byzerllm query时报错：Failed to unpickle serialized exception

[feiying00544]

运行“byzerllm query --model ollama_qwen2_chat --query "who are you"”时会报错： ERROR serialization.py:425 -- Failed to unpickle serialized exception Traceback (most recent call last): File "C:\Users\xxx\Miniconda3\envs\auto-coder\Lib\site-packages\ray\exceptions.py", line 50, in from_ray_exception return pickle.loads(ray_exception.serialized_exception) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ TypeError: APIStatusError.init() missing 2 required keyword-only arguments: 'response' and 'body'

The above exception was the direct cause of the following exception:

Traceback (most recent call last): File "C:\Users\xxx\Miniconda3\envs\auto-coder\Lib\site-packages\ray_private\serialization.py", line 423, in deserialize_objects obj = self._deserialize_object(data, metadata, object_ref) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\xxx\Miniconda3\envs\auto-coder\Lib\site-packages\ray_private\serialization.py", line 305, in _deserialize_object return RayError.from_bytes(obj) ^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\xxx\Miniconda3\envs\auto-coder\Lib\site-packages\ray\exceptions.py", line 44, in from_bytes return RayError.from_ray_exception(ray_exception) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\xxx\Miniconda3\envs\auto-coder\Lib\site-packages\ray\exceptions.py", line 53, in from_ray_exception raise RuntimeError(msg) from e RuntimeError: Failed to unpickle serialized exception Traceback (most recent call last): File "", line 198, in _run_module_as_main File "", line 88, in run_code File "C:\Users\xxx\Miniconda3\envs\auto-coder\Scripts\byzerllm.exe_main.py", line 7, in File "C:\Users\xxx\Miniconda3\envs\auto-coder\Lib\site-packages\byzerllm\byzerllm_command.py", line 125, in main resp = llm_client.chat_oai( ^^^^^^^^^^^^^^^^^^^^ File "C:\Users\xxx\Miniconda3\envs\auto-coder\Lib\site-packages\byzerllm\utils\client\byzerllm_client.py", line 1207, in chat_oai res = self._query(model, v) ^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\xxx\Miniconda3\envs\auto-coder\Lib\site-packages\byzerllm\utils\client\byzerllm_client.py", line 1873, in _query raise inst File "C:\Users\xxx\Miniconda3\envs\auto-coder\Lib\site-packages\byzerllm\utils\client\byzerllm_client.py", line 1863, in _query res = ray.get(worker.async_apply.remote(new_input_value)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\xxx\Miniconda3\envs\auto-coder\Lib\site-packages\ray_private\auto_init_hook.py", line 21, in auto_init_wrapper return fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "C:\Users\xxx\Miniconda3\envs\auto-coder\Lib\site-packages\ray_private\client_mode_hook.py", line 103, in wrapper return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\xxx\Miniconda3\envs\auto-coder\Lib\site-packages\ray_private\worker.py", line 2656, in get values, debugger_breakpoint = worker.get_objects(object_refs, timeout=timeout) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\xxx\Miniconda3\envs\auto-coder\Lib\site-packages\ray_private\worker.py", line 873, in get_objects raise value ray.exceptions.RaySystemError: System error: Failed to unpickle serialized exception traceback: Traceback (most recent call last): File "C:\Users\xxx\Miniconda3\envs\auto-coder\Lib\site-packages\ray\exceptions.py", line 50, in from_ray_exception return pickle.loads(ray_exception.serialized_exception) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ TypeError: APIStatusError.init() missing 2 required keyword-only arguments: 'response' and 'body'

The above exception was the direct cause of the following exception:

Traceback (most recent call last): File "C:\Users\xxx\Miniconda3\envs\auto-coder\Lib\site-packages\ray_private\serialization.py", line 423, in deserialize_objects obj = self._deserialize_object(data, metadata, object_ref) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\xxx\Miniconda3\envs\auto-coder\Lib\site-packages\ray_private\serialization.py", line 305, in _deserialize_object return RayError.from_bytes(obj) ^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\xxx\Miniconda3\envs\auto-coder\Lib\site-packages\ray\exceptions.py", line 44, in from_bytes return RayError.from_ray_exception(ray_exception) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\xxx\Miniconda3\envs\auto-coder\Lib\site-packages\ray\exceptions.py", line 53, in from_ray_exception raise RuntimeError(msg) from e RuntimeError: Failed to unpickle serialized exception

[fansir]

一样的问题，解决了吗？

[hanfangyuan4396]

我是 在coding时 model_input_max_length配置的太小了出现了这个问题

[yx135790]

same here , when i deploy deepseek-ai/deepseek-v2-chat model ,but the deepseek-chat model works file

[yx135790]

same here , when i deploy deepseek-ai/deepseek-v2-chat model ,but the deepseek-chat model works file

I was using a wrong API key ,My problem solved after i switch to a correct api Key. This issue might due to exception serialization. but I don't know for details

[Sean10]

根据​​‌​‬‬​‬​‌​​​​​​​‌‍​‌‍‌‌‍​​​​⁠​‬⁠​​​‌‬‬使用auto_coder遇到的问题及解决方案汇总 - 飞书云文档 这里的指导

可以去ray的dashboard查看, localhost:8265 看actor下面的log

我的环境这个报错最后是知识库token超了 openai.BadRequestError: Error code: 400 - {'code': 20015, 'message': 'length of prompt_tokens (434052) must be less than max_seq_len (32768).', 'data': None}

处理掉之后, 可以返回内容了. 只不过好像多个文件加起来不能超大模型的上下文, deepseek 128K超了还是会报错.

[zqc1661586344]

解决了没