[FIXED] How to use embeddings as vector_store in Langchain?

Issue

i'm trying to create a chatbot using OpenAi Langchain and a cloud database (MongoDb in my case). What I do, is load a PDF, I read the data, create chunks from it and then create embeddings using "text-embedding-ada-002" by OpenAi. After that I store in my DB the filename, the text of the PDF the list of embeddings, and the list of messages. It works good, but the problem is that i want to load the list of embeddings to create the Conversation Chain, but i don't know if it is possible to create it from the list of embeddings of i should save another thing and not the list of embeddings, because i don't want to create them each time i open the chat of the current PDf

If i use something like this to generate the vector store and then run the below code to create the conversation chain it works, but i want to load the list of embeddings i saved in the db

def get_embeddings(chunks: list[str]):
    embeddings = OpenAIEmbeddings()
    vector_store = MongoDBAtlasVectorSearch.from_texts(
        texts=chunks,
        embedding=embeddings,
        collection=embeddings_collection,
        index_name=ATLAS_VECTOR_SEARCH_INDEX_NAME,
    )
    return vector_store

def get_conversation_chain(vector_store):
    memory = ConversationBufferMemory(
        memory_key="chat_history",
        vector_store=vector_store,
        similarity_threshold=0.8,
        max_memory_size=100,
        return_messages=True,
        input_key="question")
    conversation_chain = ConversationalRetrievalChain.from_llm(
        retriever=vector_store.as_retriever(),
        llm=llm,  
        memory=memory)
    result = conversation_chain({"question": "what is the text about"})
    print(result)
    return conversation_chain

Is there a way to create a vector_store from the list of embeddings i saved? or should i use another type of conversation chain?

Solution

Langchain has integration with Mongo db atlas, check this tutorial: https://python.langchain.com/docs/integrations/vectorstores/mongodb_atlas

Alternatively, you try using vector databases for this. Use ChromaDB or Pinecone to store vectors and store other information in metadata.

Answered By - Nikoloz Naskidashvili