---
title: Hugging Face Embeddings
description: Leverage Hugging Face Inference to create embeddings.
---

Turn text into vectors with an embedding model hosted on Hugging Face, so a knowledge base can find passages by meaning.

Pick a saved connection in the **Authentication** field, or create one from there.

## What it does

Hugging Face Embeddings plugs into the **Embeddings** slot of a [Local Knowledge](/nodes/builtin/ai/aidependencies/vectorstore/localknowledge/) node. It does not run on its own and has no output. When the knowledge base is filled or searched, the text is sent to Hugging Face's hosted inference service with your token, and comes back as vectors (lists of numbers that capture meaning).

A knowledge base remembers the embedding model it was built with and always uses it. So this node decides the model when a **new, empty** knowledge base is first filled. After that, connect the same node to search it.

Your passages and questions are sent to Hugging Face. To run a similar model on your own device instead, use [Local Embeddings](/nodes/builtin/ai/aidependencies/embeddings/localembeddings/).

## When to use it

* You want a specific open embedding model from the Hugging Face Hub.
* You have a Hugging Face account and want to use its inference service.

## Inputs and settings

**Model** is the model's name on the Hugging Face Hub, in the form `owner/model`, for example `sentence-transformers/all-MiniLM-L6-v2`. Don't change it on a knowledge base that already has content.

## Outputs

This node has no output port. It plugs into a slot on another node instead of passing items along.

* **Embeddings** slot of [Local Knowledge](/nodes/builtin/ai/aidependencies/vectorstore/localknowledge/)

The vectors go to the knowledge base, not to the next node.

## Dependencies and credentials

* **Authentication** (connection): required. See [Create a connection](/app/connections/).

In **Authentication**, save a Hugging Face access token. Create one in your Hugging Face settings, under Access Tokens ([huggingface.co/settings/tokens](https://huggingface.co/settings/tokens)), with permission to call inference. See [Create a credential](/app/connections/create/).

## Example workflow

1. A [Context Menu](/nodes/builtin/trigger/contextmenu/) trigger on the page.
2. [Get All Text](/nodes/extension/getalltext/) with **Output field name** `pageText`.
3. [Indexer](/nodes/builtin/ai/aiagents/indexernode/) with **Input** `{{ $input.pageText }}`, a [Recursive Character Text Splitter](/nodes/builtin/ai/aidependencies/textsplitter/recursivecharactertextsplitter/) in its **Text Splitter** slot, and a [Local Knowledge](/nodes/builtin/ai/aidependencies/vectorstore/localknowledge/) pointing to a new knowledge base in its **Knowledge** slot.
4. Hugging Face Embeddings in the Local Knowledge's **Embeddings** slot, **Model** `sentence-transformers/all-MiniLM-L6-v2`.

## Common issues

* **"Model parameter is required and cannot be empty".** Fill in **Model**.
* **"… was built with … embeddings. Connect that embeddings node to use it."** The knowledge base was built with this model. Connect Hugging Face Embeddings with the same **Model** to its Local Knowledge.
* **A "Model mismatch" warning in the run log.** The knowledge base was built with another model, so this node was ignored. Disconnect it, or re-embed the knowledge base from its settings.
* **A 401 or 403 error.** The token is wrong or lacks inference permission. Create a new one and update the credential.

## Related nodes

* [Local Knowledge](/nodes/builtin/ai/aidependencies/vectorstore/localknowledge/): the knowledge base it plugs into.
* [Local Embeddings](/nodes/builtin/ai/aidependencies/embeddings/localembeddings/): all-MiniLM-L6-v2 on your own device, no token.
* [Indexer](/nodes/builtin/ai/aiagents/indexernode/): fill a knowledge base from a workflow.