app.py

import os
import streamlit as st
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import Chroma
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.chat_models import ChatOpenAI
from langchain.chains import ConversationalRetrievalChain
from langchain.memory import ConversationBufferMemory
from langchain.document_loaders import PyPDFLoader

# Initialize session state variables
if "messages" not in st.session_state:
    st.session_state.messages = []
if "chain" not in st.session_state:
    st.session_state.chain = None
if "processed_pdfs" not in st.session_state:
    st.session_state.processed_pdfs = False

def create_sidebar():
    with st.sidebar:
        st.title("PDF Chat")
        st.markdown("### Quick Demo of RAG")
        api_key = st.text_input("OpenAI API Key:", type="password")
        st.markdown("""
        ### Tools Used
        - OpenAI
        - LangChain
        - ChromaDB
        
        ### Steps
        1. Add API key
        2. Upload PDF
        3. Chat!
        """)
        return api_key

def process_pdfs(papers, api_key):
    if papers and not st.session_state.processed_pdfs:
        with st.spinner("Processing PDFs..."):
            texts = []
            for paper in papers:
                try:
                    file_path = os.path.join('./uploads', paper.name)
                    os.makedirs('./uploads', exist_ok=True)
                    with open(file_path, "wb") as f:
                        f.write(paper.getbuffer())
                    
                    loader = PyPDFLoader(file_path)
                    documents = loader.load()
                    text_splitter = RecursiveCharacterTextSplitter(
                        chunk_size=1000,
                        chunk_overlap=200,
                        length_function=len,
                        is_separator_regex=False,
                    )
                    texts.extend(text_splitter.split_documents(documents))
                    os.remove(file_path)
                except Exception as e:
                    st.error(f"Error processing {paper.name}: {str(e)}")
            
            if texts:
                embedding = OpenAIEmbeddings(openai_api_key=api_key)
                vectorstore = Chroma(embedding_function=embedding, persist_directory="db")
                vectorstore.add_documents(texts)
                
                st.session_state.chain = ConversationalRetrievalChain.from_llm(
                    ChatOpenAI(temperature=0, model_name="gpt-3.5-turbo", openai_api_key=api_key),
                    vectorstore.as_retriever(),
                    memory=ConversationBufferMemory(
                        memory_key="chat_history",
                        return_messages=True
                    )
                )
                st.session_state.processed_pdfs = True
                st.success("PDFs processed successfully!")
            return texts
    return []

def main():
    st.set_page_config(page_title="PDF Chat")
    
    # Sidebar with API key input
    api_key = create_sidebar()
    
    if not api_key:
        st.warning("Please enter your OpenAI API key")
        return

    st.title("Chat with PDF")
    
    # File uploader
    papers = st.file_uploader("Upload PDFs", type=["pdf"], accept_multiple_files=True)
    
    # Process PDFs if needed
    texts = process_pdfs(papers, api_key)
    
    # Display chat messages from history
    for message in st.session_state.messages:
        with st.chat_message(message["role"]):
            st.markdown(message["content"])
    
    # Accept user input
    if prompt := st.chat_input("Ask about your PDFs"):
        # Add user message to chat history
        st.session_state.messages.append({"role": "user", "content": prompt})
        
        # Display user message
        with st.chat_message("user"):
            st.markdown(prompt)
            
        # Generate and display assistant response
        with st.chat_message("assistant"):
            if not st.session_state.processed_pdfs:
                response = "Please upload a PDF first."
            else:
                with st.spinner("Thinking..."):
                    result = st.session_state.chain({"question": prompt})
                    response = result["answer"]
            
            st.markdown(response)
            st.session_state.messages.append({"role": "assistant", "content": response})

if __name__ == "__main__":
    main()