openai Embedding

Zilla runtime openai embedding resolves text to a vector using OpenAI's embeddings API, or any server that implements the same /v1/embeddings request and response schema. It backs semantic tool search or any other consumer of the embedding engine SPI with a hosted or self-hosted embedding model.

embeddings:
  embedding0:
    type: openai
    options:
      model: text-embedding-3-small
      credentials:
        api-key: ${{env.OPENAI_API_KEY}}

Configuration (* required)

type: openai

const

Specifies the embedding is openai.

options

object

The openai specific options.

options.model *

string

The OpenAI embedding model id, e.g. text-embedding-3-small or text-embedding-3-large.

options.endpoint

string | Default: https://api.openai.com/v1/embeddings

The full URL of the embeddings endpoint, including the /v1/embeddings path, used as given. Set it to use an OpenAI-compatible server, such as text-embeddings-inference, instead of OpenAI. options.model and options.credentials.api-key are still required, but a server that ignores them, such as text-embeddings-inference serving the single model it was started with, accepts any value.

options.credentials *

object

The OpenAI credentials.

options.credentials.api-key *

string

The OpenAI API key, sent as an Authorization: Bearer header on each request. Typically supplied via an environment variable reference, e.g. ${{env.OPENAI_API_KEY}}, rather than inlined directly.

Note

The key needs only one restricted permission: Model capabilities > Embeddings (/v1/embeddings): Request. No other scopes are required.