microsoft / microsoft/foundry-local
Add ability to modify chat template kwargs
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 2.6k
- Forks
- 369
- Avg merge
- 2d 17h
- Merged PRs (30d)
- 39
Description
Currently there is no way to modify/override each model's chat template defaults. For example, this would be useful to disable text output of thinking content.
Ideally this would be configurable on a per-response basis, such as a `template_kwargs: dict = ...` parameter within `complete_streaming_chat`.
This will likely require coordination with downstream dependencies (`onnxruntime`) to add the plumbing needed to support this.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by locating the complete_streaming_chat entry point and tracing how chat template defaults reach the downstream onnxruntime dependency. Define the per-response template_kwargs flow and verify that an override, including disabling thinking-content text output, is accepted end to end.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- ai, api
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 48/100