feat: Enhance PDF extraction interface with improved layout and error handling

_app.py

@@ -1,9 +1,68 @@
 import gradio as gr
 from gradio_pdf import PDF
+from pdf_text_extractor import PDFTextExtractor
 
-with gr.Blocks() as demo:
-    pdf = PDF(label="Upload a PDF", interactive=True)
-    name = gr.Textbox()
-    pdf.upload(lambda f: f, pdf, name)
+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:
+            return "", "No PDF uploaded"
+        
+        try:
+            # Initialize extractor
+            extractor = PDFTextExtractor()
+            
+            # Extract text from PDF
+            extracted_text, status, images_data = extractor.extract_text_from_pdf(pdf_file)
+            
+            return extracted_text, status
+            
+        except Exception as e:
+            return "", f"Error processing PDF: {str(e)}"
+    
+    # Create the interface with side-by-side layout
+    with gr.Blocks(title="🔍 PDF Text Extractor", theme=gr.themes.Soft()) as demo:
+        gr.Markdown("# 🔍 PDF Text Extractor")
+        gr.Markdown("Upload a PDF on the left to automatically extract and view text on the right.")
+        
+        with gr.Row(equal_height=True):
+            # Left column - PDF Display
+            with gr.Column(scale=1):
+                gr.Markdown("### 📄 PDF Document")
+                pdf_input = PDF(
+                    label="Upload and View PDF",
+                    height=600,
+                    interactive=True
+                )
+                
+                status_output = gr.Textbox(
+                    label="Status",
+                    lines=2,
+                    placeholder="Upload a PDF to see status...",
+                    interactive=False
+                )
+            
+            # Right column - Extracted Text
+            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
+                )
+        
+        # Set up automatic processing on PDF upload
+        pdf_input.upload(
+            fn=process_pdf,
+            inputs=[pdf_input],
+            outputs=[text_output, status_output]
+        )
+    
+    return demo
 
-demo.launch()
+if __name__ == "__main__":
+    demo = main()
+    demo.launch()

requirements.txt

@@ -14,6 +14,7 @@ filelock==3.18.0
 fsspec==2025.5.1
 gradio==5.33.0
 gradio_client==1.10.2
+gradio-pdf==0.0.15
 groovy==0.1.2
 h11==0.16.0
 httpcore==1.0.9
@@ -57,5 +58,4 @@ typing_extensions==4.14.0
 tzdata==2025.2
 urllib3==2.4.0
 uvicorn==0.34.3
-websockets==15.0.1
-gradio_pdf
+websockets==15.0.1

ui/interface.py

@@ -4,6 +4,7 @@ Defines the Gradio interface components and layout.
 """
 
 import gradio as gr
+from gradio_pdf import PDF
 from pdf_text_extractor import PDFTextExtractor
 from ui.handlers import process_images_for_display
 from .components.create_header import create_header
@@ -27,26 +28,34 @@ def create_dummy_interface() -> gr.Blocks:
         ⚠️ **API key not configured.** Please set MISTRAL_API_KEY environment variable and restart the application.
         """)
         
-        with gr.Row():
-            gr.File(label="Upload PDF", file_types=[".pdf"])
-        
-        with gr.Row():
-            gr.Button("Extract Text", variant="primary", interactive=False)
-        
-        with gr.Row():
-            gr.Textbox(
-                label="Extracted Text", 
-                lines=10,
-                value="API key not configured. Text extraction is unavailable.",
-                interactive=False
-            )
-        
-        with gr.Row():
-            gr.Textbox(
-                label="Status", 
-                lines=2,
-                value="❌ MISTRAL_API_KEY environment variable is not set. Please set it and restart the application."
-            )
+        # Create layout similar to main interface but disabled
+        with gr.Row(equal_height=True):
+            # Left column - PDF Display
+            with gr.Column(scale=1):
+                gr.Markdown("### 📄 PDF Document")
+                PDF(
+                    label="Upload and View PDF (Disabled)",
+                    height=700,
+                    interactive=False
+                )
+                
+                gr.Textbox(
+                    label="Status", 
+                    lines=2,
+                    value="❌ MISTRAL_API_KEY environment variable is not set. Please set it and restart the application.",
+                    interactive=False
+                )
+            
+            # Right column - Extracted Content
+            with gr.Column(scale=1):
+                gr.Markdown("### 📝 Extracted Content")
+                
+                gr.Textbox(
+                    label="Extracted Text", 
+                    lines=25,
+                    value="API key not configured. Text extraction is unavailable.",
+                    interactive=False
+                )
     
     return interface
 
@@ -98,7 +107,6 @@ def create_main_interface(extractor: PDFTextExtractor) -> gr.Blocks:
         
