app.py

import os
import gradio as gr
from langchain_community.vectorstores import FAISS
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain_community.document_loaders import PyPDFLoader
from langchain_groq import ChatGroq
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.chains import RetrievalQA
from langchain.docstore.document import Document
import nbformat

# Load Groq API Key securely
os.environ["GROQ_API_KEY"] = os.getenv("GROQ_API_KEY")

# Helper: Read .ipynb file and extract text
def load_ipynb(file):
    try:
        with open(file.name, "r", encoding="utf-8") as f:
            nb = nbformat.read(f, as_version=nbformat.NO_CONVERT)
            text = ""
            for cell in nb.cells:
                if cell.cell_type in ["markdown", "code"]:
                    text += cell.source + "\n\n"
            return [Document(page_content=text)]
    except Exception as e:
        print("Error loading .ipynb:", e)
        return []

# Helper: Read PDF or IPYNB and build retriever chain
def process_files(files):
    try:
        all_docs = []
        for file in files:
            if file.name.endswith(".pdf"):
                loader = PyPDFLoader(file.name)
                all_docs.extend(loader.load())
            elif file.name.endswith(".ipynb"):
                all_docs.extend(load_ipynb(file))

        splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
        chunks = splitter.split_documents(all_docs)

        embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
        vectorstore = FAISS.from_documents(chunks, embeddings)
        retriever = vectorstore.as_retriever()

        llm = ChatGroq(model_name="llama3-70b-8192", temperature=0)
        qa_chain = RetrievalQA.from_chain_type(llm=llm, retriever=retriever)
        return qa_chain
    except Exception as e:
        print("Error in processing files:", e)
        return None

# Global chain
qa_chain = None

def upload_docs(files):
    global qa_chain
    qa_chain = process_files(files)
    if qa_chain is None:
        return "❌ Error processing files. Please make sure the file format is correct."
    return "✅ PDFs or Notebooks uploaded and processed. Now ask your questions."

def ask_question(query):
    if qa_chain is None:
        return "❌ Please upload PDFs or Kaggle Notebooks first."
    try:
        return qa_chain.run(query)
    except Exception as e:
        return f"⚠ Error answering question: {e}"

# Gradio UI
with gr.Blocks() as app:
    gr.Markdown("## 🤖 Kaggle Study Assistant\nUpload Kaggle `.pdf` or `.ipynb` files and ask intelligent questions.")

    with gr.Row():
        upload = gr.File(file_types=[".pdf", ".ipynb"], file_count="multiple", label="Upload Kaggle Files")
        btn_upload = gr.Button("📥 Process Files")

    upload_output = gr.Textbox(label="Upload Status")
    btn_upload.click(fn=upload_docs, inputs=upload, outputs=upload_output)

    question = gr.Textbox(label="Ask a question about uploaded notebooks")
    answer = gr.Textbox(label="Assistant Answer", interactive=False)
    question.submit(fn=ask_question, inputs=question, outputs=answer)

app.launch()