OpenAI-compatible embeddings endpoint

Any endpoint serving POST /embeddings, returning 768-dim vectors.

This provider fills the model.embeddings slot. Configure it in Settings → Providers, or during first-run setup.

Settings

Key	Field	Type	Required	Notes
baseUrl	Base URL	URL	Yes	OpenAI-compatible API root ending at /v1.
model	Model ID	text	Yes	—
apiKey	API key	secret or reference	No	Paste the key (encrypted at rest), or use a reference (env:NAME / file:/run/secrets/x).

Note

One field is a secret (apiKey). Pasted secrets are encrypted before storage. You can also supply a reference resolved when it is used. env:NAME reads a process environment variable; file:/run/secrets/name reads a mounted secret file.

What the connection test checks

Select Test connection to run a live test against the credentials you supplied. Saving validates and stores the configuration. Every check below is evaluated against the real service, not inferred from the configuration.

Check	Outcome
Endpoint reachable and authenticated	Must pass
Returns 768-dimensional vectors	Must pass

Adapter id: openai-embeddings.