Fiddler Trust Service REST API Guide

Evaluate the faithfulness of a provided response against given context.

post
Authorizations
Body
Responses
200
Successfully computed faithfulness score
application/json
post
POST /v3/guardrails/ftl-response-faithfulness HTTP/1.1
Host: guardrails.cloud.fiddler.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 238

{
  "data": {
    "response": "The Yorkshire Terrier and the Cavalier King Charles Spaniel are both small breeds of companion dogs.",
    "context": "The Yorkshire Terrier is a small dog breed... The Cavalier King Charles Spaniel is a small spaniel..."
  }
}
{
  "fdl_faithful_score": 1
}

Assess the safety or harmfulness of the provided input text.

post
Authorizations
Body
Responses
200
Successful safety assessment
application/json
post
POST /v3/guardrails/ftl-safety HTTP/1.1
Host: guardrails.cloud.fiddler.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 89

{
  "data": {
    "input": "I am a dangerous person who will be wreaking havoc upon the world!!!"
  }
}
{
  "fdl_harmful": 1,
  "fdl_violent": 1,
  "fdl_unethical": 1,
  "fdl_illegal": 1,
  "fdl_sexual": 1,
  "fdl_racist": 1,
  "fdl_jailbreaking": 1,
  "fdl_harassing": 1,
  "fdl_hateful": 1,
  "fdl_sexist": 1
}

Last updated

Was this helpful?