Connect Hugging Face integrations

Verified

Search and manage models, datasets, Spaces and collections, run chat completions and react to Hub events, connected to WEXTL workflows and AI agents. Chain Hugging Face steps with the rest of your stack in one visual workflow. Combine Compare Revisions with Count Jobs or Download a File so repetitive work keeps moving on its own.

  • 3-day trial
  • Cancel anytime
  • Up to 10 minutes quick set up
  • GDPR
  • Data Encryption
  • 2FA
  • Local Data Region
  • Hugging Face
  • WEXTL
  • Airtop
  • LumaLabs AI
  • Lovo AI
  • Glam AI
  • Krisp Portal
  • Docparser
  • Dust
  • Fathom AI
  • Roe AI
  • Firecrawl
  • Botsonic
  • Markup AI
  • Synthflow AI
  • Tavily
  • Runway ML
  • Lyzr AI
  • Fish Audio
  • Parseur
  • Cody AI

Supported triggers and actions for Hugging Face integration

Triggers can detect changes in Hugging Face and run actions that can create, search or modify data inside Hugging Face automatically[3], exactly how you set them.

  • Watch Events Starts the workflow the moment Hugging Face calls the webhook, with the Event, Repo and Webhook of each call.
  • Compare Revisions Diffs two revisions of a repository, entered as Compare. Turn on Raw Diff to get the plain diff text.
  • Count Jobs Totals the jobs of a user or organization. Use Stage to count only the jobs in one stage, such as COMPLETED or ERROR.
  • Download a File Fetches a file from a repository by its Path, at the main branch or at a Revision. Returns the File with its File Name, Size (Bytes) and Content Type.
  • Get a Bucket Reads one storage bucket, giving its Author, Private flag, Description and Created At.
  • Get a Collection Loads one collection with its Title, Owner and Position.
  • Get a Container Reads one container repository, giving its Author, Private flag and Updated At.
  • Get a Dataset Loads a dataset repository, showing its Likes, Downloads and Tags.
  • Get a Discussion Reads a discussion or pull request by its Num.
  • Get a Folder Size Totals the bytes under a Path inside a repository, at the main branch or a chosen Revision.
  • Get a Job Looks up a job by its Job ID and shows its Created At, Docker Image, Timeout and Command.
  • Get a Model Fetches a model repository, giving its Likes, Downloads, Commit and Tags.
  • Get a Model Revision Reads a model as it was at a given branch, tag or commit. Use Revision to choose which, and turn on Include File Sizes to add each file size.
  • Get a Paper Pulls one paper with its Title, Authors and Published At. Use Field to add the Submission Deadline or Comments.
  • Get a Pull Request Storage Estimate Estimates the Estimated Storage a pull request adds, using its Num, and shows whether its Ref Deleted.
  • Get a Scheduled Job Looks up a scheduled job and shows its Schedule, Suspend state and Concurrency.
  • Get a Security Scan Shows the scan results of a repository, with the Scans Done and Files With Issues.
  • Get a Space Retrieves a Space, with its Likes, Downloads and Tags.
  • Get a User Overview Reads the profile of a user by Username, with their Fullname, Orgs and Num Models.
  • Get a Webhook Reads one webhook of your account and returns its full Webhook configuration.

How to integrate Hugging Face in automation workflow?

Hugging Face in three steps: start with "Watch Events", connect one credential, then add your next step.

How Hugging Face connects and integrates with WEXTL

Save and approve your credentials once. WEXTL® stores authorization information encrypted and reuses the authentication whenever Hugging Face app is called in workflows. That allows your ai automations to run without your attention, per defined schedule[7]. See the integration guide[6] for a detailed list of fields that Hugging Face supports.

Full Hugging Face API documentation

The following table illustrates what fields Hugging Face integration require during authorization flow inside our workflow builder[4].

Connect Hugging Face

  • Client ID*Text

    ••••••••

  • Client Secret*Text

    ••••••••

Demonstration of Hugging Face connection step inside WEXTL Workflow Builder[4].
FieldTypeHelp
Client IDRequired
text

Create an OAuth app in Hugging Face under Settings, then Connected Apps, and add the redirect URI shown on this form.

Client SecretRequired
password—
Scopesselect

Select the scopes enabled on your OAuth app.

Connect Hugging Face to popular apps on WEXTL

Enter a name of the other app you want to sync with Hugging Face below. Click on selected app to explore integration options with Hugging Face. If the app you search for is not available in WEXTL yet, you can use HTTP node[10] instead to integrate it directly.

Example automation with Hugging Face integration

Select Watch Events trigger from Hugging Face - this will be a starting point in your automation. Whenever event happens in Hugging Face, workflow will start[7] from Watch Events node.

Search for Add a Collection Item, connect it as the next step of integration sequence. You can use filters between Watch Events and Add a Collection Item, so only important data pass from Watch Events to the next step. WEXTL gives you full control over the process of Hugging Face automation. All parts of workflow are visible on the canvas[4].

Hugging Face on WEXTL has 150 modules for combining ai automations. Explore Hugging Face documentation for more.

  • Hugging FaceWatch Events
  • AirtopPerforms action

OR

  • AirtopTriggers
  • Hugging FaceAdd a Collection Item
Demonstration of how visual Hugging Face automation[6] looks in WEXTL.

Frequently asked questions

Common questions about automating Hugging Face in your workflows.

What triggers does Hugging Face support?

Hugging Face has 1 trigger, including "Watch Events". Triggers are start points of the workflow, and automations may start from them.

What actions can I run in Hugging Face?

Integration has 149 actions, including "Compare Revisions", "Count Jobs", and "Download a File", and more. Refer to our Hugging Face Documentation for detailed inputs and outputs.

Do I need to write code to build automations?

No. The 149 Hugging Face modules, like "Compare Revisions", are forms on the canvas: pick a field, map data from an earlier step. Code is optional[4].

Is the integration secure?

Yes. Hugging Face has 2 credential types (1 sign-in, 1 you fill in), and each module uses the one it needs. WEXTL encrypts them at rest, and only your team can use them.

How does WEXTL integrate with Hugging Face?

Through the official Hugging Face API: 149 modules, plus "Make an API Call" for any endpoint they don't cover[3].

Can I use webhooks with Hugging Face?

Yes. "Watch Events" is instant: Hugging Face pushes each event, so there is no polling delay.

Why use WEXTL platform for Hugging Face automation?

WEXTL is an AI-first visual canvas: describe the Hugging Face flow in plain words and AI wires the nodes[4].

Automate Hugging Face on WEXTL®

Claim your 3-day trial to build Hugging Face integrations and access every WEXTL® feature.

Cancel anytime.

References

List of sources used to gather information about the Hugging Face integration.

  1. Hugging Face integration source code, module specs and credentials implementation.
  2. Internal Hugging Face integration documentation, structured input and output parameters, scopes, and authentication methods.
  3. Official Hugging Face vendor API documentation, used to verify field meanings, authentication flows, and anything our own specs don't fully capture.
  4. WEXTL® Visual Workflow Builder, anonymized data from our technical support team.
  5. WEXTL® Apps Library
  6. WEXTL® Hugging Face App Documentation
  7. WEXTL® Workflow Scheduler
  8. WEXTL® HTTP node documentation

How we write and maintain Hugging Face app documentation

Explore how WEXTL® crafted Hugging Face integration page documentation. Used sources, the role of AI, and how the team validates the result.