app.py

import os
import re
import tempfile
from datetime import datetime
import gradio as gr
from transformers import pipeline
import pdfplumber
from gtts import gTTS
import nltk
import numpy as np
from sklearn.feature_extraction.text import TfidfVectorizer

# ==========================================================
# 🧠 NLTK Setup (Fixed punkt_tab Issue)
# ==========================================================
for pkg in ["punkt", "punkt_tab"]:
    try:
        nltk.data.find(f"tokenizers/{pkg}")
    except LookupError:
        nltk.download(pkg)

# ==========================================================
# ⚙️ Model Setup
# ==========================================================
DEVICE = -1  # CPU (-1), use 0 for GPU if available
SUMMARIZER_MODEL = "facebook/bart-large-cnn"
QA_MODEL = "deepset/roberta-base-squad2"

print("Loading models... please wait ⏳")

try:
    summarizer = pipeline("summarization", model=SUMMARIZER_MODEL, device=DEVICE)
    qa_pipeline = pipeline("question-answering", model=QA_MODEL, device=DEVICE)
except Exception as e:
    print("Model load error:", e)
    summarizer = None
    qa_pipeline = None


# ==========================================================
# 🧩 Utility Functions
# ==========================================================
def clean_text(text: str) -> str:
    text = re.sub(r'\r\n?', '\n', text)
    text = re.sub(r'\n{2,}', '\n\n', text)
    text = re.sub(r'References[\s\S]*', '', text, flags=re.IGNORECASE)
    text = re.sub(r'[^\x00-\x7F]+', ' ', text)
    text = re.sub(r'\s+', ' ', text)
    return text.strip()


def extract_text_from_pdf(path: str) -> str:
    try:
        text = ""
        with pdfplumber.open(path) as pdf:
            for page in pdf.pages:
                page_text = page.extract_text()
                if page_text:
                    text += page_text + "\n\n"
        return text.strip() if text.strip() else "No text extracted from PDF."
    except Exception as e:
        return f"Error extracting text: {e}"


def sentence_tokenize(text: str):
    return [s.strip() for s in nltk.tokenize.sent_tokenize(text) if len(s.strip()) > 10]


def chunk_text(text: str, max_chars=1500):
    sents = sentence_tokenize(text)
    chunks, cur = [], ""
    for s in sents:
        if len(cur) + len(s) < max_chars:
            cur += (" " if cur else "") + s
        else:
            chunks.append(cur)
            cur = s
    if cur:
        chunks.append(cur)
    return chunks


def extract_keywords_tfidf(text: str, top_k=8):
    try:
        paras = [p.strip() for p in re.split(r'\n{2,}', text) if len(p.strip()) > 0]
        vectorizer = TfidfVectorizer(stop_words='english', ngram_range=(1, 2))
        X = vectorizer.fit_transform(paras)
        features = vectorizer.get_feature_names_out()
        scores = np.asarray(X.mean(axis=0)).ravel()
        idx = np.argsort(scores)[::-1][:top_k]
        return [features[i] for i in idx]
    except Exception:
        return []


# ==========================================================
# ✍️ Adaptive Summarization
# ==========================================================
def summarize_long_text(text: str) -> str:
    if summarizer is None:
        return "Summarization model unavailable."
    text = clean_text(text)
    L = len(text)
    if L < 1500:
        max_len, min_len, chunk_size = 180, 60, 1400
    elif L < 5000:
        max_len, min_len, chunk_size = 250, 100, 1600
    elif L < 15000:
        max_len, min_len, chunk_size = 350, 150, 1800
    else:
        max_len, min_len, chunk_size = 500, 200, 2000

    if L <= chunk_size:
        return summarizer(text, max_length=max_len, min_length=min_len, do_sample=False)[0]["summary_text"]

    parts = chunk_text(text, max_chars=chunk_size)[:6]
    summaries = []
    for p in parts:
        try:
            summaries.append(summarizer(p, max_length=200, min_length=80, do_sample=False)[0]["summary_text"])
        except Exception:
            continue

    combined = " ".join(summaries)
    final = summarizer(combined, max_length=max_len, min_length=min_len, do_sample=False)[0]["summary_text"]
    return final


