app.py

import os
import tempfile
import streamlit as st
from langchain.document_loaders import PyPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import FAISS
from langchain.chains import RetrievalQA
from langchain.chat_models import ChatOpenAI

# Streamlit App Title
st.title("📄 DeepSeek-Powered RAG Chatbot")

# Step 1: Input API Key
api_key = st.text_input("🔑 Enter your DeepSeek API Key:", type="password")

if api_key:
    # Set the API key as an environment variable (optional)
    os.environ["DEEPSEEK_API_KEY"] = api_key

    # Step 2: Upload PDF Document
    uploaded_file = st.file_uploader("📂 Upload a PDF document", type=["pdf"])

    if uploaded_file:
        # Load and process the document
        try:
            with st.spinner("Processing document..."):
                # Save the uploaded file temporarily
                with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp_file:
                    tmp_file.write(uploaded_file.getvalue())
                    tmp_file_path = tmp_file.name

                # Use the temporary file path with PyPDFLoader
                loader = PyPDFLoader(tmp_file_path)
                documents = loader.load()

                # Remove the temporary file
                os.unlink(tmp_file_path)

                # Split the document into chunks
                text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
                chunks = text_splitter.split_documents(documents)

                # Generate embeddings and store them in a vector database
                embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
                vector_store = FAISS.from_documents(chunks, embeddings)

            st.success("Document processed successfully!")
        except Exception as e:
            st.error(f"Error processing document: {e}")
            st.stop()

        # Step 3: Ask Questions About the Document
        st.subheader("💬 Chat with Your Document")
        user_query = st.text_input("Ask a question:")

        if user_query:
            try:
                # Set up the RAG pipeline with DeepSeek LLM
                retriever = vector_store.as_retriever()
                llm = ChatOpenAI(
                    model="deepseek-chat",
                    openai_api_key=api_key,
                    openai_api_base="https://api.deepseek.com/v1",
                    temperature=0.85,
                    max_tokens=1000  # Adjust token limit for safety
                )
                qa_chain = RetrievalQA.from_chain_type(llm=llm, retriever=retriever)

                # Generate response
                with st.spinner("Generating response..."):
                    response = qa_chain.run(user_query)
                    st.write(f"**Answer:** {response}")
            except Exception as e:
                st.error(f"Error generating response: {e}")
else:
    st.warning("Please enter your DeepSeek API key to proceed.")