Update app.py

app.py

@@ -176,7 +176,9 @@ def extract_text_from_file(
         if not schema_doc:
             raise ValueError("No schema found for the given document type")
 
-        json_schema = schema_doc.get("json_schema")    
+        json_schema = schema_doc.get("json_schema")
+        if not json_schema:
+            raise ValueError("Schema is empty or not properly defined.")    
             
         # Retrieve file from S3 and determine content type
         content_type = get_content_type_from_s3(file_key)
@@ -194,8 +196,14 @@ def extract_text_from_file(
             "extracted_data": extracted_data
         }
 
-        inserted_doc = invoice_collection.insert_one(document)
-        document_id = str(inserted_doc.inserted_id)
+        # Insert document into MongoDB
+        try:
+            inserted_doc = invoice_collection.insert_one(document)
+            document_id = str(inserted_doc.inserted_id)
+            logger.info(f"Document inserted with ID: {document_id}")
+        except Exception as e:
+            logger.error(f"Error inserting document: {str(e)}")
+            raise HTTPException(status_code=500, detail="Error inserting document into MongoDB")
 
         return {
             "message": "Document successfully stored in MongoDB",