BUGFIX:chat robot添加internet_search

app/service/chat_robot/script/service/CallQWen.py

@@ -1,4 +1,5 @@
 import json
+import logging
 
 from dashscope import Generation
 from retry import retry
@@ -159,10 +160,11 @@ def search_from_internet(message):
         model='qwen-turbo',
         api_key=QWEN_API_KEY,
         messages=message,
-        tools=tools,
+        prompt='The output must be in English.Keep the final result under 200 words.'
+        # tools=tools,
         # seed=random.randint(1, 10000),  # 设置随机数种子seed，如果没有设置，则随机数种子默认为1234
-        result_format='message',  # 将输出设置为message形式
+        # result_format='message',  # 将输出设置为message形式
-        enable_search='True'
+        # enable_search='True'
     )
     return response
 
@@ -198,14 +200,9 @@ def get_response(messages):
 
 
 def call_with_messages(message, gender):
+    global tool_info
     user_input = message
     print('\n')
-    # messages = [
-    #     {
-    #         "content": input('请输入：'),  # 提问示例："现在几点了？" "一个小时后几点" "北京天气如何？"
-    #         "role": "user"
-    #     }
-    # ]
 
     messages = [
         {
@@ -223,14 +220,10 @@ def call_with_messages(message, gender):
         }
     ]
 
-    # 模型的第一轮调用
-    # first_response = get_response(messages)
-    # assistant_output = first_response.output.choices[0].message
-    # print(f"\n大模型第一轮输出信息：{first_response}\n")
-    # messages.append(assistant_output)
     flag = True
     count = 1
-    result_content = "我是一个时尚AI助手，请问有什么可以帮您"
+    # result_content = "我是一个时尚AI助手，请问有什么可以帮您"
+    result_content = "I am a fashion AI assistant, how can I help you?"
     response_type = "chat"
 
     while flag and count <= 3:
@@ -244,11 +237,15 @@ def call_with_messages(message, gender):
             print(f"最终答案：{assistant_output.content}")  # 此处直接返回模型的回复，您可以根据您的业务，选择当无需调用工具时最终回复的内容
             result_content = assistant_output.content
             break
-        # 如果模型选择的工具是search_from_internet
+        # 如果模型选择的工具是internet_search
-        # elif assistant_output.tool_calls[0]['function']['name'] == 'search_from_internet':
+        elif assistant_output.tool_calls[0]['function']['name'] == 'internet_search':
-        #     tool_info = {"name": "search_from_internet", "role": "tool"}
+            tool_info = {"name": "search_from_internet", "role": "tool"}
-        #     user_input = json.loads(assistant_output.tool_calls[0]['function']['arguments'])['user_input']
+            message = [
-        #     tool_info['content'] = search_from_internet(user_input)
+                {'role': 'assistant', 'content': user_input}
+            ]
+            tool_info['content'] = search_from_internet(message)
+            flag = False
+            result_content = tool_info['content'].output.text
         # 如果模型选择的工具是get_database_table
         elif assistant_output.tool_calls[0]['function']['name'] == 'get_database_table':
             tool_info = {"name": "get_database_table", "role": "tool", 'content': get_database_table()}
@@ -275,13 +272,16 @@ def call_with_messages(message, gender):
             flag = False
             result_content = tool_info['content']
             response_type = "image"
+        else :
+            tool_info = {"name": assistant_output.tool_calls[0]['function']['name'], 'content': 'null'}
+            logging.info(assistant_output.tool_calls[0]['function']['name'] + "(unknown tools)")
+            flag = False
 
         print(f"工具输出信息：{tool_info['content']}\n")
         messages.append(tool_info)
         count += 1
 
-    final_output = {"output": result_content}
+    final_output = {"output": result_content, "response_type": response_type}
-    final_output["response_type"] = response_type
     QWenCallbackHandler.on_chain_end(qwen, final_output)
 
     # 模型的第二轮调用，对工具的输出进行总结