👀 @PatriciaLee3

Thank you for raising an issue. We will investigate into the matter and get back to you as soon as possible.
Please make sure you have given us as much context as possible.
非常感谢您提交 issue。我们会尽快调查此事，并尽快回复您。 请确保您已经提供了尽可能多的背景信息。

Hey @PatriciaLee3, I'm here to help you with any bugs, questions, or contributions! Let me know how I can assist you.

The issue you're encountering is due to the fact that not all Qwen models support the enable_search parameter. According to the codebase, models that start with 'qwen-vl' do not have the enable_search parameter set to true, which might be causing the invalid parameter error you're seeing with the qwen2.5-3b-instruct model ^[1].

To resolve this, you may need to adjust the logic in the handlePayload function to ensure that enable_search is only set for models that support it. This involves checking the model name and applying the parameter conditionally based on the model's capabilities.

To continue talking to Dosu, mention @dosu.

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other}