johndev168

I raise my doubts that it's coming from tool_choice. I cut the whole function definition when responding to the tool_call and also do not append tool_choice when sending a second...

I second this issue. I may have found the culprit to this: [GIN] 2025/06/30 - 10:18:53 | 404 | 8.875µs | 127.0.0.1 | POST "/v1/api/generate" This appears from llama. Shouldn't...

I also tried issuing a search and the same problem occurs. It doesn't matter if you use ollama or litellm, the issue remains the same. Ollama will throw 404 because...

Guys for everyone who has the same issue: It's NOT a bug on r2r but it's in the documentation. The default ollama configuration has the following block: ``` [completion.generation_config] temperature...

I have the same issue. A reboot helped but it keeps popping up sometimes. If that occurs then this is looping until I stop the process: ``` 11:48AM DBG Loading...

The same issue also seems to happen when doing retrieval. ``` llama_context: CPU output buffer size = 0.00 MiB time=2025-07-07T09:56:00.889+02:00 level=INFO source=server.go:637 msg="llama runner started in 0.50 seconds" decode: cannot...