Update app.py

app.py

@@ -3,6 +3,9 @@ import os
 import json
 import requests
 from io import BytesIO
+import gradio as gr
+import pandas as pd
+from io import BytesIO
 import fitz  # PyMuPDF
 
 from urllib.parse import urlparse, unquote
@@ -228,33 +231,25 @@ def identify_headers_with_openrouter(pdf_path, model,LLM_prompt, pages_to_check=
             out.append({'text': t, 'page': page-1, 'suggested_level': level, 'confidence': conf})
     return out
 
-import gradio as gr
-import pandas as pd
-from io import BytesIO
 
-def identify_headers_with_table(pdf_path, model, LLM_prompt):
-    # Call your existing function
-    result = identify_headers_with_openrouter(pdf_path, model, LLM_prompt)
+def identify_headers_and_save_excel(pdf_path, model, llm_prompt):
+    # This calls your existing header extraction function
+    result = identify_headers_with_openrouter(pdf_path, model, llm_prompt)
     
     if not result:
-        return None  # nothing to return
+        return None
     
-    # Convert to DataFrame
     df = pd.DataFrame(result)
     
-    # Optional: adjust page numbers for human-readable format
-    df['page'] = df['page'] + 1
-    
-    # Save to in-memory Excel file
+    # Save to BytesIO
     output = BytesIO()
-    df.to_excel(output, index=False)
-    output.seek(0)
+    df.to_excel(output, index=False, engine='openpyxl')
+    output.seek(0)  # reset pointer to start
     
-    return output  # return file-like object for download
+    return output
 
-# Gradio Interface
 iface = gr.Interface(
-    fn=identify_headers_with_table,
+    fn=identify_headers_and_save_excel,
     inputs=[
         gr.Textbox(label="Document Link"),
         gr.Textbox(label="Model Type"),
@@ -264,3 +259,4 @@ iface = gr.Interface(
 )
 
 iface.launch()
+