refactor: benchmarks code style

This commit is contained in:
Johann Schopplich
2025-10-28 08:02:57 +01:00
parent 833c99ea38
commit cdd4a20c67
3 changed files with 24 additions and 8 deletions

View File

@@ -28,8 +28,20 @@ export const models: Record<string, LanguageModelV2> = {
* Evaluate a single question with a specific format and model
*/
export async function evaluateQuestion(
{ question, formatName, formattedData, model, modelName}:
{ question: Question, formatName: string, formattedData: string, model: LanguageModelV2, modelName: string },
{
question,
formatName,
formattedData,
model,
modelName,
}:
{
question: Question
formatName: string
formattedData: string
model: LanguageModelV2
modelName: string
},
): Promise<EvaluationResult> {
const prompt = `
Given the following data in ${formatName} format:
@@ -79,7 +91,11 @@ async function validateAnswer(
expected,
question,
}:
{ actual: string, expected: string, question: string },
{
actual: string
expected: string
question: string
},
): Promise<boolean> {
const prompt = `
You are validating answers to questions about structured data.

View File

@@ -72,7 +72,7 @@ function toCSV(data: unknown): string {
* Convert data to XML format
*
* @remarks
* Uses fast-xml-parser to generate well-formatted XML with:
* Uses `fast-xml-parser` to generate well-formatted XML with:
* - 2-space indentation for readability
* - Empty nodes suppressed
* - Proper escaping of special characters

View File

@@ -29,10 +29,10 @@ export function generateQuestions(): Question[] {
let idCounter = 1
// Get datasets with proper typing
const tabular = (datasets.find(d => d.name === 'tabular')?.data.employees as Employee[]) || []
const nested = (datasets.find(d => d.name === 'nested')?.data.orders as Order[]) || []
const analytics = (datasets.find(d => d.name === 'analytics')?.data.metrics as AnalyticsMetric[]) || []
const github = (datasets.find(d => d.name === 'github')?.data.repositories as Repository[]) || []
const tabular = (datasets.find(d => d.name === 'tabular')?.data.employees as Employee[]) ?? []
const nested = (datasets.find(d => d.name === 'nested')?.data.orders as Order[]) ?? []
const analytics = (datasets.find(d => d.name === 'analytics')?.data.metrics as AnalyticsMetric[]) ?? []
const github = (datasets.find(d => d.name === 'github')?.data.repositories as Repository[]) ?? []
// ========================================
// TABULAR DATASET QUESTIONS (70 questions)