How to generate the response from locally hosted end point in vscode?

[dkaus1]

Hi,

I managed to plug the llm-vcode extension to point to the locally running endpoint. Now when I am selected the content like as below:

function to sum 2 numbers in python

then Cmd+shif+a > llm: show code attribution
My local endpoint invokes and give the relevant response as well in below format

{ "details": { "best_of_sequences": [ { "finish_reason": "length", "generated_text": "test", "generated_tokens": 1, "prefill": [ { "id": 0, "logprob": -0.34, "text": "test" } ], "seed": 42, "tokens": [ { "id": 0, "logprob": -0.34, "special": false, "text": "test" } ], "top_tokens": [ [ { "id": 0, "logprob": -0.34, "special": false, "text": "test" } ] ] } ], "finish_reason": "length", "generated_tokens": 1, "prefill": [ { "id": 0, "logprob": -0.34, "text": "test" } ], "seed": 42, "tokens": [ { "id": 0, "logprob": -0.34, "special": false, "text": "test" } ], "top_tokens": [ [ { "id": 0, "logprob": -0.34, "special": false, "text": "test" } ] ] }, "generated_text": "test" }
"generated_text": value is replaced with actual response with python sum function

After 200, I can see the anything related to generated code in vscode.

Please suggest to how to I can get generated response in vscode itself.

[github-actions]

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