Get Ai Status
const url = 'https://example.com/admin/ai-status/?probe=false';const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
try { const response = await fetch(url, options); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}curl --request GET \ --url 'https://example.com/admin/ai-status/?probe=false' \ --header 'Authorization: Bearer <token>'Return single-deployment AI status; no provider-routing policy controls (admin only).
Authorizations
Section titled “Authorizations ”Parameters
Section titled “ Parameters ”Query Parameters
Section titled “Query Parameters ”When true, run a minimal LIVE provider call per purpose (chat + embeddings) to verify the configured key actually works. Costs a real provider API call — never enabled by dashboards.
When true, run a minimal LIVE provider call per purpose (chat + embeddings) to verify the configured key actually works. Costs a real provider API call — never enabled by dashboards.
Responses
Section titled “ Responses ”Successful Response
object
Whether AI features are enabled for this instance.
Whether an API key is configured. AI features require both ‘enabled’ and ‘configured’.
Whether pgvector-backed semantic search is enabled.
Whether at least one record has embeddings stored.
Per-purpose live provider probe results (admin ai-status ?probe=true).
object
Result of one live provider check (chat or embeddings).
Result of one live provider check (chat or embeddings).
Example
{ "semantic_search_enabled": false, "has_embeddings": false}Bad request — invalid query parameters or payload
Unauthorized — missing or invalid credentials
Forbidden — caller lacks access to this resource
Not found
Validation error
Too many requests — retry after the advertised interval
Headers
Section titled “Headers ”Seconds until the request may be retried
Internal server error
Service unavailable — the database could not serve the request