app.py

import streamlit as st
from dotenv import load_dotenv
from PyPDF2 import PdfReader
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores import FAISS
from langchain.chat_models import ChatOpenAI
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain

def get_pdf_text(pdf_docs):
    text=""
    for pdf in pdf_docs:
        pdf_reader= PdfReader(pdf)
        for page in pdf_reader.pages:
            text+= page.extract_text()
    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_vectorstores(text_chunks):
    embeddings= OpenAIEmbeddings()
    # embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
    vectorstore= FAISS.from_text(texts=text_chunks, embedding=embeddings)

def get_conversation_chain(vectorstore):
    llm = ChatOpenAI()
    # llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.5, "max_length":512})
    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 main():
    st.set_page_config(page_title="Chat", page_icon=":books:")

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

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

    with st.sidebar:
        st.subheader("Your documents")
        pdf_docs = st.file_uploader("Upload your docs here", accept_multiple_files=True)
        if st.button("Process"):
            with st.spinner("Processing"):
                # get pdf text, contents
                raw_text = get_pdf_text(pdf_docs)
                # st.write(raw_text)

                # 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)
                st.session_state.conversation = get_conversation_chain(vectorstore)                


if __name__ == "__main__":
    main()



# Instructor embeddings
# InstructorEmbedding==1.0.1
# sentence-transformers==2.2.2