app.py

import streamlit as st
from streamlit_chat import message
from langchain.chains import ConversationalRetrievalChain
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.llms import CTransformers
from langchain.llms import Replicate
from langchain.text_splitter import CharacterTextSplitter
from langchain.vectorstores import FAISS
from langchain.memory import ConversationBufferMemory
from langchain.document_loaders import PyPDFLoader, UnstructuredFileLoader
from langchain.document_loaders import TextLoader
from langchain.document_loaders import Docx2txtLoader
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
from langchain.text_splitter import Language, RecursiveCharacterTextSplitter
import os
from dotenv import load_dotenv
import tempfile
from concurrent.futures import ProcessPoolExecutor, ThreadPoolExecutor, as_completed
from constants import (
    CHROMA_SETTINGS,
    DOCUMENT_MAP,
    EMBEDDING_MODEL_NAME,
    INGEST_THREADS,
    PERSIST_DIRECTORY,
    SOURCE_DIRECTORY,
)
from langchain.docstore.document import Document
load_dotenv()


def initialize_session_state():
    if 'history' not in st.session_state:
        st.session_state['history'] = []

    if 'generated' not in st.session_state:
        st.session_state['generated'] = ["Hello! Ask me anything about 🤗"]

    if 'past' not in st.session_state:
        st.session_state['past'] = ["Hey! 👋"]

def conversation_chat(query, chain, history):
    result = chain({"question": query, "chat_history": history})
    history.append((query, result["answer"]))
    return result["answer"]

def display_chat_history(chain):
    reply_container = st.container()
    container = st.container()

    with container:
        with st.form(key='my_form', clear_on_submit=True):
            user_input = st.text_input("Question:", placeholder="Ask about your Documents", key='input')
            submit_button = st.form_submit_button(label='Send')

        if submit_button and user_input:
            with st.spinner('Generating response...'):
                output = conversation_chat(user_input, chain, st.session_state['history'])

            st.session_state['past'].append(user_input)
            st.session_state['generated'].append(output)

    if st.session_state['generated']:
        with reply_container:
            for i in range(len(st.session_state['generated'])):
                message(st.session_state["past"][i], is_user=True, key=str(i) + '_user', avatar_style="thumbs")
                message(st.session_state["generated"][i], key=str(i), avatar_style="fun-emoji")


def create_conversational_chain(vector_store):
    load_dotenv()
    llm = Replicate(
        streaming = True,
        # model = "replicate/llama-2-70b-chat:58d078176e02c219e11eb4da5a02a7830a283b14cf8f94537af893ccff5ee781",
        model = "meta/llama-2-7b-chat:8e6975e5ed6174911a6ff3d60540dfd4844201974602551e10e9e87ab143d81e",
        callbacks=[StreamingStdOutCallbackHandler()],
        input = {"temperature": 0.01, "max_length" :500,"top_p":1})
    memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)

    chain = ConversationalRetrievalChain.from_llm(llm=llm, chain_type='stuff',
                                                 retriever=vector_store.as_retriever(search_kwargs={"k": 2}),
                                                 memory=memory)
    return chain

file_paths = [
    './SOURCE_DOCUMENTS/Freedom of Information and Protection of Privacy Act, R.S.O. 1990, c. F.31[462] - Copy.pdf',
    './SOURCE_DOCUMENTS/Highway Traffic Act, R.S.O. 1990, c. H.8[465] - Copy.pdf',
    './SOURCE_DOCUMENTS/Narcotics Safety and Awareness Act, 2010, S.O. 2010, c. 22[463].pdf',
    './SOURCE_DOCUMENTS/Nutrient Management Act, 2002, S.O. 2002, c. 4[464].pdf'
    # Add more file paths as needed
]

def main():
    # load_dotenv()
    os.environ.get("REPLICATE_API_TOKEN")
    # Initialize session state
    initialize_session_state()
    st.title("Multi-Docs ChatBot using llama-2-7b :books:")
    # loader = UnstructuredFileLoader('./SOURCE_DOCUMENTS/Freedom of Information and Protection of Privacy Act, R.S.O. 1990, c. F.31[462] - Copy.pdf')
    # documents = loader.load()
    documents = []
    for file_path in file_paths:
        loader = UnstructuredFileLoader(file_path)
        loaded_doc = loader.load()  # Assuming this returns a list of pages
        documents.extend(loaded_doc)

    text_splitter=CharacterTextSplitter(separator='\n',
                                    chunk_size=1500,
                                    chunk_overlap=300)
    text_chunks=text_splitter.split_documents(documents)

    embeddings = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2',model_kwargs={'device': 'cpu'})

    vector_store=FAISS.from_documents(text_chunks, embeddings)

# Create the chain object
    chain = create_conversational_chain(vector_store)

# Display chat history
    display_chat_history(chain)


if __name__ == "__main__":
    main()