         # Call the TTS function directly - it already handles gr.Error exceptions properly
         return generate_tts_audio(clean_text, None)
-    
     def tts_click_handler(explanations_text):
         """Handle TTS button click with proper output handling"""
         try:
@@ -115,59 +123,65 @@ def create_main_interface(extractor: PDFTextExtractor) -> gr.Blocks:
         # Add the header
         create_header()
         
-        # Add file upload section
-        with gr.Row():
-            pdf_input = create_upload_section()
-        
-        # Add extract button
-        with gr.Row():
-            submit_btn = create_action_button()
-        
-        # Add status display
-        with gr.Row():
-            status_output = gr.Textbox(
-                label="Status", 
-                lines=2,
-                placeholder="Upload a PDF to see status..."
-            )
-        
-        # Create tabs for text, explanations, and images
-        with gr.Tabs():
-            with gr.TabItem("Extracted Text"):
-                text_output = gr.Textbox(
-                    label="Extracted Text", 
-                    lines=15,
-                    max_lines=30,
-                    placeholder="Extracted text will appear here...",
-                    show_copy_button=True
+        # Create main layout with PDF on left and content on right
+        with gr.Row(equal_height=True):
+            # Left column - PDF Display
+            with gr.Column(scale=1):
+                gr.Markdown("### 📄 PDF Document")
+                pdf_input = PDF(
+                    label="Upload and View PDF",
+                    height=700,
+                    interactive=True
                 )
-            
-            with gr.TabItem("📚 Explanations"):
-                with gr.Row():
-                    explain_btn = gr.Button("🤖 Generate Explanations", variant="secondary", size="lg")
-                    tts_btn = gr.Button("🔊 Generate Audio", variant="secondary", size="lg")
                 
-                explanations_output = gr.Textbox(
-                    label="Text Explanations", 
-                    lines=20,
-                    max_lines=40,
-                    placeholder="Click 'Generate Explanations' after extracting text to get simple explanations of each section...",
-                    show_copy_button=True
+                # Status display below PDF
+                status_output = gr.Textbox(
+                    label="Status", 
+                    lines=2,
+                    placeholder="Upload a PDF to see status...",
+                    interactive=False
                 )
+            
+            # Right column - Extracted Content
+            with gr.Column(scale=1):
+                gr.Markdown("### 📝 Extracted Content")
                 
-                # Add audio output for explanations
-                explanation_audio_output = gr.Audio(
-                    label="Explanation Audio",
-                    interactive=False,
-                    visible=False
-                )
+                # Create tabs for text, explanations, and images
+                with gr.Tabs():
+                    with gr.TabItem("Extracted Text"):
+                        text_output = gr.Textbox(
+                            label="Extracted Text", 
+                            lines=25,
+                            max_lines=30,
+                            placeholder="Upload a PDF to automatically extract text...",
+                            show_copy_button=True
+                        )
+                    
+                    with gr.TabItem("📚 Explanations"):
+                        with gr.Row():
+                            explain_btn = gr.Button("🤖 Generate Explanations", variant="secondary", size="lg")
+                            tts_btn = gr.Button("🔊 Generate Audio", variant="secondary", size="lg")
+                        
+                        explanations_output = gr.Textbox(
+                            label="Text Explanations", 
+                            lines=20,
+                            max_lines=25,
+                            placeholder="Click 'Generate Explanations' after extracting text to get simple explanations of each section...",
+                            show_copy_button=True
+                        )
+                        
+                        # Add audio output for explanations
+                        explanation_audio_output = gr.Audio(
+                            label="Explanation Audio",
+                            interactive=False,
+                            visible=False
+                        )
 
-            with gr.TabItem("Extracted Images"):
-                image_gallery = create_image_gallery()
-                image_info = gr.Markdown("Images extracted from the PDF will appear here.")
-        
-        # Set up function calls
-        submit_btn.click(
+                    with gr.TabItem("Extracted Images"):
+                        image_gallery = create_image_gallery()
+                        image_info = gr.Markdown("Images extracted from the PDF will appear here.")        
+        # Set up automatic PDF processing on upload
+        pdf_input.upload(
             fn=process_pdf_wrapper,
             inputs=[pdf_input],
             outputs=[text_output, status_output, image_gallery]