---
title: "Hugging Face integration for LuumenAI"
url: "https://www.luumen.ai/integrations/hugging-face/"
entity: SoftwareIntegration
category: "AI & automation"
audience: "SRE, DevOps, platform engineering, IT operations"
---

# Hugging Face integration for LuumenAI

Inspect models, datasets and Spaces, then tag or commit with approval

## What LuumenAI can do with Hugging Face

LuumenAI connects to Hugging Face with an API token and exposes 135 tools (86 read-only · 35 write · 14 destructive). Reads answer immediately; writes are shown as a plan and require approval by default, configurable per tool by an administrator.

## Key facts

- Authentication: API token
- Tools available: 135 tools (86 read-only · 35 write · 14 destructive)
- Plan: available on all plans
- Category: AI & automation

## About Hugging Face with LuumenAI

Connect Hugging Face and your team can ask about a dataset from the terminal: its schema, license, first rows, repository details. When it is time to mark a release or open a discussion, the agent shows the exact change first and waits for your approval. Luumen authenticates with an API key.

## Example tools

Read-only (86 in total):

- `HUGGING_FACE_CHECK_DATASET_VALIDITY` — Check whether a specific dataset is valid on Hugging Face Hub.
- `HUGGING_FACE_CHECK_MODELS_UPLOAD_METHOD` — Check if files should be uploaded through the Large File mechanism or directly.
- `HUGGING_FACE_CHECK_SPACES_UPLOAD_METHOD` — Check if files should be uploaded through the Large File mechanism or directly to Hugging Face Spaces.
- `HUGGING_FACE_CREATE_DATASETS_PREUPLOAD` — Check if files should be uploaded via Large File Storage (LFS) or directly to a Hugging Face dataset repository.
- `HUGGING_FACE_FILTER_DATASET_ROWS` — Filter rows in a Hugging Face dataset split based on SQL-like query conditions.
- `HUGGING_FACE_GENERATE_CHAT_COMPLETION` — Generate a response given a list of messages in a conversational context.
- `HUGGING_FACE_GENERATE_EMBEDDINGS` — Convert text into vector embeddings for feature extraction, semantic search, and similarity tasks.
- `HUGGING_FACE_GET_DAILY_PAPERS` — Retrieve daily papers from Hugging Face.

Write and destructive (49 in total, approval required by default):

- `HUGGING_FACE_CHANGE_DISCUSSIONS_STATUS` — Change the status of a Hugging Face repository discussion.
- `HUGGING_FACE_CLAIM_SETTINGS_PAPERS_CLAIM` — Claim authorship of a paper on Hugging Face.
- `HUGGING_FACE_CREATE_ASK_ACCESS` — Request access to a gated repository on Hugging Face Hub.
- `HUGGING_FACE_CREATE_COLLECTION` — Create a new collection on Hugging Face.
- `HUGGING_FACE_CREATE_DATASETS_BRANCH` — Create a new branch in a Hugging Face dataset repository.
- `HUGGING_FACE_CREATE_DATASETS_COMMIT` — Create a commit in a Hugging Face dataset repository.
- `HUGGING_FACE_CREATE_DATASETS_TAG` — Create a tag on a Hugging Face dataset repository.
- `HUGGING_FACE_CREATE_DISCUSSIONS` — Create a new discussion on a Hugging Face repository (model, dataset, or Space).

## Frequently asked questions

### How does LuumenAI connect to Hugging Face?

Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.

### Can LuumenAI change things in Hugging Face on its own?

Read actions answer immediately. Anything that writes is shown as a plan and requires approval by default, including the 14 actions classified as destructive. Administrators configure that per tool.

### Is there an audit trail?

Every call to Hugging Face — read or write, approved or declined — is recorded with the actor, the input, and the result.

Full page: https://www.luumen.ai/integrations/hugging-face/