[Bug]: Cache Needs to be inited

[theinhumaneme]

Current Behavior

i get a stack trace

False
True
Traceback (most recent call last):
  File "/home/theinhumaneme/Documents/NebuLogic/conversation-bot/development/scripts/chatbot-postgres-test.py", line 129, in <module>
    execution_time = timeit.timeit(lambda: llm.invoke("Tell me a joke"), number=1)
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.11/timeit.py", line 237, in timeit
    return Timer(stmt, setup, timer, globals).timeit(number)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.11/timeit.py", line 180, in timeit
    timing = self.inner(it, self.timer)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "<timeit-src>", line 6, in inner
  File "/home/theinhumaneme/Documents/NebuLogic/conversation-bot/development/scripts/chatbot-postgres-test.py", line 129, in <lambda>
    execution_time = timeit.timeit(lambda: llm.invoke("Tell me a joke"), number=1)
                                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/theinhumaneme/Documents/NebuLogic/conversation-bot/venv/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py", line 153, in invoke
    self.generate_prompt(
  File "/home/theinhumaneme/Documents/NebuLogic/conversation-bot/venv/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py", line 546, in generate_prompt
    return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/theinhumaneme/Documents/NebuLogic/conversation-bot/venv/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py", line 407, in generate
    raise e
  File "/home/theinhumaneme/Documents/NebuLogic/conversation-bot/venv/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py", line 397, in generate
    self._generate_with_cache(
  File "/home/theinhumaneme/Documents/NebuLogic/conversation-bot/venv/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py", line 579, in _generate_with_cache
    cache_val = llm_cache.lookup(prompt, llm_string)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/theinhumaneme/Documents/NebuLogic/conversation-bot/venv/lib/python3.11/site-packages/langchain_community/cache.py", line 813, in lookup
    res = get(prompt, cache_obj=_gptcache)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/theinhumaneme/Documents/NebuLogic/conversation-bot/venv/lib/python3.11/site-packages/gptcache/adapter/api.py", line 124, in get
    res = adapt(
          ^^^^^^
  File "/home/theinhumaneme/Documents/NebuLogic/conversation-bot/venv/lib/python3.11/site-packages/gptcache/adapter/adapter.py", line 33, in adapt
    raise NotInitError()
gptcache.utils.error.NotInitError: The cache should be inited before using

Expected Behavior

I should be able to use the cache normally

Steps To Reproduce

import os
from langchain_openai import ChatOpenAI
from langchain_openai import OpenAI
os.environ["OPENAI_API_KEY"] = ""
CONNECTION_STRING = "postgresql+psycopg2://postgres:postgres@localhost:5432/postgres"

import hashlib
import timeit
from gptcache import Cache, cache
from gptcache.adapter.api import init_similar_cache
from langchain.globals import set_llm_cache
from langchain_community.cache import GPTCache, SQLiteCache
from langchain_openai import OpenAIEmbeddings
from gptcache.manager import get_data_manager, CacheBase, VectorBase
from langchain.globals import set_llm_cache
from gptcache.similarity_evaluation.distance import SearchDistanceEvaluation


def get_content_func(data, **_):
    return data.get("prompt").split("Question")[-1]


openai_embeddings = OpenAIEmbeddings(model="text-embedding-3-small")
cache_base = CacheBase(
    "postgresql",
    sql_url="postgresql+psycopg2://postgres:postgres@127.0.0.1:5432/postgres",
)
vector_base = VectorBase(
    "pgvector",
    host="127.0.0.1",
    port="5432",
    user="postgres",
    password="postgres",
    dimension=1536,
)
data_manager = get_data_manager(cache_base, vector_base)

# cache.init(
#     pre_embedding_func=get_content_func,
#     embedding_func=OpenAIEmbeddings(model="text-embedding-3-small").embed_query,
#     data_manager=data_manager,
#     similarity_evaluation=SearchDistanceEvaluation(),
# )
def init_gptcache(cache_obj: Cache, llm: str):
    print(cache.has_init)
    cache.init(
        pre_embedding_func=get_content_func,
        embedding_func=OpenAIEmbeddings(model="text-embedding-3-small").embed_query,
        data_manager=data_manager,
        similarity_evaluation=SearchDistanceEvaluation(),
    )
    print(cache.has_init)


llm_model = "gpt-3.5-turbo-0125"
llm = ChatOpenAI(temperature=0, model_name=llm_model)

set_llm_cache(GPTCache(init_gptcache))

execution_time = timeit.timeit(lambda: llm.invoke("Tell me a joke"), number=1)
print(f"Execution time: {execution_time} seconds")

execution_time = timeit.timeit(lambda: llm.invoke("Tell me a joke"), number=1)
print(f"Execution time: {execution_time} seconds")

Environment

No response

Anything else?

i get this error when i use the set_llm_cache() from langchain

it works fine when i use it normally i.e init but fails when i am trying to embed my text using the openai embeddings i get an error stating that to_embeddings doesn't exist when i change the code in the function to embed_query i get unexpected extra_params passed.

Thank you :D

[SimFG]

refer to: #585 (comment)
you should give the cache_obj param for the init func, like:

def init_gptcache(cache_obj: Cache, llm: str):
    print(cache.has_init)
    cache.init(
        cache_obj=cache_obj,
        pre_embedding_func=get_content_func,
        embedding_func=OpenAIEmbeddings(model="text-embedding-3-small").embed_query,
        data_manager=data_manager,
        similarity_evaluation=SearchDistanceEvaluation(),
    )
    print(cache.has_init)

[theinhumaneme]

Okay that works, thank you but now i get this error

Traceback (most recent call last):
  File "/home/theinhumaneme/Documents/NebuLogic/conversation-bot/development/scripts/chatbot-postgres-test.py", line 129, in <module>
    execution_time = timeit.timeit(lambda: llm.invoke("Tell me a joke"), number=1)
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.11/timeit.py", line 237, in timeit
    return Timer(stmt, setup, timer, globals).timeit(number)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.11/timeit.py", line 180, in timeit
    timing = self.inner(it, self.timer)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "<timeit-src>", line 6, in inner
  File "/home/theinhumaneme/Documents/NebuLogic/conversation-bot/development/scripts/chatbot-postgres-test.py", line 129, in <lambda>
    execution_time = timeit.timeit(lambda: llm.invoke("Tell me a joke"), number=1)
                                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/theinhumaneme/Documents/NebuLogic/conversation-bot/venv/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py", line 153, in invoke
    self.generate_prompt(
  File "/home/theinhumaneme/Documents/NebuLogic/conversation-bot/venv/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py", line 546, in generate_prompt
    return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/theinhumaneme/Documents/NebuLogic/conversation-bot/venv/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py", line 407, in generate
    raise e
  File "/home/theinhumaneme/Documents/NebuLogic/conversation-bot/venv/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py", line 397, in generate
    self._generate_with_cache(
  File "/home/theinhumaneme/Documents/NebuLogic/conversation-bot/venv/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py", line 579, in _generate_with_cache
    cache_val = llm_cache.lookup(prompt, llm_string)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/theinhumaneme/Documents/NebuLogic/conversation-bot/venv/lib/python3.11/site-packages/langchain_community/cache.py", line 813, in lookup
    res = get(prompt, cache_obj=_gptcache)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/theinhumaneme/Documents/NebuLogic/conversation-bot/venv/lib/python3.11/site-packages/gptcache/adapter/api.py", line 124, in get
    res = adapt(
          ^^^^^^
  File "/home/theinhumaneme/Documents/NebuLogic/conversation-bot/venv/lib/python3.11/site-packages/gptcache/adapter/adapter.py", line 78, in adapt
    embedding_data = time_cal(
                     ^^^^^^^^^
  File "/home/theinhumaneme/Documents/NebuLogic/conversation-bot/venv/lib/python3.11/site-packages/gptcache/utils/time.py", line 9, in inner
    res = func(*args, **kwargs)
          ^^^^^^^^^^^^^^^^^^^^^
TypeError: OpenAIEmbeddings.embed_query() got an unexpected keyword argument 'extra_param

is this because of the new openai endpoints or am i doing something wrong.

[SimFG]

@theinhumaneme This seems to be the wrong format of the custom embedding function.
you can refer to: https://github.com/zilliztech/GPTCache/blob/main/gptcache/embedding/openai.py

[SimFG]

@theinhumaneme or, you can show the embed_query func, maybe i can give you some advice

[theinhumaneme]

@theinhumaneme or, you can show the embed_query func, maybe i can give you some advice

there is no to_embeddings function in the OpenAIEmbeddings class now. We have embed_query and embed_documents

Here's the link
https://api.python.langchain.com/en/latest/_modules/langchain_openai/embeddings/base.html#OpenAIEmbeddings.embed_query

[SimFG]

@theinhumaneme
You cannot put langchain's embedding methods into gptcache because they are incompatible, and gptcache will not be considered when langchain is modified.

[theinhumaneme]

Okay thank you, I will look into the openai library thank you