Judgeval Python SDKConfig Types
APIScorerConfig
Configuration object for built-in Judgment scorers
Configuration object for built-in Judgment scorers.
namerequired
:strUnique identifier for the scorer configuration
Example: "accuracy_scorer"
promptrequired
:strThe evaluation prompt that will be used to judge responses
Example:
"Rate the accuracy of this answer on a scale of 1-5, where 5 is completely accurate."
options
:Dict[str, Any]Additional configuration options for the scorer
Example:
{
"model": "gpt-4",
"temperature": 0.0,
"max_tokens": 100
}judgment_api_key
:strAPI key for Judgment platform authentication. Defaults to
JUDGMENT_API_KEY environment variable
organization_id
:strOrganization identifier for API requests. Defaults to JUDGMENT_ORG_ID
environment variable