[Question] 我在练习 利用Workforce组建hackathon评审团 demo 报错？

[justinzm]

Required prerequisites

• [x] I have read the documentation https://camel-ai.github.io/camel/camel.html.
• [x] I have searched the Issue Tracker and Discussions that this hasn't already been reported. (+1 or comment there if it has.)
• [ ] Consider asking first in a Discussion.

Questions

我在练习 利用Workforce组建hackathon评审团 demo

使用的 model = ModelFactory.create( model_platform=ModelPlatformType.OPENAI_COMPATIBLE_MODEL, model_type="Qwen/Qwen2.5-72B-Instruct", url=os.getenv("MODELSCOPE_API_BASE"), api_key=os.getenv("MODELSCOPE_KEY") )

报错：camel.models.model_manager.ModelProcessingError: Unable to process messages: the only provided model did not run successfully. Error: 1 validation error for TaskAssignResult Input should be an object [type=model_type, input_value=5059208400, input_type=int]

请问这个是什么问题？怎么解决？

[zjrwtx]

hello @justinzm ,please try to use this in modelscope,let me know your feedback https://github.com/camel-ai/camel/blob/3e7d2f57458b08d120481336fc0694b8d12a242a/examples/models/modelscope_model_example.py#L22

[zjrwtx]

or It could be a problem with the model's capabilities, can you try gpt4o or another model？

[fengju0213]

这通常是因为模型的结构化输出能力较弱导致的，可以换一些能力更强的模型试试，我们在新版本也加入了提醒