Update app.py

app.py

@@ -1,3 +1,174 @@
+# import gradio as gr
+# print("GRADIO VERSION:", gr.__version__)
+# import json
+# import os
+# import tempfile
+# from pathlib import Path
+
+# # NOTE: You must ensure that 'working_yolo_pipeline.py' exists 
+# # and defines the following items correctly:
+# from working_yolo_pipeline import run_document_pipeline, DEFAULT_LAYOUTLMV3_MODEL_PATH, WEIGHTS_PATH
+# # Since I don't have this file, I am assuming the imports are correct.
+
+# # Define placeholders for assumed constants if the pipeline file isn't present
+# # You should replace these with your actual definitions if they are missing
+# try:
+#     from working_yolo_pipeline import run_document_pipeline, DEFAULT_LAYOUTLMV3_MODEL_PATH, WEIGHTS_PATH
+# except ImportError:
+#     print("Warning: 'working_yolo_pipeline.py' not found. Using dummy paths.")
+#     def run_document_pipeline(*args):
+#         return {"error": "Placeholder pipeline function called."}
+#     DEFAULT_LAYOUTLMV3_MODEL_PATH = "./models/layoutlmv3_model"
+#     WEIGHTS_PATH = "./weights/yolo_weights.pt"
+
+
+# def process_pdf(pdf_file, layoutlmv3_model_path=None):
+#     """
+#     Wrapper function for Gradio interface.
+
+#     Args:
+#         pdf_file: Gradio UploadButton file object
+#         layoutlmv3_model_path: Optional custom model path
+
+#     Returns:
+#         Tuple of (JSON string, download file path)
+#     """
+#     if pdf_file is None:
+#         return "❌ Error: No PDF file uploaded.", None
+
+#     # Use default model path if not provided
+#     if not layoutlmv3_model_path:
+#         layoutlmv3_model_path = DEFAULT_LAYOUTLMV3_MODEL_PATH
+
+#     # Verify model and weights exist
+#     if not os.path.exists(layoutlmv3_model_path):
+#         return f"❌ Error: LayoutLMv3 model not found at {layoutlmv3_model_path}", None
+
+#     if not os.path.exists(WEIGHTS_PATH):
+#         return f"❌ Error: YOLO weights not found at {WEIGHTS_PATH}", None
+
+#     try:
+#         # Get the uploaded PDF path
+#         pdf_path = pdf_file.name
+
+#         # Run the pipeline
+#         result = run_document_pipeline(pdf_path, layoutlmv3_model_path, 'label_studio_import.json')
+
+#         if result is None:
+#             return "❌ Error: Pipeline failed to process the PDF. Check console for details.", None
+
+#         # Create a temporary file for download
+#         output_filename = f"{Path(pdf_path).stem}_analysis.json"
+#         temp_output = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.json', prefix='analysis_')
+
+#         # Dump results to the temporary file
+#         with open(temp_output.name, 'w', encoding='utf-8') as f:
+#             json.dump(result, f, indent=2, ensure_ascii=False)
+
+#         # Format JSON for display
+#         json_display = json.dumps(result, indent=2, ensure_ascii=False)
+
+#         return json_display, temp_output.name
+
+#     except Exception as e:
+#         return f"❌ Error during processing: {str(e)}", None
+
+
+# # Create Gradio interface
+# # FIX APPLIED: Removed 'theme=gr.themes.Soft()' which caused the TypeError
+# with gr.Blocks(title="Document Analysis Pipeline") as demo:
