app.py

import streamlit as st
from dotenv import load_dotenv
from PyPDF2 import PdfReader
from langchain.text_splitter import CharacterTextSplitter, RecursiveCharacterTextSplitter
from langchain.embeddings import OpenAIEmbeddings, HuggingFaceInstructEmbeddings
from langchain.vectorstores import FAISS, Chroma
from langchain.embeddings import HuggingFaceEmbeddings  # General embeddings from HuggingFace models.
from langchain.chat_models import ChatOpenAI
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from htmlTemplates import css, bot_template, user_template
from langchain.llms import HuggingFaceHub, LlamaCpp, CTransformers  # For loading transformer models.
from langchain.document_loaders import PyPDFLoader, TextLoader, JSONLoader, CSVLoader
from tempfile import NamedTemporaryFile
import os


def get_pdf_text(pdf_docs):
    with NamedTemporaryFile() as temp_file:
        temp_file.write(pdf_docs.getvalue())
        temp_file.seek(0)
        pdf_loader = PyPDFLoader(temp_file.name)
        # print('pdf_loader = ', pdf_loader)
        pdf_doc = pdf_loader.load()
        # print('pdf_doc = ',pdf_doc)
        return pdf_doc


def get_text_file(docs):
    with NamedTemporaryFile() as temp_file:
        temp_file.write(docs.getvalue())
        temp_file.seek(0)
        text_loader = TextLoader(temp_file.name)
        text_doc = text_loader.load()

        return text_doc


def get_csv_file(docs):
    with NamedTemporaryFile() as temp_file:
        temp_file.write(docs.getvalue())
        temp_file.seek(0)
        text_loader = CSVLoader(temp_file.name)
        text_doc = text_loader.load()

        return text_doc


def get_json_file(docs):
    with NamedTemporaryFile() as temp_file:
        temp_file.write(docs.getvalue())
        temp_file.seek(0)
        json_loader = JSONLoader(temp_file.name,
                                 jq_schema='.scans[].relationships',
                                 text_content=False)
        json_doc = json_loader.load()

        return json_doc


def get_text_chunks(documents):
    text_splitter = RecursiveCharacterTextSplitter(
        chunk_size=1000,
        chunk_overlap=200,
        length_function=len
    )

    documents = text_splitter.split_documents(documents)
    return documents


def get_vectorstore(text_chunks):
    # Load the desired embeddings model.

    embeddings = OpenAIEmbeddings()
    vectorstore = FAISS.from_documents(text_chunks, embeddings)

    return vectorstore


def get_conversation_chain(vectorstore):
    gpt_model_name = 'gpt-3.5-turbo'
    llm = ChatOpenAI(model_name = gpt_model_name)
    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 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)

    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:
        openai_key = st.text_input("Paste your OpenAI API key (sk-...)")
        if openai_key:
            os.environ["OPENAI_API_KEY"] = openai_key

        st.subheader("Your documents")
        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
                doc_list = []

                for file in docs:
                    print('file - type : ', file.type)
                    if file.type == 'text/plain':
                        # file is .txt
                        doc_list.extend(get_text_file(file))
                    elif file.type in ['application/octet-stream', 'application/pdf']:
                        # file is .pdf
                        doc_list.extend(get_pdf_text(file))
                    elif file.type == 'text/csv':
                        # file is .csv
                        doc_list.extend(get_csv_file(file))
                    elif file.type == 'application/json':
                        # file is .json
                        doc_list.extend(get_json_file(file))

                # get the text chunks
                text_chunks = get_text_chunks(doc_list)

                # create vector store
                vectorstore = get_vectorstore(text_chunks)

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


if __name__ == '__main__':
    main()