[Feature Request] 502 Error When Using Local Model with Ollama

[Pakchoioioi]

Motivation

Kept trying to use a local model with the following settings (as shown in the screenshot): Model Platform: Ollama Model Endpoint URL: http://127.0.0.1:11434/v1 Model Name / Type: deepseek-r1:8b The configuration has been saved successfully, but it does not work as expected, showing the error of 502 all the time.

Solution

No response

Alternatives

No response

Additional context

No response