gmakstutis/LightRAG
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Clean up RAG evaluator logging and remove excessive separator lines

Browse source 
• Remove excessive separator lines
• Add RAGAS concurrency comment
• Fix output buffer timing
This commit is contained in:
yangdx 2025-11-04 18:04:19 +08:00
parent 4e4b8d7e25
commit 6d61f70b92
1 changed files with 8 additions and 29 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

37
lightrag/evaluation/eval_rag_quality.py
View file

@ -185,13 +185,9 @@ class RAGEvaluator:
def _display_configuration(self): def _display_configuration(self):
"""Display all evaluation configuration settings""" """Display all evaluation configuration settings"""
logger.info("") logger.info("EVALUATION CONFIGURATION")
logger.info("%s", "=" * 70)
logger.info("🔧 EVALUATION CONFIGURATION")
logger.info("%s", "=" * 70)
logger.info("") logger.info(" Evaluation Models:")
logger.info("Evaluation Models:")
logger.info(" • LLM Model: %s", self.eval_model) logger.info(" • LLM Model: %s", self.eval_model)
logger.info(" • Embedding Model: %s", self.eval_embedding_model) logger.info(" • Embedding Model: %s", self.eval_embedding_model)
if self.eval_base_url: if self.eval_base_url:
@ -200,29 +196,18 @@ class RAGEvaluator:
else: else:
logger.info(" • Endpoint: OpenAI Official API") logger.info(" • Endpoint: OpenAI Official API")
logger.info("") logger.info(" Concurrency & Rate Limiting:")
logger.info("Concurrency & Rate Limiting:")
max_concurrent = int(os.getenv("EVAL_MAX_CONCURRENT", "1"))
query_top_k = int(os.getenv("EVAL_QUERY_TOP_K", "10")) query_top_k = int(os.getenv("EVAL_QUERY_TOP_K", "10"))
logger.info(
" • Max Concurrent: %s %s",
max_concurrent,
"(serial evaluation)" if max_concurrent == 1 else "parallel evaluations",
)
logger.info(" • Query Top-K: %s Entities/Relations", query_top_k) logger.info(" • Query Top-K: %s Entities/Relations", query_top_k)
logger.info(" • LLM Max Retries: %s", self.eval_max_retries) logger.info(" • LLM Max Retries: %s", self.eval_max_retries)
logger.info(" • LLM Timeout: %s seconds", self.eval_timeout) logger.info(" • LLM Timeout: %s seconds", self.eval_timeout)
logger.info("") logger.info(" Test Configuration:")
logger.info("Test Configuration:")
logger.info(" • Total Test Cases: %s", len(self.test_cases)) logger.info(" • Total Test Cases: %s", len(self.test_cases))
logger.info(" • Test Dataset: %s", self.test_dataset_path.name) logger.info(" • Test Dataset: %s", self.test_dataset_path.name)
logger.info(" • LightRAG API: %s", self.rag_api_url) logger.info(" • LightRAG API: %s", self.rag_api_url)
logger.info(" • Results Directory: %s", self.results_dir.name) logger.info(" • Results Directory: %s", self.results_dir.name)
logger.info("%s", "=" * 70)
logger.info("")
def _load_test_dataset(self) -> List[Dict[str, str]]: def _load_test_dataset(self) -> List[Dict[str, str]]:
"""Load test cases from JSON file""" """Load test cases from JSON file"""
if not self.test_dataset_path.exists(): if not self.test_dataset_path.exists():
@ -395,6 +380,8 @@ class RAGEvaluator:
) )
# Run RAGAS evaluation # Run RAGAS evaluation
# IMPORTANT: Create fresh metric instances for each evaluation to avoid
# concurrent state conflicts when multiple tasks run in parallel
try: try:
eval_results = evaluate( eval_results = evaluate(
dataset=eval_dataset, dataset=eval_dataset,
@ -478,7 +465,6 @@ class RAGEvaluator:
logger.info("🚀 Starting RAGAS Evaluation of Portfolio RAG System") logger.info("🚀 Starting RAGAS Evaluation of Portfolio RAG System")
logger.info("🔧 Concurrent evaluations: %s", max_async) logger.info("🔧 Concurrent evaluations: %s", max_async)
logger.info("%s", "=" * 70) logger.info("%s", "=" * 70)
logger.info("")
# Create semaphore to limit concurrent evaluations # Create semaphore to limit concurrent evaluations
semaphore = asyncio.Semaphore(max_async) semaphore = asyncio.Semaphore(max_async)
@ -770,12 +756,11 @@ class RAGEvaluator:
# Add a small delay to ensure all buffered output is completely written # Add a small delay to ensure all buffered output is completely written
await asyncio.sleep(0.2) await asyncio.sleep(0.2)
# Flush all output buffers to ensure RAGAS progress bars are fully displayed # Flush all output buffers to ensure RAGAS progress bars are fully displayed
# before showing our results table
sys.stdout.flush() sys.stdout.flush()
sys.stderr.flush() sys.stderr.flush()
# Make sure the progress bar line ends before logging summary output
await asyncio.sleep(0.2)
sys.stderr.write("\n") sys.stderr.write("\n")
sys.stderr.flush() sys.stderr.flush()
@ -867,15 +852,9 @@ async def main():
if len(sys.argv) > 1: if len(sys.argv) > 1:
rag_api_url = sys.argv[1] rag_api_url = sys.argv[1]
logger.info("")
logger.info("%s", "=" * 70) logger.info("%s", "=" * 70)
logger.info("🔍 RAGAS Evaluation - Using Real LightRAG API") logger.info("🔍 RAGAS Evaluation - Using Real LightRAG API")
logger.info("%s", "=" * 70) logger.info("%s", "=" * 70)
if rag_api_url:
logger.info("📡 RAG API URL: %s", rag_api_url)
else:
logger.info("📡 RAG API URL: http://localhost:9621 (default)")
logger.info("%s", "=" * 70)
evaluator = RAGEvaluator(rag_api_url=rag_api_url) evaluator = RAGEvaluator(rag_api_url=rag_api_url)
await evaluator.run() await evaluator.run()