/
/Text Embeddings Inference
DocsSign in
Sign in
  • APIs
  • Generators
  • Stacks
  • Projects
  • Docs
  • History
  • Schema
Checked 2h ago · Updated 1mo ago
Text Embeddings Inference12
  • postDecode input ids
  • postGet Embeddings. Returns a 424 status code if the model is not an embedding model.
  • postGet all Embeddings without Pooling.
  • postGet Sparse Embeddings. Returns a 424 status code if the model is not an embedding model with SPLADE pooling.
  • postOpenAI compatible route. Returns a 424 status code if the model is not an embedding model.
  • getHealth check method
  • getText Embeddings Inference endpoint info
  • getPrometheus metrics scrape endpoint
  • postGet Predictions. Returns a 424 status code if the model is not a Sequence Classification model
  • postGet Ranks. Returns a 424 status code if the model is not a Sequence Classification model with
  • postTokenize inputs
  • postGenerate embeddings from a Vertex request
    Text Embeddings Inference

    Tokenize inputs

    Tokenize inputs

    post/tokenize

    Request body

    add_special_tokensboolean

    Response

    Tokenized ids

    Example response

    [
      [
        {
          "id": 0,
          "special": false,
          "start": 0,
          "stop": 2,
          "text": "test"
        }
      ]
    ]

    Changes