# ==========================================================
# 🔊 Text-to-Speech
# ==========================================================
def text_to_speech(text):
    if not text:
        return None
    try:
        t = tempfile.NamedTemporaryFile(delete=False, suffix=".mp3")
        gTTS(text=text[:900], lang="en").save(t.name)
        return t.name
    except Exception:
        return None


# ==========================================================
# 🧠 Q&A
# ==========================================================
def generate_auto_questions(text: str, n=5):
    sents = sentence_tokenize(text)
    qs = []
    for s in sents[:n]:
        words = s.split()
        if len(words) > 5:
            qs.append(f"What is meant by: '{' '.join(words[:8])}...'?")
    return qs


def answer_question(question, context):
    if qa_pipeline is None or not context:
        return "Q&A model unavailable or no context."
    try:
        res = qa_pipeline(question=question, context=context)
        return res.get("answer", "No answer found.")
    except Exception:
        return "Error while generating answer."


# ==========================================================
# 📄 PDF Handler
# ==========================================================
def process_pdf(pdf_file):
    if not pdf_file:
        return "Please upload a PDF.", "", None, "", ""

    text = extract_text_from_pdf(pdf_file)
    if text.startswith("Error") or text.startswith("No text"):
        return text, "", None, "", ""

    text = clean_text(text)
    summary = summarize_long_text(text)
    keywords = ", ".join(extract_keywords_tfidf(text))
    audio = text_to_speech(summary)
    auto_qs = "\n".join(generate_auto_questions(text, n=6))

    return text, summary, audio, keywords, auto_qs


# ==========================================================
# 🎨 Gradio UI
# ==========================================================
with gr.Blocks(title="AI PDF Assistant", theme=gr.themes.Soft()) as demo:
    gr.Markdown("# 📘 AI PDF Assistant — Smart Chat & Summarizer")
    gr.Markdown("Easily extract, summarize, and chat with your PDFs using AI.")

    with gr.Tab("📄 Analyze PDF"):
        with gr.Row():
            with gr.Column(scale=1):
                pdf_input = gr.File(label="Upload PDF", file_types=[".pdf"], type="filepath")
                process_btn = gr.Button("🚀 Process PDF", variant="primary")
            with gr.Column(scale=2):
                extracted_text = gr.Textbox(label="Extracted Text", lines=8, interactive=False)
                summary_box = gr.Textbox(label="Summary", lines=6, interactive=False)
                audio_box = gr.Audio(label="Summary Audio", interactive=False)
                keywords_box = gr.Textbox(label="Top Keywords", lines=2, interactive=False)

    with gr.Tab("💬 Chat with PDF"):
        gr.Markdown("### Auto-Generated Questions")
        auto_q_box = gr.Textbox(label="Generated Questions", lines=6, interactive=False, placeholder="Questions will appear after PDF is processed.")
        gr.Markdown("### Ask Your Own Question")
        user_q = gr.Textbox(label="Your Question", placeholder="Type your question here...")
        ask_btn = gr.Button("Ask", variant="primary")
        answer_box = gr.Textbox(label="Answer", lines=4, interactive=False)

    with gr.Tab("ℹ️ About"):
        gr.Markdown("""
## 📘 About AI PDF Assistant
**AI PDF Assistant** helps you understand and interact with PDFs effortlessly.

### Features
- Extracts and cleans text
- Generates adaptive summaries
- Identifies keywords
- Creates audio summaries
- Auto-generates Q&A
- Lets you chat with your PDF content

Built with ❤️ using Hugging Face Transformers, gTTS, and Gradio.
        """)

    process_btn.click(
        process_pdf,
        inputs=[pdf_input],
        outputs=[extracted_text, summary_box, audio_box, keywords_box, auto_q_box],
    )

    ask_btn.click(
        answer_question,
        inputs=[user_q, extracted_text],
        outputs=[answer_box],
    )

print("🚀 Launching AI PDF Assistant...")
demo.launch()