src/get_vector.py

import streamlit as st
from langchain_community.document_loaders import WebBaseLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.vectorstores import Chroma
from langchain_openai import OpenAIEmbeddings, ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain.chains import create_history_aware_retriever,create_retrieval_chain
from langchain.chains.combine_documents import create_stuff_documents_chain
from dotenv import load_dotenv
import os

load_dotenv()
KEY=os.getenv("MY_KEY")


def get_vectorstore_from_url(url):
    # get the text in document form
    loader = WebBaseLoader(url)
    document = loader.load()
    
    # split the document into chunks
    text_splitter = RecursiveCharacterTextSplitter(chunk_size=200,
                                                chunk_overlap=10,
                                                length_function=len)
    document_chunks = text_splitter.split_documents(document)
    
    # create a vectorstore from the chunks
    vector_store = Chroma.from_documents(document_chunks,
                                          OpenAIEmbeddings(openai_api_key=KEY))

    return vector_store

def get_response(user_input):
    retriever_chain = get_context_retriever_chain(st.session_state.vector_store)
    conversation_rag_chain = get_conversational_rag_chain(retriever_chain)
    
    response = conversation_rag_chain.invoke({
        "chat_history": st.session_state.chat_history,
        "input": user_input
    })
    
    return response['answer']


def get_context_retriever_chain(vector_store):
    llm = ChatOpenAI(openai_api_key=KEY)
    
    retriever = vector_store.as_retriever()
    
    prompt = ChatPromptTemplate.from_messages([
      MessagesPlaceholder(variable_name="chat_history"),
      ("user", "{input}"),
      ("user", "Given the above conversation, generate a search query to look up in order to get information relevant to the conversation")
    ])
    
    retriever_chain = create_history_aware_retriever(llm, retriever, prompt)
    
    return retriever_chain

def get_conversational_rag_chain(retriever_chain): 
    
    llm = ChatOpenAI(openai_api_key=KEY)
    
    prompt = ChatPromptTemplate.from_messages([
      ("system", "Answer the user's questions based on the below context:\n\n{context}"),
      MessagesPlaceholder(variable_name="chat_history"),
      ("user", "{input}"),
    ])
    
    stuff_documents_chain = create_stuff_documents_chain(llm,prompt)
    
    return create_retrieval_chain(retriever_chain, stuff_documents_chain)