embeddings

Create embeddings

Changed on

Creates an embedding vector representing the input text. Embeddings are useful for semantic search, clustering, classification, and similarity comparisons.

post/api/v1/embeddings

Request

  • Base URL: / (relative, and the document was published on a file host, not at the API’s origin)
  • URL: /api/v1/embeddings
  • Auth: HTTP bearer

Request body

dimensionsinteger nullable

Number of dimensions for output embeddings

encoding_format'float' | 'base64'

Encoding format for embeddings

input_typestring nullable

Hadrian Extension: Input type hint for embedding providers that support it (e.g., Cohere)

modelstring required

Model to use for embedding

providerobject

Hadrian Extension: Provider routing configuration

userstring nullable

User identifier for abuse detection

Response

Embedding vectors for the input text(s)

Changes