Upload app.py

app.py

@@ -0,0 +1,58 @@
+import gradio as gr
+import os
+import json
+import requests
+from io import BytesIO
+from datetime import datetime
+from difflib import SequenceMatcher
+import pandas as pd
+from io import BytesIO
+import fitz  # PyMuPDF
+from collections import defaultdict, Counter
+from urllib.parse import urlparse, unquote   
+import os
+from io import BytesIO
+import re
+import requests
+import pandas as pd
+import fitz  # PyMuPDF
+import re
+import urllib.parse
+import difflib
+
+import copy
+# import tsadropboxretrieval
+
+import urllib.parse
+import logging
+
+
+# Set up logging to see everything
+logging.basicConfig(
+    level=logging.DEBUG,
+    format='%(asctime)s - %(levelname)s - %(message)s',
+    handlers=[
+        logging.StreamHandler(),  # Print to console
+        logging.FileHandler('debug.log', mode='w')  # Save to file
+    ]
+)
+
+logger = logging.getLogger(__name__)
+
+
+
+# Improved launch with debug mode enabled
+iface = gr.Interface(
+    fn=identify_headers_and_save_excel,
+    inputs=[
+        gr.Textbox(label="PDF URL"),
+        gr.Textbox(label="Model Type"), # Default example
+        gr.Textbox(label="LLM Prompt"),
+        gr.Textbox(label="LLM Prompt Hierarchy")
+    ],
+    outputs=gr.File(label="Download Excel Results"),
+    title="PDF Header Extractor"
+)
+
+# Launch with debug=True to see errors in the console
+iface.launch(debug=True)