app.py

app_code = '''
import os
import streamlit as st
import tempfile
import fitz  # PyMuPDF
from sentence_transformers import SentenceTransformer
import faiss
import numpy as np
from groq import Groq

# Get API Key securely from Hugging Face Secrets
os.environ["GROQ_API_KEY"] = st.secrets["GROQ_API_KEY"]

# Initialize Groq client
client = Groq(api_key=os.environ.get("GROQ_API_KEY"))

# Load sentence transformer model
embed_model = SentenceTransformer("all-MiniLM-L6-v2")

# Text Chunking
def chunk_text(text, chunk_size=500, overlap=100):
    chunks = []
    start = 0
    while start < len(text):
        end = start + chunk_size
        chunks.append(text[start:end])
        start += chunk_size - overlap
    return chunks

# PDF Text Extraction
def extract_text_from_pdf(uploaded_file):
    text = ""
    with tempfile.NamedTemporaryFile(delete=False) as tmp_file:
        tmp_file.write(uploaded_file.read())
        doc = fitz.open(tmp_file.name)
        for page in doc:
            text += page.get_text()
    return text

# Build FAISS index
def build_faiss_index(chunks):
    embeddings = embed_model.encode(chunks)
    dim = embeddings.shape[1]
    index = faiss.IndexFlatL2(dim)
    index.add(np.array(embeddings))
    return index, embeddings

# Retrieve top-k chunks
def retrieve_chunks(query, chunks, index, embeddings, top_k=3):
    query_embed = embed_model.encode([query])
    D, I = index.search(np.array(query_embed), top_k)
    return [chunks[i] for i in I[0]]

# Ask Groq with context
def ask_groq(query, context):
    prompt = f"Context:\\n{context}\\n\\nQuestion: {query}"
    response = client.chat.completions.create(
        messages=[{"role": "user", "content": prompt}],
        model="llama-3-70b-8192",
    )
    return response.choices[0].message.content

# Streamlit App UI
st.title("🧠 PDF Q&A with RAG (Groq + FAISS)")

uploaded_file = st.file_uploader("Upload a PDF", type="pdf")
query = st.text_input("Ask a question about the PDF")

if uploaded_file:
    st.info("Processing PDF...")
    full_text = extract_text_from_pdf(uploaded_file)
    chunks = chunk_text(full_text)
    index, embeddings = build_faiss_index(chunks)
    st.success("PDF processed. Ask a question now.")

    if query:
        st.info("Retrieving relevant information...")
        top_chunks = retrieve_chunks(query, chunks, index, embeddings)
        context = "\\n\\n".join(top_chunks)
        response = ask_groq(query, context)
        st.markdown("### 💬 Answer")
        st.write(response)
'''
with open("app.py", "w") as f:
    f.write(app_code)