app.py

import streamlit as st
from dotenv import load_dotenv
from PyPDF2 import PdfReader
import langchain
from htmlTemplates import css,bot_template,user_template,url,aiLogoUrl

cohere_api_key="gf0VDS934ffUjm9XYGR7WBDyqVL9RPWI6CINzLje"
def get_pdf_text(pdf_docs):
    text = ""
    for pdf in pdf_docs:
        pdfReader = PdfReader(pdf)
        for Page in pdfReader.pages:
            text += Page.extract_text()
    return text

def get_text_chunks(text):
    text_splitter = langchain.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 = langchain.embeddings.CohereEmbeddings()
    vectorstore = langchain.vectorstores.FAISS.from_texts(texts=text_chunks,embedding=embeddings)
    return vectorstore


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


def handle_userinput(user_question):
    response = st.session_state.conversation({'question':user_question})
    st.session_state.chat_history = response['chat_history']

    for i,message in enumerate(st.session_state.chat_history):
        if i % 2 == 0:
            st.write(user_template.replace("{{MSG}}",message.content), unsafe_allow_html=True)
        else:
            st.write(bot_template.replace("{{MSG}}", message.content), unsafe_allow_html=True)

def main():
    load_dotenv()
    st.set_page_config(page_title="Chat with multiple pdfs", page_icon=":books:")
    st.write(css,unsafe_allow_html=True)
    st.markdown(
        '<div class="logo-container"><img class="logo" src="' + url + '" /><img class="logo" src="' + aiLogoUrl + '" /></div>',
        unsafe_allow_html=True)


    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:
        handle_userinput(user_question)


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

                # get the text chunks
                text_chunks = get_text_chunks(raw_text)

                # create vector store
                vectorstore = get_vectorstore(text_chunks)

                # create conversation chai

                st.session_state.conversation = get_conversation_chain(vectorstore)

if __name__=='__main__':
    main()