Check a text, or a picture among the project's files, for the usual harms

post/safety/check

Check a text, or a picture among the project's files, for the usual harms: whether it is flagged, the categories, a recommendation (allow, hold for review, block and report) and the model that decided. Nothing checked is kept.

Before you call

Credential: Authorization: Bearer $KEY
Scope: compliance:read
Mcp: rivier_safety_check
Graphql: Query.complianceSafetyCheck
Sdk: compliance.safety.check
Cli: compliance safety check

Request bodyapplication/json, required

textstring
At most 12000 characters.
assetIdstring (uuid)

Responses

200application/json
Success
- flaggedbooleanrequired
- categorieslist of stringrequired
- recommendationstringrequired
- classifierstringrequired
- checkedAtstringrequired
400application/json
The request was malformed
- errorstringrequired
- messagestring
401application/json
No valid credential
- errorstringrequired
- messagestring
403application/json
The credential lacks the scope, origin or address
- errorstringrequired
- messagestring
429application/json
Over the key's rate limit; see Retry-After
- errorstringrequired
- messagestring

Example request

curl -X POST 'https://api.rivier.ai/safety/check' \
  -H 'Authorization: Bearer $KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "text": "string",
  "assetId": "string"
}'

$KEY stands for your own key. No key is shown or kept on this site.

This page as Markdown