dd1413f3eb
Add comprehensive test suites for prompt evaluation: - test_prompt_accuracy.py: 365 lines testing prompt extraction accuracy - test_prompt_quality_deep.py: 672 lines for deep quality analysis - Refactor prompt.py to consolidate optimized variants (removed prompt_optimized.py) - Apply ruff formatting and type hints across 30 files - Update pyrightconfig.json for static type checking - Modernize reproduce scripts and examples with improved type annotations - Sync uv.lock dependencies
27 lines
682 B
Python
27 lines
682 B
Python
"""
|
|
LightRAG Evaluation Module
|
|
|
|
RAGAS-based evaluation framework for assessing RAG system quality.
|
|
|
|
Usage:
|
|
from lightrag.evaluation import RAGEvaluator
|
|
|
|
evaluator = RAGEvaluator()
|
|
results = await evaluator.run()
|
|
|
|
Note: RAGEvaluator is imported lazily to avoid import errors
|
|
when ragas/datasets are not installed.
|
|
"""
|
|
|
|
from typing import Any
|
|
|
|
__all__ = ['RAGEvaluator']
|
|
|
|
|
|
def __getattr__(name: str) -> Any:
|
|
"""Lazy import to avoid dependency errors when ragas is not installed."""
|
|
if name == 'RAGEvaluator':
|
|
from .eval_rag_quality import RAGEvaluator
|
|
|
|
return RAGEvaluator
|
|
raise AttributeError(f'module {__name__!r} has no attribute {name!r}')
|