karthink
karthink
@cashpw Thank you. This (and your Google Gemini/Vertex related PRs and issues) are on the docket, I'll get to them soon.
@algal I haven't had time to look into this. It looks like Vertex AI [supports a REST interface](https://cloud.google.com/vertex-ai/docs/reference/rest) though. The `generateContent` endpoint is the one that gptel would support.
I'm not following what you mean here. Could you provide some context?
@ParetoOptimalDev Is this issue still relevant?
Closing as there has been no response for an year.
Thanks for the report. I haven't been able to reproduce this with the models I've tried with Ollama (including deepseek-coder), but in the meantime I received additional reports from someone...
Is this still an issue?
> I would love to use this as a coding assistant a la copilot etc. gptel isn't good enough for this use case. It starts an external process for each...
> Perhaps, though, the more reasonable approach would be to develop some kind of lsp-server binary that wraps your LLM of choice This is exactly what the Python project in...
> I think this might be a pointer. Tbh, I'm not too familiar with the internals though, but I have played around with --prompt-cache-all https://github.com/ggerganov/llama.cpp/issues/64 I'll take a look. >...