Overview

This node integrates with the Bento API to perform content moderation on provided text content. It sends the content along with optional metadata to Bento's moderation service to evaluate the content for compliance or policy violations. This is useful for automating content review processes in applications such as user-generated content platforms, chat moderation, or any system requiring automated content filtering.

Use Case Examples

1. Automatically moderate user comments on a website to filter out inappropriate language.
2. Evaluate messages submitted through a contact form to ensure they meet content guidelines before processing.
3. Scan social media posts or chat messages for harmful or restricted content before publishing.

Properties

Output

JSON

• operation - The operation performed, here it will be 'contentModeration'.
• success - Boolean indicating if the moderation request was successful.
• apiResponse - The raw response from Bento's content moderation API.
• contentEvaluated - The content that was evaluated by the moderation service.
• metadata - The metadata provided for context during moderation, if any.
• message - A message describing the result of the moderation operation.

Dependencies

• Requires Bento API credentials including publishableKey, secretKey, and siteUuid for authentication.

Troubleshooting

• Ensure the 'Content' field is not empty and does not exceed the maximum allowed length (50,000 characters).
• Verify that the Bento API credentials are correctly configured and valid to avoid authentication errors.
• Check network connectivity if API requests fail due to network errors.
• If the moderation payload exceeds size limits, reduce the content size or metadata.
• Review error messages returned by the node for specific issues such as invalid input or rate limiting.

Links

• Bento Content Moderation API Documentation - Official documentation for Bento's content moderation API endpoint and usage guidelines.