Namespace: Factuality
Test whether an output is factual, compared to an original (expected) value.
Functions
partial
▸ partial<T>(args): Scorer<string, Omit<LLMClassifierArgs<{ expected?: string ; input: string ; output: string }>, T> & Partial<Pick<LLMClassifierArgs<{ expected?: string ; input: string ; output: string }>, T>>>
Type parameters
| Name | Type |
|---|---|
T | extends "output" | "expected" | "model" | "maxTokens" | "temperature" | keyof OpenAIAuth | "useCoT" | "input" |
Parameters
| Name | Type |
|---|---|
args | { [K in "output" | "expected" | "model" | "maxTokens" | "temperature" | keyof OpenAIAuth | "useCoT" | "input"]: LLMClassifierArgs<Object>[K] } |
Returns
Scorer<string, Omit<LLMClassifierArgs<{ expected?: string ; input: string ; output: string }>, T> & Partial<Pick<LLMClassifierArgs<{ expected?: string ; input: string ; output: string }>, T>>>