Skip to main content

Module benchmark

Module benchmark 

Source
Expand description

Benchmarking system for quality improvements Benchmarking system for GraphRAG quality improvements

This module provides comprehensive benchmarking tools to measure:

  • Accuracy improvements from new features
  • Token usage and cost reduction
  • Latency and throughput
  • Quality metrics (F1, Exact Match, BLEU)

Structsยง

BenchmarkConfig
Configuration for benchmark runs
BenchmarkDataset
Dataset for benchmarking
BenchmarkQuery
A single query with ground truth for evaluation
BenchmarkRunner
Main benchmarking coordinator
BenchmarkSummary
Aggregate benchmark results across multiple queries
LatencyMetrics
Latency breakdown by pipeline stage
QualityMetrics
Quality metrics for answer evaluation
QueryBenchmark
Benchmark results for a single query
TokenMetrics
Token usage tracking