THUNLP-MT/StableToolBench

报错信息:AttributeError: function_call`

Opened this issue · 0 comments

请问下述报错是怎么回事?

Traceback (most recent call last): File "/home/guan/shared/StableToolBench/toolbench/tooleval/eval_pass_rate.py", line 100, in <module> example, File "/root/anaconda3/envs/StableToolBench/lib/python3.9/concurrent/futures/_base.py", line 433, in result return self.__get_result() File "/root/anaconda3/envs/StableToolBench/lib/python3.9/concurrent/futures/_base.py", line 389, in __get_result raise self._exception File "/root/anaconda3/envs/StableToolBench/lib/python3.9/concurrent/futures/thread.py", line 52, in run result = self.fn(*self.args, **self.kwargs) File "/root/anaconda3/envs/StableToolBench/lib/python3.9/site-packages/backoff/_sync.py", line 105, in retry ret = target(*args, **kwargs) File "/home/guan/shared/StableToolBench/toolbench/tooleval/eval_pass_rate.py", line 57, in compute_pass_rate answer_steps, final_step = get_steps(example) File "/home/guan/shared/StableToolBench/toolbench/tooleval/evaluators/registered_cls/rtl.py", line 72, in check_is_solved ret = self.function_call( File "/root/anaconda3/envs/StableToolBench/lib/python3.9/site-packages/tenacity/__init__.py", line 330, in wrapped_f return self(f, *args, **kw) File "/root/anaconda3/envs/StableToolBench/lib/python3.9/site-packages/tenacity/__init__.py", line 467, in __call__ do = self.iter(retry_state=retry_state) File "/root/anaconda3/envs/StableToolBench/lib/python3.9/site-packages/tenacity/__init__.py", line 368, in iter result = action(retry_state) File "/root/anaconda3/envs/StableToolBench/lib/python3.9/site-packages/tenacity/__init__.py", line 410, in exc_check raise retry_exc.reraise() File "/root/anaconda3/envs/StableToolBench/lib/python3.9/site-packages/tenacity/__init__.py", line 183, in reraise raise self.last_attempt.result() File "/root/anaconda3/envs/StableToolBench/lib/python3.9/concurrent/futures/_base.py", line 433, in result return self.__get_result() File "/root/anaconda3/envs/StableToolBench/lib/python3.9/concurrent/futures/_base.py", line 389, in __get_result raise self._exception File "/root/anaconda3/envs/StableToolBench/lib/python3.9/site-packages/tenacity/__init__.py", line 470, in __call__ result = fn(*args, **kwargs) File "/home/guan/shared/StableToolBench/toolbench/tooleval/evaluators/registered_cls/tooleval.py", line 100, in function_call ret = json.loads(res.choices[0].message.function_call.arguments) File "/root/anaconda3/envs/StableToolBench/lib/python3.9/site-packages/openai/openai_object.py", line 61, in __getattr__ raise AttributeError(*err.args) AttributeError: function_call

我打印了一下res的结果,确实没有function_call这个参数:

res = { "id": "chatcmpl-UmkknmfVagXcrYdFaqvkRP", "object": "chat.completion", "created": 1719910808, "model": "Meta-Llama-3-8B-Instruct", "choices": [ { "index": 0, "message": { "role": "assistant", "content": "Here is the JSON response:\n\n```\n{\n \"content\": \"The answer provides the channel clips and channel details, including the channel's current live stream, number of viewers and followers, and category. The answer is informative and provides a good overview of the channel. However, it does not explicitly state whether the answer solves the query or not, leaving some uncertainty.\",\n \"answer_status\": \"Unsolved\"\n}\n```\n\nThe answer is informative and provides some details about the channel, but it does not explicitly state whether it solves the query or not. Therefore, I would classify it as \"Unsolved\"." }, "finish_reason": "stop" } ], "usage": { "prompt_tokens": 374, "total_tokens": 499, "completion_tokens": 125 } }

我修改为如下格式:
ret = res.choices[0].message

但是报错:
Traceback (most recent call last): File "/home/guan/shared/StableToolBench/toolbench/tooleval/eval_pass_rate.py", line 105, in <module> query_id, is_solved, evaluate_time = thd.result() File "/root/anaconda3/envs/StableToolBench/lib/python3.9/concurrent/futures/_base.py", line 433, in result return self.__get_result() File "/root/anaconda3/envs/StableToolBench/lib/python3.9/concurrent/futures/_base.py", line 389, in __get_result raise self._exception File "/root/anaconda3/envs/StableToolBench/lib/python3.9/concurrent/futures/thread.py", line 52, in run result = self.fn(*self.args, **self.kwargs) File "/root/anaconda3/envs/StableToolBench/lib/python3.9/site-packages/backoff/_sync.py", line 105, in retry ret = target(*args, **kwargs) File "/home/guan/shared/StableToolBench/toolbench/tooleval/eval_pass_rate.py", line 62, in compute_pass_rate is_solved, is_solved_reason = evaluator.check_is_solved( File "/home/guan/shared/StableToolBench/toolbench/tooleval/evaluators/registered_cls/rtl.py", line 80, in check_is_solved answer_status = AnswerStatus(ret['answer_status']) KeyError: 'answer_status'

openai版本为0.28.0,使用的本地vllm部署的Meta-Llama-3-8B-Instruct模型