deepseek reports an error when using Response Format

[zhaobingshuang]

Self Checks

• This is only for bug report, if you would like to ask a question, please head to Discussions.
• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
• Please do not modify this template :) and fill in all the required fields.

Dify version

0.13.2

Cloud or Self Hosted

Self Hosted (Docker), Self Hosted (Source)

Steps to reproduce

1 Create an llm node in the workflow, select deepseek-chat as the model, and set the Response Format to text or json_object
2 Run the node

[deepseek] Error: API request failed with status code 422: Failed to deserialize the JSON body into the target type: response_format: invalid type: string "text", expected internally tagged enum ResponseFormat at line 1 column 88

✔️ Expected Behavior

❌ Actual Behavior

[deepseek] Error: API request failed with status code 422: Failed to deserialize the JSON body into the target type: response_format: invalid type: string "text", expected internally tagged enum ResponseFormat at line 1 column 88

[dosubot]

The error you're encountering suggests that the ResponseFormat parameter is not being recognized correctly when set to "text" or "json_object". This could be due to a mismatch between the expected values for the ResponseFormat and what is being provided.

In the Dify platform, the valid options for the 'Response Format' when configuring an LLM node are "text", "json_object", and "json_schema" ^[1][2]. However, the error message indicates that there might be an issue with how these values are being processed or expected by the deepseek-chat model.

Here are a few steps you can take to troubleshoot and potentially resolve this issue:

1. Verify Configuration: Double-check the configuration of your LLM node to ensure that the Response Format is set correctly to one of the valid options.

2. Check for Updates: Ensure that you are using the latest version of the Dify platform and the deepseek-chat model, as there might have been updates or bug fixes related to this issue.

3. Review Model Integration: Make sure that the deepseek-chat model is integrated correctly according to the Dify documentation, especially regarding the ResponseFormat parameter.

If the issue persists, it might be necessary to look into the codebase or configuration files to ensure that the ResponseFormat enum is correctly defined and used in the model's API request handling.

To continue talking to Dosu, mention @dosu.

---

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