Evaluation compatibility

Ce produit n'est pas pris en charge par le site Datadog que vous avez sélectionné. ().
Cette page n'est pas encore disponible en français, sa traduction est en cours.
Si vous avez des questions ou des retours sur notre projet de traduction actuel, n'hésitez pas à nous contacter.

Evaluation compatibility

The supported third party LLM providers are OpenAI, Azure OpenAI, Anthropic, and Bedrock Anthropic.

Managed evaluations

Managed evaluations are supported for the following configurations.

EvaluationDD-trace versionLLM ProviderApplicable span
Tool Selectionv3.12+OpenAI, Azure OpenAILLM only
Tool Argument Correctnessv3.12+OpenAI, Azure OpenAILLM only
Goal CompletenessFully supportedOpenAI, Azure OpenAILLM only
Hallucinationv2.18+OpenAILLM only
Language MismatchFully supportedSelf hostedAll span kinds

Custom LLM-as-a-judge evaluations

Custom LLM-as-a-judge evaluations are supported for the following configurations.

EvaluationDD-trace versionLLM ProviderApplicable span
BooleanFully supportedAll third party LLM providersAll span kinds
ScoreFully supportedOpenAI, Azure OpenAI, Anthropic, Vertex AIAll span kinds
CategoricalFully supportedOpenAI, Azure OpenAI, Anthropic, Vertex AIAll span kinds

Template LLM-as-a-judge evaluations

Existing templates for custom LLM-as-a-judge evaluations are supported for the following configurations.

EvaluationDD-trace versionLLM ProviderApplicable span
Failure to AnswerFully supportedAll third party LLM providersAll span kinds
SentimentFully supportedAll third party LLM providersAll span kinds
ToxicityFully supportedAll third party LLM providersAll span kinds
Prompt InjectionFully supportedAll third party LLM providersAll span kinds
Topic RelevancyFully supportedAll third party LLM providersAll span kinds