Update working_yolo_pipeline.py

working_yolo_pipeline.py

@@ -2047,8 +2047,9 @@ def embed_images_as_base64_in_memory(structured_data: List[Dict[str, Any]], figu
 
 
 
-def run_document_pipeline(input_pdf_path: str, layoutlmv3_model_path: str) -> Optional[
-    List[Dict[str, Any]]]:
+# def run_document_pipeline(input_pdf_path: str, layoutlmv3_model_path: str) -> Optional[
+#     List[Dict[str, Any]]]:
+def run_document_pipeline( input_pdf_path: str, layoutlmv3_model_path: str, structured_intermediate_output_path: Optional[str] = None) -> Optional[List[Dict[str, Any]]]:
     if not os.path.exists(input_pdf_path): return None
 
     print("\n" + "#" * 80)
@@ -2118,29 +2119,6 @@ def run_document_pipeline(input_pdf_path: str, layoutlmv3_model_path: str) -> Op
     return final_result
 
 
-    
-
-# if __name__ == "__main__":
-#     parser = argparse.ArgumentParser(description="Complete Pipeline")
-#     parser.add_argument("--input_pdf", type=str, required=True, help="Input PDF")
-#     parser.add_argument("--layoutlmv3_model_path", type=str, default=DEFAULT_LAYOUTLMV3_MODEL_PATH, help="Model Path")
-#     parser.add_argument("--ls_output_path", type=str, default=None, help="Label Studio Output Path")
-#     args = parser.parse_args()
-
-#     pdf_name = os.path.splitext(os.path.basename(args.input_pdf))[0]
-#     final_output_path = os.path.abspath(f"{pdf_name}_final_output_embedded.json")
-#     ls_output_path = os.path.abspath(
-#         args.ls_output_path if args.ls_output_path else f"{pdf_name}_label_studio_tasks.json")
-
-#     final_json_data = run_document_pipeline(args.input_pdf, args.layoutlmv3_model_path, ls_output_path)
-
-#     if final_json_data:
-#         with open(final_output_path, 'w', encoding='utf-8') as f:
-#             json.dump(final_json_data, f, indent=2, ensure_ascii=False)
-#         print(f"\n✅ Final Data Saved: {final_output_path}")
-#     else:
-#         print("\n❌ Pipeline Failed.")
-#         sys.exit(1)
 
 
 
@@ -2180,61 +2158,3 @@ if __name__ == "__main__":
 
 
 
-
-
-
-# if __name__ == "__main__":
-#     # Ensure 'json', 'argparse', 'os', and 'sys' are imported at the top of your script
-#     # import json
-#     # import argparse
-#     # import os
-#     # import sys
-#
-#     parser = argparse.ArgumentParser(description="Complete Pipeline")
-#     parser.add_argument("--input_pdf", type=str, required=True, help="Input PDF")
-#     parser.add_argument("--layoutlmv3_model_path", type=str, default=DEFAULT_LAYOUTLMV3_MODEL_PATH, help="Model Path")
-#     parser.add_argument("--ls_output_path", type=str, default=None, help="Label Studio Output Path")
-#     # --- ADDED ARGUMENT FOR DEBUGGING ---
-#     parser.add_argument("--raw_preds_path", type=str, default='BIO_debug.json',
-#                         help="Debug path for raw BIO tag predictions (JSON).")
-#     # ------------------------------------
-#     args = parser.parse_args()
-#
-#     pdf_name = os.path.splitext(os.path.basename(args.input_pdf))[0]
-#     final_output_path = os.path.abspath(f"{pdf_name}_final_output_embedded.json")
-#     ls_output_path = os.path.abspath(
-#         args.ls_output_path if args.ls_output_path else f"{pdf_name}_label_studio_tasks.json")
-#     # --- CALCULATE RAW PREDICTIONS OUTPUT PATH ---
-#     # raw_predictions_output_path = os.path.abspath(
-#     #     args.raw_preds_path if args.raw_preds_path else f"{pdf_name}_raw_predictions_debug.json")
-#     # ---------------------------------------------
-#
-#     # --- UPDATED FUNCTION CALL ---
-#     final_json_data = run_document_pipeline(
-#         args.input_pdf,
-#         args.layoutlmv3_model_path,
-#         ls_output_path,
-#         # raw_predictions_output_path # Pass the new argument
-#     )
-#     # -----------------------------
-#
-#     # 🛑 CRITICAL FIX: CUSTOM JSON SAVING TO REMOVE DOUBLE BACKSLASHES 🛑
-#     if final_json_data:
-#         # 1. Dump the Python object to a standard JSON string.
-#         # This uses json.dumps which correctly escapes single backslashes ('\') to ('\\').
-#         json_str = json.dumps(final_json_data, indent=2, ensure_ascii=False)
-#
-#         # 2. **UNDO ESCAPING:** Replace every instance of the JSON-escaped backslash ('\\')
-#         # with a single literal backslash ('\'). This forces the file content to be correct for LaTeX.
-#         final_output_content = json_str.replace('\\\\', '\\')
-#
-#         # 3. Write the corrected string content to the file.
-#         with open(final_output_path, 'w', encoding='utf-8') as f:
-#             f.write(final_output_content)
-#
-#         print(f"\n✅ Final Data Saved: {final_output_path}")
-#     else:
-#         print("\n❌ Pipeline Failed.")
-#         sys.exit(1)
-
-