Skip to content
Documentation
Contact
← Back to documentation
Technical Reference

Clarifai

AI-powered visual recognition

CategoryArtificial Intelligence
Authenticationcustom
Version0.4.0
Published scopes0 published scopes
Last updatedSeptember 19, 2026

Overview

Connect Clarifai with Flows360

AI-powered visual recognition

Use the Clarifai 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 10 actions and no declared triggers.

Available actions

  • Ask LLM
  • Ask IGM
  • Classify Images or Videos
  • Classify Text
  • Image to Text
  • Text to Text
  • Audio to Text
  • Add Inputs
  • Plus 2 additional declared actions.

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: Clarifai
  • Package: @activepieces/piece-clarifai@0.4.0
  • Exact artifact digest: sha256:7d8ad3b9cabc901de47190da9c6e7ed14f082aca69e16c576c925720068c0075
  • 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

  • Ask LLM (ask-llm), Send a prompt to any large language models (LLM) supported by clarifai. Classification: read.
  • Ask IGM (generate-igm), Generate an image using the Image generating models supported by clarifai. Classification: read.
  • Classify Images or Videos (visual_classifier_model), Call an visual classifier AI model to recognize concepts Classification: read.
  • Classify Text (text_classifier_model), Call a text classifier AI model to recognize concepts Classification: read.
  • Image to Text (image_text_model), Call an image to text AI model Classification: read.
  • Text to Text (text_text_model), Call a text to text AI model Classification: read.
  • Audio to Text (audio_text_model), Call a audio to text AI model Classification: read.
  • Add Inputs (post_inputs), Add inputs to your clarifai app Classification: read.
  • Run Workflow (workflow_predict), Call a Clarifai workflow Classification: read.
  • Custom API Call (custom_api_call), Make a custom API call to a specific endpoint Classification: read.

Trigger contracts

  • No trigger delivery contracts are declared.

Verification

Deterministic execution evidence is recorded for the pinned artifact, including 1 exercised action entrypoint and 0 exercised trigger entrypoints.

Capability summary

Authenticationcustom
Supported objects10
Supported actions10
TriggersNone published

Authentication

Authentication method: custom

Authentication profiles

connection · custom
  • PAT Key Required · protected credential

Supported objects

ObjectReadWriteNotes
Ask LLM Yes No Send a prompt to any large language models (LLM) supported by clarifai.
Ask IGM Yes No Generate an image using the Image generating models supported by clarifai.
Classify Images or Videos Yes No Call an visual classifier AI model to recognize concepts
Classify Text Yes No Call a text classifier AI model to recognize concepts
Image to Text Yes No Call an image to text AI model
Text to Text Yes No Call a text to text AI model
Audio to Text Yes No Call a audio to text AI model
Add Inputs Yes No Add inputs to your clarifai app
Run Workflow Yes No Call a Clarifai workflow
Custom API Call Yes No Make a custom API call to a specific endpoint

Supported actions

Ask LLM · Read

Send a prompt to any large language models (LLM) supported by clarifai.

ask_llm · Risk: low · Retry: safe

Inputs

  • models · string · Required, The model which will generate the response. If the model is not listed, get the model id from the clarifai website. Example : 'GPT-4' you can get the model id from here [https://clarifai.com/openai/chat-completion/models/GPT-4](https://clarifai.com/openai/chat-completion/models/GPT-4)
  • prompt · string · Required, The prompt to send to the model.
Ask IGM · Read

Generate an image using the Image generating models supported by clarifai.

generate_igm · Risk: low · Retry: safe

Inputs

  • models · string · Required, The model which will generate the response. If the model is not listed, get the model id from the clarifai website. Example : 'GPT-4' you can get the model id from here [https://clarifai.com/openai/chat-completion/models/GPT-4](https://clarifai.com/openai/chat-completion/models/GPT-4)
  • prompt · string · Required, The prompt to send to the model.
Classify Images or Videos · Read

Call an visual classifier AI model to recognize concepts

visual_classifier_model · Risk: low · Retry: safe

Inputs

  • modelUrl · string · Required, URL of the Clarifai model. For example https://clarifai.com/clarifai/main/models/general-image-recognition OR a specific version such as https://clarifai.com/clarifai/main/models/general-image-recognition/versions/aa7f35c01e0642fda5cf400f543e7c40. Find more models at https://clarifai.com/explore/models
  • file · object · Required, URL or base64 bytes of the image or video to classify
Classify Text · Read

