Update app.py

app.py

@@ -1,4 +1,4 @@
-import io
+import tempfile
 import os
 import json
 import gradio as gr
@@ -16,6 +16,9 @@ from langchain_core.runnables import RunnableParallel, RunnablePassthrough
 
 huggingface_token = os.environ.get("HUGGINGFACE_TOKEN")
 
+# At the beginning of your script
+os.environ['TMPDIR'] = '/tmp'
+
 def load_and_split_document(file):
     """Loads and splits the document into pages."""
     loader = PyPDFLoader(file.name)
@@ -89,14 +92,12 @@ def extract_db_to_excel():
     data = [{"page_content": doc.page_content, "metadata": json.dumps(doc.metadata)} for doc in documents]
     df = pd.DataFrame(data)
     
-    # Save DataFrame to an in-memory Excel file
-    output = io.BytesIO()
-    with pd.ExcelWriter(output, engine='openpyxl') as writer:
-        df.to_excel(writer, index=False)
-    output.seek(0)
+    # Create a temporary file
+    with tempfile.NamedTemporaryFile(delete=False, suffix='.xlsx') as tmp:
+        excel_path = tmp.name
+        df.to_excel(excel_path, index=False)
     
-    # Return the file data in a format Gradio can handle
-    return (output.getvalue(), "database_output.xlsx")
+    return excel_path
 
 # Modify the Gradio interface
 with gr.Blocks() as demo: