报错[xinference] Server Unavailable Error, Failed to rerank documents, detail: [address=192.168.1.29:57290, pid=11640] Error when sending message

[Hiroshi230]

System Info / 系統信息

算力端在winserver2019上，dify在虚拟机docker里，我需要用虚拟机里的dify调用算力端的9997端口，dify设置rerank的时候报错如下内容，embedding模型dify能够导入，sentence-transformers已经<4.0.0。

[xinference] Server Unavailable Error, Failed to rerank documents, detail: [address=192.168.1.29:57290, pid=11640] Error when sending message 3a11c129d2bb66a0a835e4660d670d2f3dea936d90e9c44cbd331e36a3a00b0f. Caused by PicklingError('Could not pickle object as excessively deep recursion required.'). Original error: RecursionError('maximum recursion depth exceeded')Traceback: File "D:\anaconda\envs\xinference\lib\site-packages\xoscar\backends\pool.py", line 667, in send result = await self._run_coro(message.message_id, coro) File "D:\anaconda\envs\xinference\lib\site-packages\xoscar\backends\pool.py", line 370, in _run_coro return await coro File "D:\anaconda\envs\xinference\lib\site-packages\xoscar\api.py", line 384, in __on_receive__ return await super().__on_receive__(message) # type: ignore File "xoscar\\core.pyx", line 558, in __on_receive__ File "xoscar\\core.pyx", line 520, in xoscar.core._BaseActor.__on_receive__ File "xoscar\\core.pyx", line 521, in xoscar.core._BaseActor.__on_receive__ File "xoscar\\core.pyx", line 526, in xoscar.core._BaseActor.__on_receive__ File "D:\anaconda\envs\xinference\lib\site-packages\xinference\core\model.py", line 106, in wrapped_func ret = await fn(self, *args, **kwargs) File "D:\anaconda\envs\xinference\lib\site-packages\xinference\core\utils.py", line 93, in wrapped ret = await func(*args, **kwargs) File "D:\anaconda\envs\xinference\lib\site-packages\xinference\core\model.py", line 916, in rerank return await self._call_wrapper_json( File "D:\anaconda\envs\xinference\lib\site-packages\xinference\core\model.py", line 641, in _call_wrapper_json return await self._call_wrapper("json", fn, *args, **kwargs) File "D:\anaconda\envs\xinference\lib\site-packages\xinference\core\model.py", line 141, in _async_wrapper return await fn(self, *args, **kwargs) File "D:\anaconda\envs\xinference\lib\site-packages\xinference\core\model.py", line 666, in _call_wrapper ret = await asyncio.to_thread(fn, *args, **kwargs) File "D:\anaconda\envs\xinference\lib\asyncio\threads.py", line 25, in to_thread return await loop.run_in_executor(None, func_call) File "D:\anaconda\envs\xinference\lib\concurrent\futures\thread.py", line 58, in run result = self.fn(*self.args, **self.kwargs) File "D:\anaconda\envs\xinference\lib\site-packages\xinference\model\rerank\core.py", line 275, in rerank self._model.model.n_tokens = 0 File "D:\anaconda\envs\xinference\lib\site-packages\torch\nn\modules\module.py", line 2032, in __setattr__ super().__setattr__(name, value) File "D:\anaconda\envs\xinference\lib\site-packages\xinference\model\rerank\core.py", line 131, in n_tokens self._local_data.n_tokens = new_n_tokens File "D:\anaconda\envs\xinference\lib\site-packages\xinference\model\rerank\core.py", line 134, in __getattr__ return getattr(self._module, attr) File "D:\anaconda\envs\xinference\lib\site-packages\xinference\model\rerank\core.py", line 134, in __getattr__ return getattr(self._module, attr) File "D:\anaconda\envs\xinference\lib\site-packages\xinference\model\rerank\core.py", line 134, in __getattr__ return getattr(self._module, attr) [Previous line repeate

Running Xinference with Docker? / 是否使用 Docker 运行 Xinfernece？

• docker / docker
• pip install / 通过 pip install 安装
• installation from source / 从源码安装

Version info / 版本信息

xinference 1.4.0

The command used to start Xinference / 用以启动 xinference 的命令

启动用的是192.168.1.29:9997这个端口启用

Reproduction / 复现过程

无

Expected behavior / 期待表现

无

[qinxuye]

能不能重新贴下错误栈。看不清楚。