Embedding Providers

Manage embedding providers that generate vector embeddings for text columns. Providers can be service-based (e.g., OpenAI) or local. Register a provider, then reference it when creating vector indexes on text columns.

List embedding providers

List all registered embedding providers.

Response 200 — List of embedding providers

• embedding_providers EmbeddingProviderResponse[] — required
  • config any — required
  • created_at string — required
  • has_secret boolean — required
  • id string — required
  • name string — required
  • provider_type string — required
  • source string — required. Provider source: "system" (from config) or "user" (created via API).
  • updated_at string — required

{
  "embedding_providers": [
    {
      "config": null,
      "created_at": "2026-01-01T00:00:00Z",
      "has_secret": true,
      "id": "string",
      "name": "string",
      "provider_type": "string",
      "source": "string",
      "updated_at": "2026-01-01T00:00:00Z"
    }
  ]
}

Create embedding provider

Register a new embedding provider that can be used to generate vector embeddings for text columns. Providers can be service-based (e.g., OpenAI) or local.

Request body

• api_key string,null — Inline API key. If provided, a secret is auto-created and referenced. Cannot be used together with secret_name.
• config object — Provider-specific configuration (model name, base URL, dimensions, etc.)
• name string — required
• provider_type string — required. Provider type: "local" or "service"
• secret_name string,null — Reference an existing stored secret by name (for service providers). A stored secret is only sent to an approved provider origin — by default OpenAI's public API. To use a different endpoint, supply the key inline with api_key instead, or ask your operator to approve the origin.

{
  "config": {
    "base_url": "https://api.openai.com/v1",
    "dimensions": 1536,
    "model": "text-embedding-3-small"
  },
  "name": "openai-text-embedding-3-small",
  "provider_type": "service",
  "secret_name": "openai-api-key"
}

Response 201 — Embedding provider created

• config any — required
• created_at string — required
• id string — required
• name string — required
• provider_type string — required

{
  "config": null,
  "created_at": "2026-01-01T00:00:00Z",
  "id": "string",
  "name": "string",
  "provider_type": "string"
}

Errors

Get embedding provider

Path parameters

• id string — required. Embedding provider ID

Response 200 — Embedding provider details

• config any — required
• created_at string — required
• has_secret boolean — required
• id string — required
• name string — required
• provider_type string — required
• source string — required. Provider source: "system" (from config) or "user" (created via API).
• updated_at string — required

{
  "config": null,
  "created_at": "2026-01-01T00:00:00Z",
  "has_secret": true,
  "id": "string",
  "name": "string",
  "provider_type": "string",
  "source": "string",
  "updated_at": "2026-01-01T00:00:00Z"
}

Errors

Update embedding provider

Path parameters

• id string — required. Embedding provider ID

Request body

• api_key string,null — Inline API key. If provided, updates (or creates) the auto-managed secret.
• config any
• name string,null
• secret_name string,null — Secret name containing the API key. Pass null to clear.

All fields are optional. Send only the ones you want to set.

Response 200 — Embedding provider updated

• id string — required
• name string — required
• updated_at string — required

{
  "id": "string",
  "name": "string",
  "updated_at": "2026-01-01T00:00:00Z"
}

Errors

Delete embedding provider

Path parameters

• id string — required. Embedding provider ID

Response 204 — Embedding provider deleted

Errors