docs: note OpenAI client base_url for multi-model gateways - #6670
docs: note OpenAI client base_url for multi-model gateways#6670seven7763 wants to merge 1 commit into
Conversation
Clarify that the OpenAI plugin works with OpenAI-compatible multi-model gateways when you are not self-hosting, using DaoXE (https://api.daoxe.com/v1) as one concrete example. Docs only — no runtime behavior changes. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
|
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
| cli.run_app(server) | ||
| ``` | ||
|
|
||
| > **Note:** The OpenAI plugin also works with OpenAI-compatible multi-model gateways when you are not self-hosting — for example [DaoXE](https://daoxe.com) at `https://api.daoxe.com/v1` (set `base_url` if the plugin supports it). |
There was a problem hiding this comment.
🟨 README recommends routing model traffic and API keys through an unvetted third-party endpoint
The added note directs users to point the OpenAI plugin's base_url at a third-party gateway (https://api.daoxe.com/v1) in the project's official README. Following this guidance sends prompts, conversation content, and provider credentials to an external host not affiliated with or vetted by LiveKit, with no caveat about the trust implications.
Was this helpful? React with 👍 or 👎 to provide feedback.
2 participants
Summary
The README already shows the OpenAI plugin for LLM.
This PR adds a one-line note that the same OpenAI plugin pattern works with OpenAI-compatible multi-model gateways when you are not self-hosting, using DaoXE (
https://api.daoxe.com/v1) as one concrete example.Docs only — no runtime behavior changes.
Test plan
Co-Authored-By: Claude Fable 5 noreply@anthropic.com