增加单句多篇幅检测

flask_check_bert_test.py

@@ -808,7 +808,7 @@ def ulit_recall_paper(recall_data_list_dict):
     return data
 
 
-def recall_10(title, abst_zh, content) -> dict:
+def recall_10(queue_uuid, title, abst_zh, content) -> dict:
     '''
     宇鹏召回接口
     :param paper_name:
@@ -816,6 +816,7 @@ def recall_10(title, abst_zh, content) -> dict:
     '''
 
     request_json = {
+        "uuid": queue_uuid,
         "title": title,
         "abst_zh": abst_zh,
         "content": content
@@ -958,8 +959,8 @@ def classify():  # 调用模型，设置最大batch_size
             # 加载文件的对象
             data_dict = json.load(f1)
 
-        query_id = data_dict['id']
-        print(query_id)
+        queue_uuid = data_dict['id']
+        print(queue_uuid)
         dataBases = data_dict['dataBases']
         minSimilarity = data_dict['minSimilarity']
         minWords = data_dict['minWords']
@@ -973,12 +974,11 @@ def classify():  # 调用模型，设置最大batch_size
         callbackUrl = data_dict['callbackUrl']
 
         # 调用宇鹏查询相似十篇
-        # recall_data_list_dict = recall_10(title, abst_zh, content)
+        recall_data_list_dict = recall_10(queue_uuid, title, abst_zh, content)
 
-        t1 = time.time()
-        print("查找相似的50篇完成")
-        with open("data/rell_json.txt") as f:
-            recall_data_list_dict = eval(f.read())
+        # print("查找相似的50篇完成")
+        # with open("data/rell_json.txt") as f:
+        #     recall_data_list_dict = eval(f.read())
 
         # 读取文章转化成格式数据
         recall_data_list = ulit_recall_paper(recall_data_list_dict)