dosubot[bot]
commented
1 year ago 🤖
Hello,
Thank you for reaching out with your question. It seems like you want to configure the OpenAiAgent in LangChain to access different vectorstores if the answer is not found in a particular vectorstore. This is indeed possible and can be achieved by using the VectorStoreRouterToolkit and the create_vectorstore_router_agent function.
Here is a code snippet that shows how to do this:
from langchain.agents.agent_toolkits import (
create_vectorstore_router_agent,
VectorStoreRouterToolkit,
VectorStoreInfo,
)
from langchain.vectorstores.pgvector import PGVector
from langchain.embeddings.openai import OpenAIEmbeddings
# Create the VectorStoreInfo instances
state_of_union_store = PGVector.from_existing_index(
connection_string="postgresql+psycopg2://user:password@localhost:5432/dbname",
embedding_function=OpenAIEmbeddings(),
collection_name="state_of_union_address",
)
ruff_store = PGVector.from_existing_index(
connection_string="postgresql+psycopg2://user:password@localhost:5432/dbname",
embedding_function=OpenAIEmbeddings(),
collection_name="ruff",
)
state_of_union_info = VectorStoreInfo(
name="state_of_union_address",
description="the most recent state of the Union adress",
vectorstore=state_of_union_store,
)
ruff_info = VectorStoreInfo(
name="ruff",
description="Information about the Ruff python linting library",
vectorstore=ruff_store,
)
# Create the VectorStoreRouterToolkit instance
router_toolkit = VectorStoreRouterToolkit(
vectorstores=[state_of_union_info, ruff_info], llm=llm
)
# Create the agent
agent_executor = create_vectorstore_router_agent(
llm=llm, toolkit=router_toolkit, verbose=True
)In this example, the agent can route between two vectorstores: "state_of_union_address" and "ruff". When you run the agent with a question, it will route the question to the appropriate vectorstore based on the question's context.
You can find more information about this in the following documentation:
- docs/extras/modules/agents/how_to/agent_vectorstore.ipynb
- docs/extras/integrations/toolkits/vectorstore.ipynb
- libs/langchain/langchain/vectorstores/pgvector.py
I hope this helps! If you have any other questions, feel free to ask.
Best, Dosu
Sources
- toolkit.py in agent toolkits vectorstore has open ai implementation which restricts the usage of other LLMs. When I try to use Googlepalm, I get the open ai error.
- docs/extras/modules/agents/how_to/agent_vectorstore.ipynb
- docs/extras/integrations/toolkits/vectorstore.ipynb
- libs/langchain/langchain/vectorstores/pgvector.py
- libs/langchain/langchain/agents/openai_functions_agent/base.py
- libs/langchain/langchain/chat_models/openai.py
- libs/langchain/langchain/llms/openai.py
This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.
Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.
If you want to continue the conversation, start your reply with @dosu-bot.
Ajaypawar02
Issue you'd like to raise.
In my problem statement I am defining multiple tools which are all based on retrieval chain and I am using OpenAiAgent as the agent to call this tools. So when I am running a query it invokes to a single vectorstore. But I need my agent to access different vectorstores if the answer is not fetched from that particular vectorstore.I know the approach to get this working done by other agents.But I need this to be done by openaiAgent.
Suggestion:
No response