/
HUhuggingface
⌘K
DocsSign in
  • Docs
  • History
  • Schema
  • Generate
Text Embeddings Inference12
  • post/decodeDecode input ids
  • post/embedGet Embeddings. Returns a 424 status code if the model is not an embedding model.
  • post/embed_allGet all Embeddings without Pooling.
  • post/embed_sparseGet Sparse Embeddings. Returns a 424 status code if the model is not an embedding model with SPLADE pooling.
  • get/healthHealth check method
  • get/infoText Embeddings Inference endpoint info
  • get/metricsPrometheus metrics scrape endpoint
  • post/predictGet Predictions. Returns a 424 status code if the model is not a Sequence Classification model
  • post/rerankGet Ranks. Returns a 424 status code if the model is not a Sequence Classification model with
  • post/similarityGet Sentence Similarity. Returns a 424 status code if the model is not an embedding model.
  • post/tokenizeTokenize inputs
  • post/v1/embeddingsOpenAI compatible route. Returns a 424 status code if the model is not an embedding model.
    Text Embeddings Inference

    Changes to Health check method

    get/health
    • Sep 1, 20259988d0e89620Revision changes
      • warning

        added the new Empty enum value to the response property for the response status

    • Oct 13, 20238c00768ef703Revision changes
      • info

        removed the Empty enum value from the response property for the response status