Lynx for Hallucination Detection

Lynx is a State-of-the-Art model for hallucination detection. To query Lynx for hallucination detection, simply run the following cURL request:

curl --location 'https://api.patronus.ai/v1/evaluate' \
--header 'X-API-KEY: YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
  "capture": "all",
  "app": "default",
  "evaluators": [
    {
      "evaluator": "retrieval-hallucination-lynx",
      "explain_strategy": "always"
    }
  ],
  "evaluated_model_input": "Who are you?",
  "evaluated_model_output": "My name is Barry.",
  "evaluated_model_retrieved_context": ["I am John."],
  "tags": {"experiment": "question_answering"}
}'

The default model endpoint is Lynx (70B). You can swap out retrieval-hallucination-lynx in the above query for retrieval-hallucination-lynx-small to query Lynx (8B).