Skip to content
← Back to documentation
Technical Reference

Metatext

AI content moderation and safety guard API

CategoryArtificial Intelligence
Authenticationcustom
Version0.1.7
Published scopes0 published scopes
Last updatedSeptember 21, 2026

Overview

Connect Metatext with Flows360

AI content moderation and safety guard API

Use the Metatext 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 3 actions and no declared triggers.

Available actions

  • Extract Text
  • Classify Text
  • Fine-tune Model

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: Metatext
  • Package: @activepieces/piece-metatext@0.1.7
  • Exact artifact digest: sha256:7b62e5909c747987caa7267e2a3574f2be9c0bb3f9ec6e790cd52c7affeddfd3
  • 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

  • Extract Text (extract_text), Extract information from text (entities, keywords, custom models) Classification: read.
  • Classify Text (classify_text), Classify text into categories (sentiment, intent, topic, custom models) Classification: read.
  • Fine-tune Model (finetune_model), Initiate a fine-tuning job for your model 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 objects3
Supported actions3
TriggersNone published

Authentication

Authentication method: custom

Authentication profiles

connection · custom
  • API Key Required · protected credential

Supported objects

ObjectReadWriteNotes
Extract Text Yes No Extract information from text (entities, keywords, custom models)
Classify Text Yes No Classify text into categories (sentiment, intent, topic, custom models)
Fine-tune Model Yes No Initiate a fine-tuning job for your model

Supported actions

Extract Text · Read

Extract information from text (entities, keywords, custom models)

extract_text · Risk: low · Retry: safe

Inputs

  • project_id · string · Required, The ID of your extraction project
  • text · string · Required, The text to extract information from
  • model · string · Optional, The model to use for extraction
  • refresh · boolean · Optional, Force refresh the extraction
  • version · string · Optional, Model version to use
Classify Text · Read

Classify text into categories (sentiment, intent, topic, custom models)

classify_text · Risk: low · Retry: safe

Inputs

  • project_id · string · Required, The ID of your classification project
  • text · string · Required, The text to classify
  • model · string · Optional, The model to use for classification
  • threshold · number · Optional, Minimum confidence score for predictions
  • top_labels · number · Optional, Maximum number of labels to return
  • refresh · boolean · Optional, Force refresh the classification
  • version · string · Optional, Model version to use
Fine-tune Model · Read

Initiate a fine-tuning job for your model

finetune_model · Risk: low · Retry: safe

Inputs

  • project_id · string · Required, The ID of your project
  • taskType · string · Required, The type of task for fine-tuning
  • modelBase · string · Required, The base model to fine-tune (e.g., BERT)
  • hyperparameters · object · Optional, Custom hyperparameters for fine-tuning

Setup

Setup

  1. Add the Metatext 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-metatext@0.1.7; provider behaviour can change independently and should be revalidated when the provider or connector version changes.
  • Only the 3 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 Metatext 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-metatext@0.1.7 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.