[BUG] qwen2.5在WEBUI中可以正常调用，通过api调用返回不支持tools call / It works in WEBUI when using the model 'qwen2.5', but an error occurred in api call, it return "only [xxx] support tool calls"

[mttbyte]

问题描述
在xinference里我切换了模型为qwen2.5-instruct的7b模型，在WEBUI中可以正常使用，但是通过api访问时返回{'detail': "Only ['qwen1.5-chat', 'qwen1.5-moe-chat', 'qwen2-instruct', 'qwen2-moe-instruct', 'glm4-chat', 'glm4-chat-1m'] support tool calls"}

复现问题的步骤

1. 在xinference里用vllm加载qwen2.5-instruct-7b
2. 相同代码调用api中的/chat/chat/completions
   3.无返回，查看窗口提示
   openai.BadRequestError: Error code: 400 - {'detail': "Only ['qwen1.5-chat', 'qwen1.5-moe-chat', 'qwen2-instruct', 'qwen2-moe-instruct', 'glm4-chat', 'glm4-chat-1m'] support tool calls"}

预期的结果
和前端一样正确返回

实际结果
INFO: 127.0.0.1:59766 - "POST /chat/chat/completions HTTP/1.1" 500 Internal Server Error
ERROR: Exception in ASGI application
Traceback (most recent call last):
File "/home/sutai/miniconda3/envs/langchain/lib/python3.10/site-packages/uvicorn/protocols/http/h11_impl.py", line 396, in run_asgi
result = await app( # type: ignore[func-returns-value]
File "/home/sutai/miniconda3/envs/langchain/lib/python3.10/site-packages/uvicorn/middleware/proxy_headers.py", line 70, in call
return await self.app(scope, receive, send)
File "/home/sutai/miniconda3/envs/langchain/lib/python3.10/site-packages/fastapi/applications.py", line 1054, in call
await super().call(scope, receive, send)
File "/home/sutai/miniconda3/envs/langchain/lib/python3.10/site-packages/starlette/applications.py", line 123, in call
await self.middleware_stack(scope, receive, send)
File "/home/sutai/miniconda3/envs/langchain/lib/python3.10/site-packages/starlette/middleware/errors.py", line 186, in call
raise exc
File "/home/sutai/miniconda3/envs/langchain/lib/python3.10/site-packages/starlette/middleware/errors.py", line 164, in call
await self.app(scope, receive, _send)
File "/home/sutai/miniconda3/envs/langchain/lib/python3.10/site-packages/starlette/middleware/exceptions.py", line 62, in call
await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
File "/home/sutai/miniconda3/envs/langchain/lib/python3.10/site-packages/starlette/_exception_handler.py", line 64, in wrapped_app
raise exc
File "/home/sutai/miniconda3/envs/langchain/lib/python3.10/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
await app(scope, receive, sender)
File "/home/sutai/miniconda3/envs/langchain/lib/python3.10/site-packages/starlette/routing.py", line 758, in call
await self.middleware_stack(scope, receive, send)
File "/home/sutai/miniconda3/envs/langchain/lib/python3.10/site-packages/starlette/routing.py", line 778, in app
await route.handle(scope, receive, send)
File "/home/sutai/miniconda3/envs/langchain/lib/python3.10/site-packages/starlette/routing.py", line 299, in handle
await self.app(scope, receive, send)
File "/home/sutai/miniconda3/envs/langchain/lib/python3.10/site-packages/starlette/routing.py", line 79, in app
await wrap_app_handling_exceptions(app, request)(scope, receive, send)
File "/home/sutai/miniconda3/envs/langchain/lib/python3.10/site-packages/starlette/_exception_handler.py", line 64, in wrapped_app
raise exc
File "/home/sutai/miniconda3/envs/langchain/lib/python3.10/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
await app(scope, receive, sender)
File "/home/sutai/miniconda3/envs/langchain/lib/python3.10/site-packages/starlette/routing.py", line 74, in app
response = await func(request)
File "/home/sutai/miniconda3/envs/langchain/lib/python3.10/site-packages/fastapi/routing.py", line 299, in app
raise e
File "/home/sutai/miniconda3/envs/langchain/lib/python3.10/site-packages/fastapi/routing.py", line 294, in app
raw_response = await run_endpoint_function(
File "/home/sutai/miniconda3/envs/langchain/lib/python3.10/site-packages/fastapi/routing.py", line 191, in run_endpoint_function
return await dependant.call(**values)
File "/home/sutai/miniconda3/envs/langchain/lib/python3.10/site-packages/chatchat/server/api_server/chat_routes.py", line 208, in chat_completions
return await openai_request(
File "/home/sutai/miniconda3/envs/langchain/lib/python3.10/site-packages/chatchat/server/api_server/openai_routes.py", line 115, in openai_request
result = await method(**params)
File "/home/sutai/miniconda3/envs/langchain/lib/python3.10/site-packages/openai/resources/chat/completions.py", line 1295, in create
return await self._post(
File "/home/sutai/miniconda3/envs/langchain/lib/python3.10/site-packages/openai/_base_client.py", line 1826, in post
return await self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)
File "/home/sutai/miniconda3/envs/langchain/lib/python3.10/site-packages/openai/_base_client.py", line 1519, in request
return await self._request(
File "/home/sutai/miniconda3/envs/langchain/lib/python3.10/site-packages/openai/_base_client.py", line 1620, in _request
raise self._make_status_error_from_response(err.response) from None
openai.BadRequestError: Error code: 400 - {'detail': "Only ['qwen1.5-chat', 'qwen1.5-moe-chat', 'qwen2-instruct', 'qwen2-moe-instruct', 'glm4-chat', 'glm4-chat-1m'] support tool calls"}

环境信息

• Langchain-Chatchat 版本 / commit 号：0.3.1.3
• 部署方式（pypi 安装 / 源码部署 / docker 部署）：pypi安装
• 使用的模型推理框架（Xinference / Ollama / OpenAI API 等）：Xinference
• 使用的 LLM 模型（GLM-4-9B / Qwen2-7B-Instruct 等）：qwen2.5-instruct-7b
• 使用的 Embedding 模型（bge-large-zh-v1.5 / m3e-base 等）：bge-large-zh-v1.5
• 使用的向量库类型 (faiss / milvus / pg_vector 等)： faiss
• 操作系统及版本 / Operating system and version: ubuntu22.04
• Python 版本 / Python version: 3.10.14
• 推理使用的硬件（GPU / CPU / MPS / NPU 等）:GPU (Nvidia RTX 4090)

附加信息
1.发送的json内容：
Id: 0
User: Euler
Timeout: 600
MaxTokens: 4096
Messages: [{你是人工智能助手 system system} {测试 user Euler}]
Stream: false
Model: qwen2.5-instruct
Temperature: 0.7
TopP: 0.8
RepetitionPenalty: 1.05
Flag: 0
Tools: []

2.曾经代码正确执行过，原因未知

[mttbyte]

目前使用自定义模型定义qwen2base以加载qwen2.5，但agent结果和直接qwen2.5有偏差

[wangsiyu666]

更新xinference，并重新启动xinference。

[mttbyte]

更新xinference，并重新启动xinference。

成功了，多谢，为何问题居然是出现在xinference里……

[github-actions]

这个问题已经被标记为 stale ，因为它已经超过 30 天没有任何活动。

[whq-27]

我在配置文件中均调用的qwen2.5，但是实际weibu中却提示condaERROR chatchat.server.api server.openai routes:generator:105 openal request error:Connection error. 有大佬知道啥情况吗

[zx0406]

我在配置文件中均调用的qwen2.5，但是实际weibu中却提示condaERROR chatchat.server.api server.openai routes:generator:105 openal request error:Connection error. 有大佬知道啥情况吗

请问这个问题解决了吗？我现在也出现这个问题了，出现的情况是在图片问答的时候，我的模型是Qwen2.5-7B-instruct

[zx0406]

我在配置文件中均调用的qwen2.5，但是实际weibu中却提示condaERROR chatchat.server.api server.openai routes:generator:105 openal request error:Connection error. 有大佬知道啥情况吗

请问这个问题解决了吗？我现在也出现这个问题了，出现的情况是在图片问答的时候，我的模型是Qwen2.5-7B-instruct

[github-actions]

这个问题已经被标记为 stale ，因为它已经超过 30 天没有任何活动。