更新主函数，添加PDF和TXT文件处理说明，注释掉文件选择和处理逻辑

src/add_chunk_cli_pdf_img.py

@@ -157,19 +157,27 @@ def process_pdf_txt_pairs(pdf_dict, txt_dict, dataset):
             process_txt_chunks(document, txt_path)
 
 def main():
-    file_path = "g:\\11\\22\\规范\\"
-    pdf_dict, txt_dict = pair_pdf_and_txt(file_path, file_path)
 
-    if not pdf_dict:
-        print("未选择任何文件。")
-        return
+    """主函数，处理PDF和TXT文件对
+    
+    dataset.id = bucket_name
+    chunk_id = object_name
+    """
+    file_path = "g:\\11\\22\\规范\\"
+    #pdf_dict, txt_dict = pair_pdf_and_txt(file_path, file_path)
+    
+    # if not pdf_dict:
+    #     print("未选择任何文件。")
+    #     return
         
     dataset = select_dataset(rag_object)
+    print(f"选择的数据集: {dataset.name}")
+    print(f"选择的数据集id: {dataset.id}")
     if not dataset:
         print("未选择数据集。")
         return
         
-    process_pdf_txt_pairs(pdf_dict, txt_dict, dataset)
+    #process_pdf_txt_pairs(pdf_dict, txt_dict, dataset)