Reference/Autoevals library/TypeScript/Modules

Namespace: ClosedQA

Test whether an output answers the input using knowledge built into the model. You can specify criteria to further constrain the answer.

Functions

partial

partial<T>(args): Scorer<string, Omit<LLMClassifierArgs<{ criteria: any ; input: string }>, T> & Partial<Pick<LLMClassifierArgs<{ criteria: any ; input: string }>, T>>>

Type parameters

NameType
Textends "model" | "temperature" | "maxTokens" | keyof OpenAIAuth | "useCoT" | "input" | "criteria"

Parameters

NameType
args{ [K in "model" | "temperature" | "maxTokens" | keyof OpenAIAuth | "useCoT" | "input" | "criteria"]: LLMClassifierArgs<Object>[K] }

Returns

Scorer<string, Omit<LLMClassifierArgs<{ criteria: any ; input: string }>, T> & Partial<Pick<LLMClassifierArgs<{ criteria: any ; input: string }>, T>>>

Defined in

autoevals/js/partial.ts:5

On this page