Update app.py

app.py

@@ -11,7 +11,7 @@ import numpy as np
 from sklearn.feature_extraction.text import TfidfVectorizer
 
 # ==========================================================
-# 🧠 NLTK Setup (Fix for punkt_tab)
+# 🧠 NLTK Setup (Fixed punkt_tab Issue)
 # ==========================================================
 for pkg in ["punkt", "punkt_tab"]:
     try:
@@ -22,7 +22,7 @@ for pkg in ["punkt", "punkt_tab"]:
 # ==========================================================
 # ⚙️ Model Setup
 # ==========================================================
-DEVICE = -1  # CPU (-1), 0 for GPU if available
+DEVICE = -1  # CPU (-1), use 0 for GPU if available
 SUMMARIZER_MODEL = "facebook/bart-large-cnn"
 QA_MODEL = "deepset/roberta-base-squad2"
 
@@ -94,15 +94,13 @@ def extract_keywords_tfidf(text: str, top_k=8):
 
 
 # ==========================================================
-# ✍️ Summarization
+# ✍️ 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:
@@ -129,7 +127,7 @@ def summarize_long_text(text: str) -> str:
 
 
 # ==========================================================
-# 🔊 Text to Speech
+# 🔊 Text-to-Speech
 # ==========================================================
 def text_to_speech(text):
     if not text:
@@ -143,7 +141,7 @@ def text_to_speech(text):
 
 
 # ==========================================================
-# 💬 Q&A Generation
+# 🧠 Q&A
 # ==========================================================
 def generate_auto_questions(text: str, n=5):
     sents = sentence_tokenize(text)
@@ -186,13 +184,12 @@ def process_pdf(pdf_file):
 
 
 # ==========================================================
-# 🎨 Gradio Interface
+# 🎨 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.")
 
-    # --- Analyze PDF Tab ---
     with gr.Tab("📄 Analyze PDF"):
         with gr.Row():
             with gr.Column(scale=1):
@@ -204,33 +201,30 @@ with gr.Blocks(title="AI PDF Assistant", theme=gr.themes.Soft()) as demo:
                 audio_box = gr.Audio(label="Summary Audio", interactive=False)
                 keywords_box = gr.Textbox(label="Top Keywords", lines=2, interactive=False)
 
-    # --- Chat with PDF Tab ---
     with gr.Tab("💬 Chat with PDF"):
         gr.Markdown("### Auto-Generated Questions")
-        auto_q_box = gr.Textbox(label="Generated Questions", lines=6, interactive=False)
+        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)
 
-    # --- About Tab ---
     with gr.Tab("ℹ️ About"):
         gr.Markdown("""
 ## 📘 About AI PDF Assistant
-**AI PDF Assistant** helps you understand and interact with PDFs effortlessly.  
+**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  
+- 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.
         """)
 
-    # --- Event Connections ---
     process_btn.click(
         process_pdf,
         inputs=[pdf_input],