# HuggingFace

HuggingFace is renowned for its comprehensive collection of open-source natural language processing (NLP) models and tools. The HuggingFace blocks in Omnitool enable easy access to these models, offering a seamless experience for users looking to integrate the latest models into their recipes.

{% embed url="<https://www.youtube.com/watch?v=TlyaG2PKdrc>" %}

## Prerequisites

Before you begin, ensure you have the following:

* **HuggingFace Account**: Sign up or log in at [HuggingFace](https://huggingface.co/).
* **Access Token**: Generate your Access token from your HuggingFace account.

## Setup

**Adding API Key**

1. Navigate to **API Key Manager** in the left panel.
2. Add your HuggingFace Access token.

## Using the HuggingFace Block

1. Navigate to the "Add Block" collection in Omnitool.
2. Search `huggingface` namespace, which provides access to various blocks.

<div data-full-width="false"><figure><img src="/files/uP7yxoVmwuUA1wZXJLut" alt=""><figcaption></figcaption></figure></div>

3. Identify the category of the model you're interested in from the extensive collection at [HuggingFace Models](https://huggingface.co/models). Once you've selected a model, simply copy its name and apply the corresponding block in Omnitool. And just like that, you're all set to use the model!

<div data-full-width="false"><figure><img src="/files/yyuQZZybVaqML5hNF1Fn" alt=""><figcaption></figcaption></figure></div>

## Additional Resources

For developers and users seeking more advanced configurations and troubleshooting resources for these blocks, refer to the OpenAPI and block specifications on the <https://github.com/omnitool-ai/omni-core-blocks/tree/main/server/apis/huggingface>.

***

For more information of HuggingFace API, visit the [HuggingFace website](https://huggingface.co/).


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://omnitool-ai.gitbook.io/omnitool/tutorial/blocks/huggingface.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.