Update pipeline.py

pipeline.py

@@ -548,17 +548,24 @@ def pipeline_with_gemini(accessions,stop_flag=None, niche_cases=None, save_df=No
       if stop_flag is not None and stop_flag.value:
         print(f"🛑 Stop processing {accession}, aborting early...")
         return {}
+      print("chunk filename: ", chunk_filename)    
       if chunk_exists:
         print("File chunk exists!")
         if not chunk:
             print("start to get chunk")
             text, table, document_title = model.read_docx_text(file_chunk_path)
             chunk = data_preprocess.normalize_for_overlap(text) + "\n" + data_preprocess.normalize_for_overlap(". ".join(table))
+        if str(chunk_filename) != "":
+            print("first time have chunk path at chunk exist: ", str(chunk_filename))
+            acc_score["file_chunk"] = str(chunk_filename)    
       if all_exists:
         print("File all output exists!")
         if not all_output:
             text_all, table_all, document_title_all = model.read_docx_text(file_all_path)
             all_output = data_preprocess.normalize_for_overlap(text_all) + "\n" + data_preprocess.normalize_for_overlap(". ".join(table_all))
+        if str(all_filename) != "":
+            print("first time have all path at all exist: ", str(all_filename))
+            acc_score["file_all_output"] = str(all_filename)    
       if not chunk and not all_output:
         print("not chunk and all output")  
         # else: check if we can reuse these chunk and all output of existed accession to find another