app.py

import os
import streamlit as st
from dotenv import load_dotenv
from PyPDF2 import PdfReader
from langchain.text_splitter import CharacterTextSplitter
#from langchain_community.embeddings import HuggingFaceInstructEmbeddings
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain_community.vectorstores import FAISS
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from langchain_community.llms import HuggingFacePipeline
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer, pipeline

# Load custom HTML templates
css = """
<style>
@import url('https://fonts.googleapis.com/css2?family=Source+Sans+Pro:wght@400;600&display=swap');

.chat-message {
    font-family: 'Source Sans Pro', sans-serif; padding: 1.5rem; border-radius: 0.5rem; margin-bottom: 1rem; display: flex
}
.chat-message.user {
    background-color: #2b313e
}
.chat-message.bot {
    background-color: #475063
}
.chat-message .avatar {
  width: 20%;
}
.chat-message .avatar img {
  max-width: 78px;
  max-height: 78px;
  border-radius: 50%;
  object-fit: cover;
}
.chat-message .message {
  width: 80%;
  padding: 0 1.5rem;
  color: #fff;
}
</style>
"""

bot_template = """
<div class="chat-message bot">
    <div class="avatar">
        <img src="https://i.ibb.co/cN0nmSj/Screenshot-2023-05-28-at-02-37-21.png" style="max-height: 78px; max-width: 78px; border-radius: 50%; object-fit: cover;">
    </div>
    <div class="message">{{MSG}}</div>
</div>
"""

user_template = """
<div class="chat-message user">
    <div class="avatar">
        <img src="https://i.ibb.co/rdZC7LZ/Photo-logo-1.png">
    </div>    
    <div class="message">{{MSG}}</div>
</div>
"""

# Load the Hugging Face API token from environment variables
load_dotenv()
hf_token = os.getenv("HUGGINGFACE_API_TOKEN")

if hf_token is None:
    raise ValueError("Hugging Face API Token not found. Please make sure it's stored as a secret in Hugging Face.")

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):
    if not text.strip():
        raise ValueError("No text extracted from PDFs")
        
    text_splitter = CharacterTextSplitter(
        separator="\n",
        chunk_size=1000,
        chunk_overlap=200,
        length_function=len
    )
    return text_splitter.split_text(text)

def get_vectorstore(text_chunks):
    # Using simpler embeddings model
    embeddings = HuggingFaceEmbeddings(
        model_name="sentence-transformers/all-MiniLM-L6-v2",
        model_kwargs={"device": "cpu"}  # Force CPU usage
    )
    return FAISS.from_texts(texts=text_chunks, embedding=embeddings)

def get_conversation_chain(vectorstore):
    try:
        # Option 1: Use local pipeline (more reliable)
        model_name = "google/flan-t5-small"  # Smallest working version
        tokenizer = AutoTokenizer.from_pretrained(model_name)
        model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
        
        pipe = pipeline(
            "text2text-generation",
            model=model,
            tokenizer=tokenizer,
            max_length=512,
            temperature=0.5,
            device="cpu"  # Force CPU usage
        )
        
        llm = HuggingFacePipeline(pipeline=pipe)
        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
    except Exception as e:
        st.error(f"Failed to initialize LLM: {str(e)}")
        return None

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():
    st.set_page_config(page_title="Chat with multiple PDFs", page_icon=":books:")
    st.write(css, unsafe_allow_html=True)

    st.header("Chat with multiple PDFs :books:")

    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

    user_question = st.text_input("Ask a question about your documents:")

    if user_question and st.session_state.conversation:
        handle_userinput(user_question)

    with st.sidebar:
        st.subheader("Your documents")
        pdf_docs = st.file_uploader("Upload your PDFs here and click on 'Process'", accept_multiple_files=True)

        if st.button("Process"):
            with st.spinner("Processing..."):
                raw_text = get_pdf_text(pdf_docs)
                text_chunks = get_text_chunks(raw_text)
                vectorstore = get_vectorstore(text_chunks)
                st.session_state.conversation = get_conversation_chain(vectorstore)
                st.success("Documents processed! You can now chat.")

if __name__ == "__main__":
    main()