Skip to content
Documentation
Contact
← Back to documentation
Technical Reference

Hugging Face

Run inference on 100,000+ open ML models for NLP, vision, and audio tasks

CategoryArtificial Intelligence
Authenticationcustom
Version0.1.8
Published scopes0 published scopes
Last updatedSeptember 30, 2026

Overview

Connect Hugging Face with Flows360

Run inference on 100,000+ open ML models for NLP, vision, and audio tasks

Use the Hugging Face connector to include its declared actions and events in Flows360 workflows without duplicating the integration logic inside each consuming system. This pinned connector version currently exposes 8 actions and no declared triggers.

Available actions

  • Document Question Answering
  • Language Translation
  • Text Classification
  • Text Summarization
  • Chat Completion
  • Create Image
  • Object Detection
  • Image Classification

Available triggers

  • No triggers are declared in this pinned package.

The capability list above is generated from the exact reviewed connector package so the public description stays aligned with the version Flows360 operates.

Technical guide

Technical reference

Package identity

  • Connector: Hugging Face
  • Package: @activepieces/piece-hugging-face@0.1.8
  • Exact artifact digest: sha256:a61332fbcd517e99c4d54d511ea448b06648b02c0aef6da9d9df6dccb1fac71d
  • Runtime: Activepieces-compatible deterministic worker
  • Source: the exact reviewed Activepieces source

Authentication

SECRET TEXT. Connection values are tenant-specific and remain in the consuming Studio instance; CDK stores definitions and field metadata, not customer credential values.

Action contracts

  • Document Question Answering (document_question_answering), Answer questions from document images using Hugging Face models Classification: read.
  • Language Translation (language_translation), Translate text between languages using specialized Hugging Face translation models Classification: read.
  • Text Classification (text_classification), Classify text into categories using Hugging Face models - includes zero-shot classification for custom categories Classification: read.
  • Text Summarization (text_summarization), Generate abstractive summaries of long text using Hugging Face models - optimized for business content Classification: read.
  • Chat Completion (chat_completion), Generate assistant replies using chat-style LLMs - perfect for FAQ bots, support agents, and content generation Classification: read.
  • Create Image (create_image), Generate stunning images from text prompts using state-of-the-art diffusion models - perfect for marketing, product design, and creative content Classification: read.
  • Object Detection (object_detection), Detect and locate objects in images with precise bounding boxes - perfect for inventory management, content moderation, and automated tagging Classification: read.
  • Image Classification (image_classification), Classify images with pre-trained models or custom categories - perfect for content moderation, automated tagging, and smart asset management Classification: read.

Trigger contracts

  • No trigger delivery contracts are declared.

Verification

Runtime execution evidence is managed separately from package metadata.

Capability summary

Authenticationcustom
Supported objects8
Supported actionsNot published
TriggersNone published

Authentication

Authentication method: custom

Authentication profiles

connection · custom
  • API Token Required · protected credential

Supported objects

ObjectReadWriteNotes
Document Question Answering Yes No Answer questions from document images using Hugging Face models
Language Translation Yes No Translate text between languages using specialized Hugging Face translation models
Text Classification Yes No Classify text into categories using Hugging Face models - includes zero-shot classification for custom categories
Text Summarization Yes No Generate abstractive summaries of long text using Hugging Face models - optimized for business content
Chat Completion Yes No Generate assistant replies using chat-style LLMs - perfect for FAQ bots, support agents, and content generation
Create Image Yes No Generate stunning images from text prompts using state-of-the-art diffusion models - perfect for marketing, product design, and creative content
Object Detection Yes No Detect and locate objects in images with precise bounding boxes - perfect for inventory management, content moderation, and automated tagging
Image Classification Yes No Classify images with pre-trained models or custom categories - perfect for content moderation, automated tagging, and smart asset management

Setup

Setup

  1. Add the Hugging Face connector to the workflow in the target Flows360 Studio instance.
  2. Create or select the tenant-specific connection required by the connector. Connection secrets remain in the Studio connection boundary and are not copied into CDK documentation.
  3. Provide the connection fields declared by the pinned package:
  • No provider credential fields are declared by the pinned package.
  1. Select the required action or trigger and complete its declared input fields. Required and optional inputs are defined by the exact package schema.
  2. Test the workflow in the appropriate environment before enabling production scheduling or event delivery.

Limitations

Limitations and operational notes

  • This content describes @activepieces/piece-hugging-face@0.1.8; provider behaviour can change independently and should be revalidated when the provider or connector version changes.
  • Only the 8 actions and 0 triggers declared by this pinned package are represented here.
  • Tenant credentials and connection values are not stored in the public connector record.
  • Provider-side permissions, account entitlements, quotas and rate limits remain subject to the connected provider account and are not inferred when the package does not declare them.
  • Runtime execution evidence is managed separately from package metadata.

Troubleshooting

Why canu2019t the connector authenticate?

Check the tenant connection in Studio and confirm every required Hugging Face connection field is present. Re-authorise OAuth-based connections if the provider token or consent has expired. Do not place credential values in CDK content or logs.

Why is an action or trigger unavailable?

Confirm that the workflow is using @activepieces/piece-hugging-face@0.1.8 and compare the requested capability with the declared action and trigger list for this version. A capability that is not declared by the pinned package should not be presented as supported.

What should I check after a provider-side change?

Revalidate authentication, required fields, action/trigger behaviour and provider documentation before publishing refreshed connector content or moving a new package version into production.

github.com