app.py

import gradio as gr
from langchain_community.document_loaders import PyPDFLoader
from langchain_huggingface import HuggingFaceEmbeddings
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_community.vectorstores import FAISS
from langchain_groq import ChatGroq
from langchain_core.prompts import ChatPromptTemplate
from langchain.chains import create_retrieval_chain
from langchain.chains.combine_documents import create_stuff_documents_chain
from dotenv import load_dotenv
import os

# Load environment variables
load_dotenv()
groq_api_key = os.getenv("GROQ_API_KEY")

# Initialize embedding model and LLM
embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
llm = ChatGroq(model_name="Llama3-8b-8192", groq_api_key=groq_api_key)

# Prompt template
prompt = ChatPromptTemplate.from_messages([
    ("system", "You are an assistant for question-answering tasks."
     "Answer the question in detail."
     "You are an assistant for question-answering tasks."
     "act as a Q/A chatbot."
     "answer concise and detailed."
     "\n\n"
     "{context}"
    ),
    ("human", "{input}")
])

# Store the chain globally
rag_chain = None

# Upload and process PDF
def handle_upload(pdf_file):
    global rag_chain
    try:
        loader = PyPDFLoader(pdf_file.name)
        docs = loader.load()
        splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=30)
        split_docs = splitter.split_documents(docs)
        vectorstore = FAISS.from_documents(split_docs, embeddings)
        retriever = vectorstore.as_retriever()
        qa_chain = create_stuff_documents_chain(llm, prompt)
        rag_chain = create_retrieval_chain(retriever, qa_chain)
        return "✅ PDF uploaded. Ask your question below."
    except Exception as e:
        return f"❌ Error: {str(e)}"

# Answer user question
def ask_question(question):
    if not rag_chain:
        return "⚠️ Please upload a PDF first."
    try:
        result = rag_chain.invoke({"input": question})
        return result["answer"]
    except Exception as e:
        return f"❌ Error generating answer: {str(e)}"

# Gradio UI
with gr.Blocks() as demo:
    gr.Markdown("## 🤖 Simple PDF Q&A ChatBot")
    with gr.Row():
        pdf_file = gr.File(label="📄 Upload PDF", file_types=[".pdf"])
        upload_btn = gr.Button("Upload")
    upload_status = gr.Textbox(label="Status", interactive=False)

    question = gr.Textbox(label="Ask a Question", placeholder="e.g., What is this paper about?")
    answer = gr.Textbox(label="Answer", lines=10)

    upload_btn.click(handle_upload, inputs=[pdf_file], outputs=[upload_status])
    question.submit(ask_question, inputs=question, outputs=answer)

# Run the app
demo.launch()