+#     gr.Markdown("""
+#     # 📄 Document Analysis Pipeline
+
+#     Upload a PDF document to extract structured data including questions, options, answers, passages, and embedded images.
+
+#     **Pipeline Steps:**
+#     1. 🔍 YOLO/OCR Preprocessing (word extraction + figure/equation detection)
+#     2. 🤖 LayoutLMv3 Inference (BIO tagging)
+#     3. 📊 Structured JSON Decoding
+#     4. 🖼️ Base64 Image Embedding
+#     """)
+
+#     with gr.Row():
+#         with gr.Column(scale=1):
+#             pdf_input = gr.File(
+#                 label="Upload PDF Document",
+#                 file_types=[".pdf"],
+#                 type="filepath"
+#             )
+
+#             model_path_input = gr.Textbox(
+#                 label="LayoutLMv3 Model Path (optional)",
+#                 placeholder=DEFAULT_LAYOUTLMV3_MODEL_PATH,
+#                 value=DEFAULT_LAYOUTLMV3_MODEL_PATH,
+#                 interactive=True
+#             )
+
+#             process_btn = gr.Button("🚀 Process Document", variant="primary", size="lg")
+
+#             gr.Markdown("""
+#             ### ℹ️ Notes:
+#             - Processing may take several minutes depending on PDF size
+#             - Figures and equations will be extracted and embedded as Base64
+#             - The output JSON includes structured questions, options, and answers
+#             """)
+
+#         with gr.Column(scale=2):
+#             json_output = gr.Code(
+#                 label="Structured JSON Output",
+#                 language="json",
+#                 lines=25
+#             )
+
+#             download_output = gr.File(
+#                 label="Download Full JSON",
+#                 interactive=False
+#             )
+
+#     # Status/Examples section
+#     with gr.Row():
+#         gr.Markdown("""
+#         ### 📋 Output Format
+#         The pipeline generates JSON with the following structure:
+#         - **Questions**: Extracted question text
+#         - **Options**: Multiple choice options (A, B, C, D, etc.)
+#         - **Answers**: Correct answer(s)
+#         - **Passages**: Associated reading passages
+#         - **Images**: Base64-encoded figures and equations (embedded with keys like `figure1`, `equation2`)
+#         """)
+
+#     # Connect the button to the processing function
+#     process_btn.click(
+#         fn=process_pdf,
+#         inputs=[pdf_input, model_path_input],
+#         outputs=[json_output, download_output],
+#         api_name="process_document"
+#     )
+
+#     # Example section (optional - add example PDFs if available)
+#     # gr.Examples(
+#     #     examples=[
+#     #         ["examples/sample1.pdf"],
+#     #         ["examples/sample2.pdf"],
+#     #     ],
+#     #     inputs=pdf_input,
+#     # )
+
+# # Launch the app
+# if __name__ == "__main__":
+#     demo.launch(
+#         server_name="0.0.0.0",
+#         server_port=7860,
+#         share=False,
+#         show_error=True
+#     )
+
+
+
+
+
+
+
 import gradio as gr
 print("GRADIO VERSION:", gr.__version__)
 import json
@@ -5,13 +176,35 @@ import os
 import tempfile
 from pathlib import Path
 
