adjust README and local inference configuration script

This commit is contained in:
geoffsee
2025-06-09 14:15:59 -04:00
committed by Geoff Seemueller
parent f29bb6779c
commit 370c3e5717
2 changed files with 16 additions and 25 deletions

View File

@@ -44,10 +44,10 @@ This is a full-stack Conversational AI. It runs on Cloudflare or Bun.
## Local Inference
> Local inference is achieved by overriding the `OPENAI_API_KEY` and `OPENAI_API_ENDPOINT` environment variables. See below.
> Local inference is supported for Ollama and mlx-omni-server. OpenAI compatible servers can be used by overriding OPENAI_API_KEY and OPENAI_API_ENDPOINT.
### mlx-omni-server
(default) (Apple Silicon Only) - Use Ollama for other platforms.
(default) (Apple Silicon Only)
~~~bash
# (prereq) install mlx-omni-server
brew tap seemueller-io/tap