HF TEI Embeddings Connector

The Text Embeddings Inference Server is a toolkit for deploying and serving open source text embeddings and sequence classification models.

This node can connect to locally or remotely hosted TEI servers which includes Text Embedding Inference Endpoints of popular embeddings models that are deployed via Hugging Face Hub. Protected endpoints require to connect a HF Hub Authenticator in order to authenticate with Hugging Face hub.

For more details and information about integrating with the Hugging Face Embeddings Inference and setting up a server, refer to Text Embeddings Inference GitHub .

Output ports

1. Type: org.knime.python3.nodes.PythonBinaryBlobFileStorePortObject
   Embeddings Model

   Connection to an embeddings model hosted on a Text Embeddings Inference server.

Hugging Face Hub Connection (Dynamic Inport)

An optional Hugging Face hub connection that can be used to access protected Hugging Face inference endpoints.

1. Type: org.knime.python3.nodes.PythonBinaryBlobFileStorePortObject