+# ==============================
+# WRITE CUSTOM CSS FOR FONTS
+# ==============================
+
+CUSTOM_CSS = """
+@font-face {
+    font-family: 'NotoSansMath';
+    src: url('./NotoSansMath-Regular.ttf') format('truetype');
+    font-weight: normal;
+    font-style: normal;
+}
+
+html, body, * {
+    font-family: 'NotoSansMath', sans-serif !important;
+}
+"""
+
+# Write the CSS file if not exists
+if not os.path.exists("custom.css"):
+    with open("custom.css", "w") as f:
+        f.write(CUSTOM_CSS)
+# ==============================
+
+
+
 # NOTE: You must ensure that 'working_yolo_pipeline.py' exists 
 # and defines the following items correctly:
 from working_yolo_pipeline import run_document_pipeline, DEFAULT_LAYOUTLMV3_MODEL_PATH, WEIGHTS_PATH
-# Since I don't have this file, I am assuming the imports are correct.
 
-# Define placeholders for assumed constants if the pipeline file isn't present
-# You should replace these with your actual definitions if they are missing
 try:
     from working_yolo_pipeline import run_document_pipeline, DEFAULT_LAYOUTLMV3_MODEL_PATH, WEIGHTS_PATH
 except ImportError:
@@ -25,22 +218,13 @@ except ImportError:
 def process_pdf(pdf_file, layoutlmv3_model_path=None):
     """
     Wrapper function for Gradio interface.
-
-    Args:
-        pdf_file: Gradio UploadButton file object
-        layoutlmv3_model_path: Optional custom model path
-
-    Returns:
-        Tuple of (JSON string, download file path)
     """
     if pdf_file is None:
         return "❌ Error: No PDF file uploaded.", None
 
-    # Use default model path if not provided
     if not layoutlmv3_model_path:
         layoutlmv3_model_path = DEFAULT_LAYOUTLMV3_MODEL_PATH
 
-    # Verify model and weights exist
     if not os.path.exists(layoutlmv3_model_path):
         return f"❌ Error: LayoutLMv3 model not found at {layoutlmv3_model_path}", None
 
@@ -48,24 +232,19 @@ def process_pdf(pdf_file, layoutlmv3_model_path=None):
         return f"❌ Error: YOLO weights not found at {WEIGHTS_PATH}", None
 
     try:
-        # Get the uploaded PDF path
         pdf_path = pdf_file.name
 
-        # Run the pipeline
         result = run_document_pipeline(pdf_path, layoutlmv3_model_path, 'label_studio_import.json')
 
         if result is None:
             return "❌ Error: Pipeline failed to process the PDF. Check console for details.", None
 
-        # Create a temporary file for download
         output_filename = f"{Path(pdf_path).stem}_analysis.json"
         temp_output = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.json', prefix='analysis_')
 
-        # Dump results to the temporary file
         with open(temp_output.name, 'w', encoding='utf-8') as f:
             json.dump(result, f, indent=2, ensure_ascii=False)
 
-        # Format JSON for display
         json_display = json.dumps(result, indent=2, ensure_ascii=False)
 
         return json_display, temp_output.name
@@ -74,10 +253,15 @@ def process_pdf(pdf_file, layoutlmv3_model_path=None):
         return f"❌ Error during processing: {str(e)}", None
 
 
-# Create Gradio interface
-# FIX APPLIED: Removed 'theme=gr.themes.Soft()' which caused the TypeError
-with gr.Blocks(title="Document Analysis Pipeline",
-              css='style.css') as demo:
+
+# ======================
+# CREATE THE GRADIO UI
+# ======================
+with gr.Blocks(
+    title="Document Analysis Pipeline",
+    css_paths=["custom.css"]   # <── IMPORTANT FOR CUSTOM FONTS
+) as demo:
+
     gr.Markdown("""
     # 📄 Document Analysis Pipeline
 
@@ -126,19 +310,17 @@ with gr.Blocks(title="Document Analysis Pipeline",
                 interactive=False
             )
 
-    # Status/Examples section
     with gr.Row():
         gr.Markdown("""
         ### 📋 Output Format
         The pipeline generates JSON with the following structure:
         - **Questions**: Extracted question text
-        - **Options**: Multiple choice options (A, B, C, D, etc.)
+        - **Options**: Multiple choice options
         - **Answers**: Correct answer(s)
         - **Passages**: Associated reading passages
-        - **Images**: Base64-encoded figures and equations (embedded with keys like `figure1`, `equation2`)
+        - **Images**: Base64-encoded figures and equations
         """)
 
-    # Connect the button to the processing function
     process_btn.click(
         fn=process_pdf,
         inputs=[pdf_input, model_path_input],
@@ -146,20 +328,11 @@ with gr.Blocks(title="Document Analysis Pipeline",
         api_name="process_document"
     )
 
-    # Example section (optional - add example PDFs if available)
-    # gr.Examples(
-    #     examples=[
-    #         ["examples/sample1.pdf"],
-    #         ["examples/sample2.pdf"],
-    #     ],
-    #     inputs=pdf_input,
-    # )
 
-# Launch the app
 if __name__ == "__main__":
     demo.launch(
         server_name="0.0.0.0",
         server_port=7860,
         share=False,
         show_error=True
-    )
+    )