Is it still intended and possible to use custom endpoint in 0.2.0?

Question

Is it still intended and possible to use custom endpoint in 0.2.0?

Kaschi14 opened this issue 9 months ago · 9 comments

Answer 1 · 2024-03-15T03:30:44.000Z

same question. I can use my own custom endpoint in the previous version, but it can not work in the newest 0.2.0 version with the same configuration.

Answer 2 · 2024-04-15T02:49:02.000Z

This issue is stale because it has been open for 30 days with no activity.

Answer 3 · 2024-04-24T07:27:49.000Z

I have the same question

Answer 4 · 2024-05-25T01:46:32.000Z

This issue is stale because it has been open for 30 days with no activity.

Answer 5 · 2024-05-29T08:07:43.000Z

Sorry for the late response. What do you mean by custom endpoint? Could you share your configuration? llm-vscode supports multiple backends, namely Hugging Face, TGI, OpenAI, ollama & llama.cpp

Answer 6 · 2024-05-29T12:06:31.000Z

Sorry for the late response. What do you mean by custom endpoint? Could you share your configuration? llm-vscode supports multiple backends, namely Hugging Face, TGI, OpenAI, ollama & llama.cpp

@McPatate In the previous version of llm-vscode, I can use my own local deployed model. For example, I deployed my model at the port: http://192.168.1.73:8192/generate, then I can put the address at ModelID or Endpoint to obtain the response. But in the newest version of 0.2.0, it does not work anymore. Great thanks.

Answer 7 · 2024-05-29T12:07:58.000Z

Could you share your configuration settings, any logs or anything else that could help understand what is going on?

Have you tried updating to the latest version of llm-vscode?

Answer 8 · 2024-06-29T01:48:09.000Z

This issue is stale because it has been open for 30 days with no activity.

Answer 9 · 2024-07-03T08:34:10.000Z

I'll close this issue, feel free to re-open if you are still facing an issue.