HF TEI Embeddings Connector

This node can connect to locally or remotely hosted TEI servers which includes Text Embedding Inference Endpoints of popular embedding models that are deployed via Hugging Face Hub.

Protected endpoints require a connection with a HF Hub Authenticator node in order to authenticate with Hugging Face Hub.

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

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

Note: If you use the Credentials Configuration node and do not select the "Save password in configuration (weakly encrypted)" option for passing the API key via the HF Hub Authenticator node, the Credentials Configuration node will need to be reconfigured upon reopening the workflow, as the credentials flow variable was not saved and will therefore not be available to downstream nodes.