moonming opened a new pull request, #13770: URL: https://github.com/apache/apisix/pull/13770
## Summary - add an official tutorial for proxying LocalAI's OpenAI-compatible APIs through APISIX - scope the Route to `/v1/*` and cover streaming, LocalAI bearer authentication, and optional APISIX `key-auth` - add the tutorial to the English documentation sidebar ## Validation - `npx -p [email protected] markdownlint docs/en/latest/tutorials/proxy-localai.md` - `uvx --from codespell==2.1.0 codespell --ignore-words=.ignore_words docs/en/latest/tutorials/proxy-localai.md` - `python3 utils/check-category.py` - `python3 -m json.tool docs/en/latest/config.json` - `git diff --check origin/master...HEAD` - real, no-mock E2E on APISIX 3.17.0 and LocalAI v4.7.1: - verified a real Llama 3.2 1B GGUF (`sha256:1d0e9419ec4e12aef73ccf4ffd122703e94c48344a96bc7c5f0f2772c2152ce3`) - `/v1/models` and non-streaming chat returned `200` - streaming chat returned 16 SSE `data:` events and one `[DONE]` event - LocalAI management path returned `404` through APISIX - missing gateway key and missing LocalAI bearer each returned `401`; both credentials returned `200` LocalAI image used for E2E: `quay.io/go-skynet/local-ai@sha256:66c8824a4bd85f24c55c14b916ecac14550c684d64c7b8fcb5000952d665c30a` (the project's official registry mirror). Related: https://github.com/mudler/LocalAI/issues/11215 and https://github.com/mudler/LocalAI/pull/11294 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
