csoriano2718 comments

Results 14 comments of


                                            csoriano2718

RFE: Add --reasoning-budget flag to control thinking in reasoning models

@olliewalsh thanks for the suggestion on --runtime-args. I've read in the [MR](https://app.semanticdiff.com/gh/ggml-org/llama.cpp/pull/13771/overview) that some models might still not behave as expected even when forcing a budget or limiting thinking, which...

Pass through reasoning_content in RAG proxy streaming

/gemini review

Pass through reasoning_content in RAG proxy streaming

/gemini review

Pass through reasoning_content in RAG proxy streaming

/gemini review

Pass through reasoning_content in RAG proxy streaming

/gemini review

Pass through reasoning_content in RAG proxy streaming

/gemini review

Pass through reasoning_content in RAG proxy streaming

all Gemini feedback should be taken care of now

Pass through reasoning_content in RAG proxy streaming

The `test_serve_api` E2E test failure sems unrelated to this PR, the same test is also failing on the `main` branch ([CI run from Nov 25](https://github.com/containers/ramalama/actions/runs/19667725826/job/56328674926)).

Add RAG modes and strengthen strict mode

/gemini review

Add RAG modes and strengthen strict mode

@bmahabirbu ah that's a great idea, doing RAG as an MCP server. I wonder, should we not implement this PR to avoid exposing new features/APIs in Ramalama that in the...