Update app.py

app.py

@@ -230,14 +230,14 @@ def extract_invoice_data(file_data, content_type):
         logger.error(f"Error in data extraction: {e}")
         return {"error": str(e)}
 
-def extract_text_from_s3(file_key, content_type):
-    return "Extracted text from file", 1  # Placeholder for real extraction logic
+# def extract_text_from_s3(file_key, content_type):
+#     return "Extracted text from file", 1  # Placeholder for real extraction logic
 
-def convert_to_base64(file_key):
-    return "Base64 encoded data"  # Placeholder
+# def convert_to_base64(file_key):
+#     return "Base64 encoded data"  # Placeholder
 
-def generate_summary(extracted_text):
-    return "Summarized text"  # Placeholder
+# def generate_summary(extracted_text):
+#     return "Summarized text"  # Placeholder
 
 def get_content_type_from_s3(file_key):
     """Fetch the content type (MIME type) of a file stored in S3."""
@@ -275,18 +275,12 @@ def extract_text_from_file(
                 "document": existing_document
             }
             
-        # Retrieve file from S3 and determine content type (Ensure this step is implemented)
-        content_type = get_content_type_from_s3(file_key)  # Implement this function
+        # Retrieve file from S3 and determine content type
+        content_type = get_content_type_from_s3(file_key)
 
-        # Extract text (Ensure Extraction function is implemented)
-        extracted_text, num_pages = extract_text_from_s3(file_key, content_type)
-
-        # Define values for small/large files
-        base64DataResp = None
-        summary = None
-        if num_pages <= 2:
-            base64DataResp = convert_to_base64(file_key)  # Implement this function
-            summary = generate_summary(extracted_text)  # Implement this function
+        # Extract and parse invoice data
+        file_data, _ = fetch_file_from_s3(file_key)
+        extracted_data = extract_invoice_data(file_data, content_type)
 
         # Store extracted data in MongoDB
         document = {
@@ -294,10 +288,7 @@ def extract_text_from_file(
             "file_type": content_type,
             "document_type": document_type,
             "entityrefkey": entity_ref_key,
-            "num_pages": num_pages,
-            "base64DataResp": base64DataResp,  # Only for small files
-            "extracted_text": extracted_text,
-            "summary": summary,  # Only for small files
+            "extracted_data": extracted_data
         }
 
         inserted_doc = invoice_collection.insert_one(document)
@@ -306,9 +297,7 @@ def extract_text_from_file(
         return {
             "message": "Document successfully stored in MongoDB",
             "document_id": document_id,
-            "file_key": file_key,
-            "num_pages": num_pages,
-            "summary": summary if summary else "Skipped for large documents"
+            "extracted_data": extracted_data
         }
 
     except Exception as e:
@@ -318,6 +307,7 @@ def extract_text_from_file(
             "traceback": traceback.format_exc()
         }
         return {"error": error_details}
+
      
 # Serve the output folder as static files
 app.mount("/output", StaticFiles(directory="output", follow_symlink=True, html=True), name="output")