult - - RegexParserScoringFnParams - - RegisterDatasetRequest - - RegisterEvalTaskRequest - - RegisterModelRequest - - RegisterScoringFunctionRequest - - RegisterShieldRequest - - RegisterToolGroupRequest - - RegisterVectorDbRequest - - ResponseFormat - - RouteInfo - - RunEvalRequest - - RunShieldRequest - - RunShieldResponse - - SafetyViolation - - SamplingParams - - SaveSpansToDatasetRequest - - ScoreBatchRequest - - ScoreBatchResponse - - ScoreRequest - - ScoreResponse - - ScoringFn - - ScoringFnParams - - ScoringResult - - Session - - Shield - - ShieldCallStep - - Span - - SpanEndPayload - - SpanStartPayload - - SpanStatus - - SpanWithStatus - - StopReason - - StringType - - StructuredLogEvent - - StructuredLogPayload - - SupervisedFineTuneRequest - - SyntheticDataGenerateRequest - - SyntheticDataGenerationResponse - - SystemMessage - - TextContentItem - - TextDelta - - TokenLogProbs - - Tool - - ToolCall - - ToolCallDelta - - ToolCallParseStatus - - ToolChoice - - ToolDef - - ToolDefinition - - ToolExecutionStep - - ToolGroup - - ToolHost - - ToolInvocationResult - - ToolParamDefinition - - ToolParameter - - ToolPromptFormat - - ToolResponse - - ToolResponseMessage - - TopKSamplingStrategy - - TopPSamplingStrategy - - Trace - - TrainingConfig - - Turn - - URL - - UnionType - - UnstructuredLogEvent - - UserMessage - - VectorDB - - VersionInfo - - ViolationLevel + - name: Operations + tags: + - Agents + - BatchInference (Coming Soon) + - DatasetIO + - Datasets + - Eval + - EvalTasks + - Inference + - Inspect + - Models + - PostTraining (Coming Soon) + - Safety + - Scoring + - ScoringFunctions + - Shields + - SyntheticDataGeneration (Coming Soon) + - Telemetry + - ToolGroups + - ToolRuntime + - VectorDBs + - VectorIO + - name: Types + tags: + - AgentCandidate + - AgentConfig + - AgentCreateResponse + - AgentSessionCreateResponse + - AgentStepResponse + - AgentTool + - AgentTurnInputType + - AgentTurnResponseEvent + - AgentTurnResponseEventPayload + - AgentTurnResponseStepCompletePayload + - AgentTurnResponseStepProgressPayload + - AgentTurnResponseStepStartPayload + - AgentTurnResponseStreamChunk + - AgentTurnResponseTurnCompletePayload + - AgentTurnResponseTurnStartPayload + - AggregationFunctionType + - AlgorithmConfig + - AppEvalTaskConfig + - AppendRowsRequest + - ArrayType + - BasicScoringFnParams + - BatchChatCompletionRequest + - BatchChatCompletionResponse + - BatchCompletionRequest + - BatchCompletionResponse + - BenchmarkEvalTaskConfig + - BooleanType + - BuiltinTool + - CancelTrainingJobRequest + - ChatCompletionInputType + - ChatCompletionRequest + - ChatCompletionResponse + - ChatCompletionResponseEvent + - ChatCompletionResponseEventType + - ChatCompletionResponseStreamChunk + - Checkpoint + - CompletionInputType + - CompletionMessage + - CompletionRequest + - CompletionResponse + - CompletionResponseStreamChunk + - ContentDelta + - CreateAgentRequest + - CreateAgentSessionRequest + - CreateAgentTurnRequest + - DPOAlignmentConfig + - DataConfig + - Dataset + - DatasetFormat + - DefaultRAGQueryGeneratorConfig + - EfficiencyConfig + - EmbeddingsRequest + - EmbeddingsResponse + - EvalCandidate + - EvalTask + - EvalTaskConfig + - EvaluateResponse + - EvaluateRowsRequest + - Event + - GrammarResponseFormat + - GreedySamplingStrategy + - HealthInfo + - ImageContentItem + - ImageDelta + - InferenceStep + - InsertChunksRequest + - InsertRequest + - InterleavedContent + - InterleavedContentItem + - InvokeToolRequest + - Job + - JobStatus + - JsonSchemaResponseFormat + - JsonType + - LLMAsJudgeScoringFnParams + - LLMRAGQueryGeneratorConfig + - ListDatasetsResponse + - ListEvalTasksResponse + - ListModelsResponse + - ListPostTrainingJobsResponse + - ListProvidersResponse + - ListRoutesResponse + - ListScoringFunctionsResponse + - ListShieldsResponse + - ListToolGroupsResponse + - ListToolsResponse + - ListVectorDBsResponse + - LogEventRequest + - LogSeverity + - LoraFinetuningConfig + - MemoryRetrievalStep + - Message + - MetricEvent + - Model + - ModelCandidate + - ModelType + - NumberType + - ObjectType + - OptimizerConfig + - OptimizerType + - PaginatedRowsResult + - ParamType + - PostTrainingJob + - PostTrainingJobArtifactsResponse + - PostTrainingJobStatusResponse + - PreferenceOptimizeRequest + - ProviderInfo + - QATFinetuningConfig + - QueryChunksRequest + - QueryChunksResponse + - QueryCondition + - QueryConditionOp + - QueryRequest + - QuerySpanTreeResponse + - QuerySpansResponse + - QueryTracesResponse + - RAGDocument + - RAGQueryConfig + - RAGQueryGeneratorConfig + - RAGQueryResult + - RegexParserScoringFnParams + - RegisterDatasetRequest + - RegisterEvalTaskRequest + - RegisterModelRequest + - RegisterScoringFunctionRequest + - RegisterShieldRequest + - RegisterToolGroupRequest + - RegisterVectorDbRequest + - ResponseFormat + - RouteInfo + - RunEvalRequest + - RunShieldRequest + - RunShieldResponse + - SafetyViolation + - SamplingParams + - SaveSpansToDatasetRequest + - ScoreBatchRequest + - ScoreBatchResponse + - ScoreRequest + - ScoreResponse + - ScoringFn + - ScoringFnParams + - ScoringResult + - Session + - Shield + - ShieldCallStep + - Span + - SpanEndPayload + - SpanStartPayload + - SpanStatus + - SpanWithStatus + - StopReason + - StringType + - StructuredLogEvent + - StructuredLogPayload + - SupervisedFineTuneRequest + - SyntheticDataGenerateRequest + - SyntheticDataGenerationResponse + - SystemMessage + - TextContentItem + - TextDelta + - TokenLogProbs + - Tool + - ToolCall + - ToolCallDelta + - ToolCallParseStatus + - ToolChoice + - ToolDef + - ToolDefinition + - ToolExecutionStep + - ToolGroup + - ToolHost + - ToolInvocationResult + - ToolParamDefinition + - ToolParameter + - ToolPromptFormat + - ToolResponse + - ToolResponseMessage + - TopKSamplingStrategy + - TopPSamplingStrategy + - Trace + - TrainingConfig + - Turn + - URL + - UnionType + - UnstructuredLogEvent + - UserMessage + - VectorDB + - VersionInfo + - ViolationLevel