Namespace: AnswerCorrectness
Measures answer correctness compared to ground truth using a weighted average of factuality and semantic similarity.
Functions
partial
▸ partial<T>(args): Scorer<string, Omit<{ context?: string | string[] ; input?: string ; model?: string } & { maxTokens?: number ; temperature?: number } & OpenAIAuth & { answerSimilarity?: Scorer<string, {}> ; answerSimilarityWeight?: number ; factualityWeight?: number }, T> & Partial<Pick<{ context?: string | string[] ; input?: string ; model?: string } & { maxTokens?: number ; temperature?: number } & OpenAIAuth & { answerSimilarity?: Scorer<string, {}> ; answerSimilarityWeight?: number ; factualityWeight?: number }, T>>>
Type parameters
| Name | Type |
|---|---|
T | extends "model" | "maxTokens" | "temperature" | keyof OpenAIAuth | "input" | "context" | "factualityWeight" | "answerSimilarityWeight" | "answerSimilarity" |
Parameters
| Name | Type |
|---|---|
args | { [K in "model" | "maxTokens" | "temperature" | keyof OpenAIAuth | "input" | "context" | "factualityWeight" | "answerSimilarityWeight" | "answerSimilarity"]: (Object & Object & OpenAIAuth & Object)[K] } |
Returns
Scorer<string, Omit<{ context?: string | string[] ; input?: string ; model?: string } & { maxTokens?: number ; temperature?: number } & OpenAIAuth & { answerSimilarity?: Scorer<string, {}> ; answerSimilarityWeight?: number ; factualityWeight?: number }, T> & Partial<Pick<{ context?: string | string[] ; input?: string ; model?: string } & { maxTokens?: number ; temperature?: number } & OpenAIAuth & { answerSimilarity?: Scorer<string, {}> ; answerSimilarityWeight?: number ; factualityWeight?: number }, T>>>