Class LLMObsIntegrationInferenceRequest

Parameters for an LLM inference request.

Hierarchy

  • LLMObsIntegrationInferenceRequest

Constructors

Properties

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
anthropicMetadata?: LLMObsAnthropicMetadata

Anthropic-specific metadata for an inference request.

azureOpenaiMetadata?: LLMObsAzureOpenAIMetadata

Azure OpenAI-specific metadata for an integration account or inference request.

bedrockMetadata?: LLMObsBedrockMetadata

Amazon Bedrock-specific metadata for an inference request.

frequencyPenalty?: number

Penalty for token frequency to reduce repetition.

jsonSchema?: string

JSON schema for structured output, if supported by the model.

maxCompletionTokens?: number

Maximum number of completion tokens to generate (alternative to max_tokens for some providers).

maxTokens?: number

Maximum number of tokens to generate.

List of messages in an inference conversation.

modelId: string

The model identifier to use for inference.

openaiMetadata?: LLMObsOpenAIMetadata

OpenAI-specific metadata for an inference request.

presencePenalty?: number

Penalty for token presence to encourage topic diversity.

temperature?: number

Sampling temperature between 0 and 2. Higher values produce more random output.

List of tools available to the model.

topK?: number

Top-K sampling parameter.

topP?: number

Nucleus sampling probability mass.

vertexAiMetadata?: LLMObsVertexAIMetadata

Vertex AI-specific metadata for an integration account or inference request.

Generated using TypeDoc