Update api_request.py

inference/api_request.py

@@ -68,22 +68,23 @@ client = OpenAI(
     base_url=openai_api_base,
 )
 completion = client.chat.completions.create(
-    model="zai-org/GLM-4.5",
+    model="glm-4.5",
     messages=messages,
     max_tokens=4096,
     temperature=0.0,
     # extra_body={"chat_template_kwargs": {"enable_thinking": False}} # Uncomment this line to disable thinking
 )
-tool_call = completion.choices[0].message.tool_calls[0]
-args = json.loads(tool_call.function.arguments)
-print("===== TOOL CALL =====")
-print(tool_call)
+print(completion.choices[0].message)
+# tool_call = completion.choices[0].message.tool_calls[0]
+# args = json.loads(tool_call.function.arguments)
+# print("===== TOOL CALL =====")
+# print(tool_call)
 messages.append(completion.choices[0].message)
 messages.append(tools_messages[0])
 
 ## This part is to simulate the tool response
 completion_2 = client.chat.completions.create(
-    model="zai-org/GLM-4.5",
+    model="glm-4.5",
     messages=messages,
     tools=tools,
     extra_body={"chat_template_kwargs": {"enable_thinking": False}},