Repository navigation
docs: add Nativ provider guide - #4534
Merged
Merged
Conversation
Signed-off-by: David Gageot <david.gageot@docker.com>
melmennaoui
approved these changes
Oct 7, 2026
aheritier
added
area/docs
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Nativ is a local inference server for Apple Silicon that runs MLX models directly on macOS 26, and it's not yet documented anywhere in the provider guides, so users have no way to discover or configure it.
This adds a full provider guide at docs/providers/nativ/index.md covering setup, the optional bearer authentication, and support for both the Chat and Responses APIs, including the extra_body thinking override that only applies to Chat. It also calls out tool-call reliability caveats and container networking considerations so users don't hit surprises when running Nativ from inside a container. A runnable example at examples/nativ.yaml uses the tiny Qwen3-0.6B-4bit model (about 351MB) so it stays cheap to try, and the provider is wired into docs/data/nav.yml and cross-linked from the local and overview provider pages.
No Go code changes; this is docs and example content only. The example was dry-run against a local Nativ 0.4 install bundling mlx-vlm 0.7.6 to confirm the Chat and Responses streamed tool loops behave as described.