Class LLMObsCustomEvalConfigLLMProvider

LLM provider configuration for a custom evaluator.

Hierarchy

  • LLMObsCustomEvalConfigLLMProvider

Constructors

constructor

Properties

additionalProperties? bedrock? integrationAccountId? integrationProvider? modelName? vertexAi?

Constructors

constructor

Properties

Optional additionalProperties

additionalProperties?: {
    [key: string]: any;
}

A container for additional, undeclared properties. This is a holder for any undeclared properties as specified with the 'additionalProperties' keyword in the OAS document.

Type declaration

  • [key: string]: any

Optional bedrock

bedrock?: LLMObsCustomEvalConfigBedrockOptions

AWS Bedrock-specific options for LLM provider configuration.

Optional integrationAccountId

integrationAccountId?: string

Integration account identifier.

Optional integrationProvider

integrationProvider?: LLMObsCustomEvalConfigIntegrationProvider

Name of the LLM integration provider. Use deterministic for a code evaluator, which runs llm_judge_config.user_specified_json_post_processing_function instead of calling an LLM. insights_sponsored is returned for evaluators that Datadog manages and cannot be set.

Optional modelName

modelName?: string

Name of the LLM model. Use javascript for a deterministic evaluator.

Optional vertexAi

vertexAi?: LLMObsCustomEvalConfigVertexAIOptions

Google Vertex AI-specific options for LLM provider configuration.

Settings

Member Visibility

Theme

Generated using TypeDoc