整理

chunk_operations.py

@@ -12,7 +12,6 @@ def update_img_id_in_elasticsearch(tenant_id, doc_id, chunk_id, new_img_id):
     如果img_id不存在，则增加一个新的 img_id。
 
     :param tenant_id: 租户 ID
-    :param dataset_id: 数据集 ID
     :param doc_id: 文档 ID
     :param chunk_id: 文档块 ID
     :param new_img_id: 新的 img_id
@@ -43,25 +42,7 @@ def update_img_id_in_elasticsearch(tenant_id, doc_id, chunk_id, new_img_id):
     # 获取目标文档的 ID
     hit = result['hits']['hits'][0]
     doc_id_in_es = hit['_id']
-    # print(doc_id_in_es)
-    #print(hit)
-    #print(len(hit['_source']['img_id']))
-    # image_id = hit['_source'].get('img_id', None)
 
-    # if (image_id):
-    #     mapping = es.indices.get_mapping(index=index_name)
-    #     print(mapping)
-
-    # else:
-    #     # img_id 不存在，添加新的 img_id
-    #     # 获取索引的映射
-    #     mapping = es.indices.get_mapping(index=index_name)
-    #     mapping[index_name]['mappings']['properties']['img_id'] = {'type': 'text'}
-    #     es.indices.put_mapping(index="my_index", body=mapping)
-    #     print(mapping)
-
-    
-    #         # 构建更新请求
     update_body = {
         "doc": {
             "img_id": new_img_id

minio_api.py

@@ -122,4 +122,8 @@ try:
 except S3Error as exc:
     print("MinIO错误:", exc)
 except Exception as e:
-    print("发生错误:", e)
+    print("发生错误:", e)
+
+
+
+    

src/add_chunk_cli.py

@@ -71,7 +71,7 @@ def pair_pdf_and_txt(pdf_path, txt_path):
 
 def main():
 
-    file_path = "g:\\11\\22\\路桥设计党建\\"
+    file_path = "g:\\11\\22\\规范\\"
     pdf_dict, txt_dict = pair_pdf_and_txt(file_path,file_path)
 
     if not pdf_dict: