LangChain FAISS throws 'list' object has no attribute 'as_retriever'

[seahyuhuai]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

import os
from openai import OpenAI
import streamlit as st
from dotenv import load_dotenv 
from PyPDF2 import PdfReader
from langchain.text_splitter import CharacterTextSplitter
from langchain_openai import OpenAIEmbeddings
from langchain.vectorstores import FAISS
from langchain_openai import ChatOpenAI
from langchain.memory import ConversationBufferMemory
from langchain.chains.conversational_retrieval.base import ConversationalRetrievalChain
from langchain.callbacks import get_openai_callback


def get_pdf_text(pdf_docs):
    text = "" #initialise variable
    #loop all pdf and read them, take content, concatenate
    for pdf in pdf_docs:
        pdf_reader = PdfReader(pdf) #initiate PDF object that has pages
        #loop through the pages, read each pages and add to the text
        for page in pdf_reader.pages:
            text += page.extract_text() #extract all raw text from this pdf
    return text

def get_text_chunks(text):
    text_splitter = CharacterTextSplitter(
        separator="\n",
        chunk_size=1000,
        chunk_overlap=200,
        length_function=len
    )
    chunks = text_splitter.split_text(text)
    return chunks

def get_vectorstore(text_chunks):
    embeddings = OpenAIEmbeddings(model="text-embedding-3-large")
    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
    vectorstore.save_local("faiss_index")
    return vectorstore

def get_conversation_chain(vectorstore):
    llm = ChatOpenAI()
    memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)
    conversation_chain = ConversationalRetrievalChain.from_llm(
        llm=llm,
        retriever=vectorstore.as_retriever(),
        memory=memory
    )
    return conversation_chain

def user_input(user_question):
    embeddings = OpenAIEmbeddings(model = "text-embedding-3-large")
    
    new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
    docs = new_db.similarity_search(user_question)

    chain = get_conversation_chain(docs)

    
    response = chain(
        {"input_documents":docs, "question": user_question}
        , return_only_outputs=True)

    print(response)
    st.write("Reply: ", response["output_text"])

    with get_openai_callback() as cost:
        response = chain.invoke(input={"question": user_question, "input_documents":docs})
        print(cost)


def main():
    load_dotenv()
    
    st.set_page_config(page_title="Chat with multiple PDFs", page_icon=":books")

    if "conversation" not in st.session_state:
        st.session_state.conversation = None
    
    if "chat_history" not in st.session_state:
        st.session_state.chat_history = None

    st.header("Chat with multiple PDFs :books:")
    user_question = st.text_input("Ask a question about your documents")

    if user_question:
        user_input(user_question)

    with st.sidebar:
        st.subheader("Your documents")
        pdf_docs = st.file_uploader(
            "Upload your PDFs here and click on 'Process'", accept_multiple_files=True)
        if st.button("Process"):
            with st.spinner("Processing"):
                #get pdf text
                raw_text = get_pdf_text(pdf_docs)
                #get text chunks
                text_chunks = get_text_chunks(raw_text)
                #create vector store
                vectorstore = get_vectorstore(text_chunks)
                #create conversation chain
                conversation = get_conversation_chain(vectorstore)

if __name__ == "__main__":
    main()

Description

I tried to run the code, I was able to upload the PDF files successfully, however the error appears after I try to query the system as it attempts to retrieve from the vectorstore

`

`AttributeError: 'list' object has no attribute 'as_retriever'

`

This error occurs at the function get_conversation_chain(vectorstore)

Any advice on what happened here and how i can solve it?

System Info

langchain-core<1.0.0,>=0.3.39: Installed.
windows
python 3.12.7