@directus-labs/ai-image-moderation-operation
v1.0.0
Published
Use Clarifai's Moderation Recognition Model to analyze image safety.
Downloads
8
Readme
AI Image Moderation Operation
Analyze images for drugs, suggestive or explicit material, powered by Clarifai.
This operation contains four configuration options - a Clarifai API Key, a link to a file, and a threshold percentage for the concepts to be 'flagged'. It returns a JSON object containing a score for each concept, and an array of which concepts are over the threshold.
Output
This operation outputs a JSON object with the following structure:
{
"concepts": [
{
"name": "drug",
"value": "99.99"
},
{
"name": "suggestive",
"value": "0.00"
},
{
"name": "gore",
"value": "0.00"
},
{
"name": "explicit",
"value": "0.00"
}
],
"flags": [
"drug"
]
}
Flow Setup
Automatically Moderate New Files
Create a Flow with an Event Hook action trigger and a scope of files.upload
. Use the AI Image Moderation operation, setting the File URL to https://your-directus-project-url/assets/{{ $trigger.key }}
, being sure to provide your specific Directus Project URL.
This will work if your file is public, but if it isn't, you can append ?access_token=token
to the File URL, replacing the value with a valid user token that has access to the file.
This operation will trigger on every new file upload, regardless of location or filetype. You may wish to add a conditional step between the trigger and moderation operation. The following condition rule will check that the file is an image:
{
"$trigger": {
"payload": {
"type": {
"_contains": "image"
}
}
}
}