Call a text classifier AI model to recognize concepts

text_classifier_model · Risk: low · Retry: safe

Inputs

  • modelUrl · string · Required, URL of the Clarifai model. For example https://clarifai.com/clarifai/main/models/general-image-recognition OR a specific version such as https://clarifai.com/clarifai/main/models/general-image-recognition/versions/aa7f35c01e0642fda5cf400f543e7c40. Find more models at https://clarifai.com/explore/models
  • txt · string · Required, Text to classify
Image to Text · Read

Call an image to text AI model

image_text_model · Risk: low · Retry: safe

Inputs

  • modelUrl · string · Required, URL of the Clarifai model. For example https://clarifai.com/clarifai/main/models/general-image-recognition OR a specific version such as https://clarifai.com/clarifai/main/models/general-image-recognition/versions/aa7f35c01e0642fda5cf400f543e7c40. Find more models at https://clarifai.com/explore/models
  • file · object · Required, URL or base64 bytes of the image to classify
Text to Text · Read

Call a text to text AI model

text_text_model · Risk: low · Retry: safe

Inputs

  • modelUrl · string · Required, URL of the Clarifai model. For example https://clarifai.com/clarifai/main/models/general-image-recognition OR a specific version such as https://clarifai.com/clarifai/main/models/general-image-recognition/versions/aa7f35c01e0642fda5cf400f543e7c40. Find more models at https://clarifai.com/explore/models
  • txt · string · Required, Text to classify
Audio to Text · Read

Call a audio to text AI model

audio_text_model · Risk: low · Retry: safe

Inputs

  • modelUrl · string · Required, URL of the Clarifai model. For example https://clarifai.com/clarifai/main/models/general-image-recognition OR a specific version such as https://clarifai.com/clarifai/main/models/general-image-recognition/versions/aa7f35c01e0642fda5cf400f543e7c40. Find more models at https://clarifai.com/explore/models
  • file · object · Required, URL or base64 bytes of the audio to classify
Add Inputs · Read

Add inputs to your clarifai app

post_inputs · Risk: low · Retry: safe

Inputs

  • userId · string · Required, User ID to associate with the input
  • appId · string · Required, App ID (project) to associate with the input
  • file · object · Required, URL or base64 bytes of the audio to classify
Run Workflow · Read

Call a Clarifai workflow

workflow_predict · Risk: low · Retry: safe

Inputs

  • workflowUrl · string · Required, URL of the Clarifai workflow. For example https://clarifai.com/clarifai/main/workflows/Demographics. Find more workflows at https://clarifai.com/explore/workflows
  • file · object · Required, URL or base64 bytes of the incoming image/video/text/audio to run through the workflow. Note: must be appropriate first step of the workflow to handle that data type.
Custom API Call · Read

Make a custom API call to a specific endpoint

custom_api_call · Risk: low · Retry: safe

Inputs

  • url · object · Required
  • method · string · Required
  • headers · object · Optional, Authorization headers are injected automatically from your connection.
  • queryParams · object · Optional, Appended to the URL as ?key=value.
  • body_type · string · Optional
  • body · object · Optional
  • response_is_binary · boolean · Optional, Enable for files like PDFs, images, etc.
  • failsafe · boolean · Optional, On a failed request, output the error instead of failing the step.
  • timeout · number · Optional, Seconds to wait for a response. Empty: up to the flow limit (10 min).
  • followRedirects · boolean · Optional, Follow 3xx redirects instead of returning them as the response.

Setup

Setup

  1. Add the Clarifai 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-clarifai@0.4.0; provider behaviour can change independently and should be revalidated when the provider or connector version changes.
  • Only the 10 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.
  • Deterministic execution evidence is recorded for the pinned artifact, including 1 exercised action entrypoint and 0 exercised trigger entrypoints.

Troubleshooting

Why canu2019t the connector authenticate?

Check the tenant connection in Studio and confirm every required Clarifai 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-clarifai@0.4.0 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