feat: Add explanation generation and audio output features to PDF extractor

_app.py

@@ -7,6 +7,7 @@ load_dotenv()
 
 def main():
     """Main function to create and launch the interface."""
+    
     def process_pdf(pdf_file):
         """Process PDF and extract text automatically"""
         if pdf_file is None:
@@ -24,8 +25,69 @@ def main():
         except Exception as e:
             return "", f"Error processing PDF: {str(e)}"
     
-    # Create the interface with side-by-side layout
+    def generate_explanations(extracted_text):
+        """Generate explanations for extracted text"""
+        if not extracted_text or extracted_text.strip() == "":
+            return "No text available to explain. Please extract text from a PDF first."
+        
+        try:
+            # Initialize extractor
+            extractor = PDFTextExtractor()
+            
+            # Generate explanations
+            explanations = extractor.generate_explanations(extracted_text)
+            return explanations
+            
+        except Exception as e:
+            return f"Error generating explanations: {str(e)}"
+    
+    def generate_audio(explanation_text):
+        """Generate TTS audio for explanations"""
+        if not explanation_text or explanation_text.strip() == "":
+            raise gr.Error("No explanations available to convert to audio. Please generate explanations first.")
+        
+        try:
+            # Import the TTS function
+            from ui.chatterbox.generate_tts_audio import generate_tts_audio
+            
+            # Clean up the text for better TTS
+            clean_text = explanation_text.strip()
+            
+            # Limit text length for TTS (assuming 1000 character limit)
+            if len(clean_text) > 1000:
+                # Truncate at sentence boundary if possible
+                sentences = clean_text[:950].split('.')
+                if len(sentences) > 1:
+                    clean_text = '.'.join(sentences[:-1]) + '.'
+                else:
+                    clean_text = clean_text[:950]
+                clean_text += " [Text has been truncated for audio generation]"
+            
+            # Generate audio and make it visible
+            audio_result = generate_tts_audio(clean_text, None)
+            return audio_result, gr.update(visible=True)
+            
+        except Exception as e:
+            raise gr.Error(f"Error generating audio: {str(e)}")
+      # Create the interface with side-by-side layout
     with gr.Blocks(title="🔍 PDF Text Extractor", theme=gr.themes.Soft()) as demo:
+        # Inject fullscreen CSS
+        gr.HTML("""
+        <style>
+        html, body, #root, .gradio-container {
+            height: 100% !important;
+            width: 100% !important;
+            margin: 0 !important;
+            padding: 0 !important;
+        }
+        .gradio-container {
+            max-width: 100vw !important;
+            min-height: 100vh !important;
+            box-sizing: border-box;
+        }
+        </style>
+        """)
+        
         gr.Markdown("# 🔍 PDF Text Extractor")
         gr.Markdown("Upload a PDF on the left to automatically extract and view text on the right.")
         
@@ -45,24 +107,72 @@ def main():
                     placeholder="Upload a PDF to see status...",
                     interactive=False
                 )
-            
-            # Right column - Extracted Text
+              # Right column - Extracted Content with Tabs
             with gr.Column(scale=1):
-                gr.Markdown("### 📝 Extracted Text")
-                text_output = gr.Textbox(
-                    label="Extracted Text",
-                    lines=25,
-                    placeholder="Upload a PDF to automatically extract text...",
-                    show_copy_button=True,
-                    interactive=False
+                gr.Markdown("### 📝 Extracted Content")
+                
+                with gr.Tabs():
+                    with gr.TabItem("Extracted Text"):
+                        text_output = gr.Textbox(
+                            label="Extracted Text",
+                            lines=20,
+                            placeholder="Upload a PDF to automatically extract text...",
+                            show_copy_button=True,
+                            interactive=False
+                        )
+                    
+                    with gr.TabItem("Explanation Script"):
+                        with gr.Row():
+                            generate_explanation_btn = gr.Button(
+                                "🤖 Generate Explanation Script", 
+                                variant="primary", 
+                                size="lg"
+                            )
+                        
+                        explanation_output = gr.Textbox(
+                            label="Generated Explanation Script",
+                            lines=15,
+                            placeholder="Click 'Generate Explanation Script' after extracting text to get explanations...",
+                            show_copy_button=True,
+                            interactive=False
+                        )
+                
+                # Audio generation section (below tabs)
+                gr.Markdown("### 🔊 Audio Generation")
+                with gr.Row():
+                    generate_audio_btn = gr.Button(
+                        "🎵 Generate Explanation Audio", 
+                        variant="secondary", 
+                        size="lg"
+                    )
+                
+                audio_output = gr.Audio(
+                    label="Generated Explanation Audio",
+                    interactive=False,
+                    visible=False
                 )
-        
-        # Set up automatic processing on PDF upload
+          # Set up automatic processing on PDF upload
         pdf_input.upload(
             fn=process_pdf,
             inputs=[pdf_input],
             outputs=[text_output, status_output]
         )
+        
+        # Set up explanation generation button
+        generate_explanation_btn.click(
+            fn=generate_explanations,
+            inputs=[text_output],
+            outputs=[explanation_output],
+            show_progress=True
+        )
+        
+        # Set up audio generation button
+        generate_audio_btn.click(
+            fn=generate_audio,
+            inputs=[explanation_output],
+            outputs=[audio_output, audio_output],
+            show_progress=True
+        )
     
     return demo