LightRAG/lightrag/evaluation
clssck 9f5948650e chore(lightrag): add wikipedia test dataset for evaluation
Add comprehensive test dataset with 7 domain-specific Wikipedia documents
(climate, finance, medical, sports) and corresponding test cases in JSON format.
Total of 2292 lines of test data across 8 files for RAG quality evaluation
and end-to-end testing infrastructure.
2025-11-30 20:14:52 +01:00
..
sample_documents feat(evaluation): Add sample documents for reproducible RAGAS testing 2025-11-03 13:28:46 +01:00
wiki_documents chore(lightrag): add wikipedia test dataset for evaluation 2025-11-30 20:14:52 +01:00
__init__.py fix(evaluation): Move import-time validation to runtime and improve documentation 2025-11-03 05:56:38 +01:00
compare_results.py chore(docker-compose, lightrag): optimize test infrastructure and add evaluation tools 2025-11-29 10:39:20 +01:00
download_wikipedia.py chore(docker-compose, lightrag): optimize test infrastructure and add evaluation tools 2025-11-29 10:39:20 +01:00
e2e_test_harness.py chore(docker-compose, lightrag): optimize test infrastructure and add evaluation tools 2025-11-29 10:39:20 +01:00
eval_rag_quality.py Add separate endpoint configuration for LLM and embeddings in evaluation 2025-11-05 18:54:38 +08:00
ingest_test_docs.py chore(docker-compose, lightrag): optimize test infrastructure and add evaluation tools 2025-11-29 10:39:20 +01:00
populate_test_data.sh chore(docker-compose, lightrag): optimize test infrastructure and add evaluation tools 2025-11-29 10:39:20 +01:00
README_EVALUASTION_RAGAS.md Update LLM cache migration docs and improve UX prompts 2025-11-08 23:48:19 +08:00
sample_dataset.json Update evaluation defaults and expand sample dataset 2025-11-04 22:17:17 +08:00
wiki_test_dataset.json chore(lightrag): add wikipedia test dataset for evaluation 2025-11-30 20:14:52 +01:00