app.py

import gradio as gr
import os
import requests
from pypdf import PdfReader
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity

# ==============================
# GROQ API SETUP
# ==============================

GROQ_API_KEY = os.environ.get("GROQ_API_KEY")

API_URL = "https://api.groq.com/openai/v1/chat/completions"

# ==============================
# MEMORY STORAGE
# ==============================

documents = []
vectorizer = TfidfVectorizer(stop_words="english")
doc_vectors = None

# ==============================
# SAFE PDF READING (HF Compatible)
# ==============================

def extract_text_from_pdf(file_obj):
    text = ""
    reader = PdfReader(file_obj)

    for page in reader.pages:
        content = page.extract_text()
        if content:
            text += content

    return text

# ==============================
# TEXT CHUNKING
# ==============================

def chunk_text(text, chunk_size=400):
    words = text.split()
    return [" ".join(words[i:i+chunk_size]) for i in range(0, len(words), chunk_size)]

# ==============================
# PROCESS MULTIPLE FILES
# ==============================

def upload_files(files):
    global documents, doc_vectors

    if not files:
        return "⚠️ Please upload files."

    added_chunks = 0

    try:
        for file in files:
            text = extract_text_from_pdf(file)

            if not text.strip():
                continue

            chunks = chunk_text(text)
            documents.extend(chunks)
            added_chunks += len(chunks)

        if not documents:
            return "❌ No readable text found in PDFs."

        doc_vectors = vectorizer.fit_transform(documents)

        return f"✅ Files processed successfully! Added {added_chunks} study sections."

    except Exception as e:
        return f"❌ Error while processing files: {str(e)}"

# ==============================
# SEARCH CONTEXT
# ==============================

def retrieve_context(question, top_k=3):
    global doc_vectors

    if doc_vectors is None or len(documents) == 0:
        return None

    q_vec = vectorizer.transform([question])
    similarity = cosine_similarity(q_vec, doc_vectors).flatten()

    top_indices = similarity.argsort()[-top_k:][::-1]
    context = "\n\n".join([documents[i] for i in top_indices])

    return context

# ==============================
# GROQ CALL (WITH ERROR HANDLING)
# ==============================

def ask_ai(question):
    if not GROQ_API_KEY:
        return "❌ GROQ_API_KEY not set in Space Secrets."

    context = retrieve_context(question)

    if context is None:
        return "⚠️ Upload study material first."

    prompt = f"""
Answer ONLY using this study material.

Material:
{context}

Question:
{question}
"""

    headers = {
        "Authorization": f"Bearer {GROQ_API_KEY}",
        "Content-Type": "application/json"
    }

    payload = {
        "model": "llama3-8b-8192",
        "messages": [{"role": "user", "content": prompt}],
        "temperature": 0.2
    }

    try:
        response = requests.post(API_URL, headers=headers, json=payload, timeout=60)

        if response.status_code != 200:
            return f"❌ Groq API Error: {response.text}"

        result = response.json()
        return result["choices"][0]["message"]["content"]

    except Exception as e:
        return f"❌ Connection Error: {str(e)}"

# ==============================
# RESET LIBRARY
# ==============================

def reset_library():
    global documents, doc_vectors
    documents = []
    doc_vectors = None
    return "🗑 Library cleared."

# ==============================
# UI
# ==============================

with gr.Blocks(title="AI StudyHub") as app:

    gr.Markdown("# 🎓 AI StudyHub")
    gr.Markdown("Upload books → Ask questions → AI learns from YOUR material.")

    with gr.Tab("📚 Upload Study Material"):
        file_input = gr.File(file_types=[".pdf"], file_count="multiple")
        upload_btn = gr.Button("Process Files")
        reset_btn = gr.Button("Reset Library")
        status = gr.Textbox(label="Status")

        upload_btn.click(upload_files, inputs=file_input, outputs=status)
        reset_btn.click(reset_library, outputs=status)

    with gr.Tab("🤖 Ask AI"):
        question = gr.Textbox(label="Ask a question from your notes")
        ask_btn = gr.Button("Ask")
        answer = gr.Textbox(label="Answer", lines=12)

        ask_btn.click(ask_ai, inputs=question, outputs=answer)

app.launch()