evals files

This index covers 77 source-grounded paths. Search matches file and directory names through D1 FTS5/BM25.

• evals/README.md
• evals/old/cognee_01042025/aggregate_metrics_v_deepeval.json
• evals/old/cognee_01042025/aggregate_metrics_v_direct_llm.json
• evals/old/cognee_01042025/metrics_output_cognee.json
• evals/old/cognee_01042025/metrics_output_cognee_direct_llm.json
• evals/old/cognee_01042025/metrics_output_cognee_human_eval.json
• evals/old/cognee_optimized_01042025/aggregate_metrics_4o_cognee_10.json
• evals/old/cognee_optimized_01042025/aggregate_metrics_4o_cognee_10_short.json
• evals/old/cognee_optimized_01042025/aggregate_metrics_4o_cognee_10_short_deepeval.json
• evals/old/cognee_optimized_01042025/metrics_output_cognee_4o_10.json
• evals/old/cognee_optimized_01042025/metrics_output_cognee_4o_10_short.json
• evals/old/comparative_eval/README.md
• evals/old/comparative_eval/helpers/calculate_aggregate_metrics.py
• evals/old/comparative_eval/helpers/convert_metrics.py
• evals/old/comparative_eval/helpers/modal_evaluate_answers.py
• evals/old/comparative_eval/hotpot_50_corpus.json
• evals/old/comparative_eval/hotpot_50_qa_pairs.json
• evals/old/falkor_01042025/aggregate_metrics_falkor_graphrag_sdk.json
• evals/old/falkor_01042025/aggregate_metrics_falkor_graphrag_sdk_direct_llm.json
• evals/old/falkor_01042025/hotpot_qa_falkor_graphrag_sdk.py
• evals/old/falkor_01042025/metrics_output_falkor_graph_sdk_human_eval.json
• evals/old/falkor_01042025/metrics_output_falkor_graphrag_sdk.json
• evals/old/falkor_01042025/metrics_output_falkor_graphrag_sdk_direct_llm.json
• evals/old/graphiti_01042025/aggregate_metrics_graphiti.json
• evals/old/graphiti_01042025/aggregate_metrics_graphiti_direct_llm.json
• evals/old/graphiti_01042025/hotpot_qa_graphiti.py
• evals/old/graphiti_01042025/metrics_output_graphiti.json
• evals/old/graphiti_01042025/metrics_output_graphiti_direct_llm.json
• evals/old/graphiti_01042025/metrics_output_graphiti_huma_eval.json
• evals/old/graphiti_updated/hotpot_qa_graphiti_results_old.json
• evals/old/graphiti_updated/hotpot_qa_graphiti_results_old_aggregate_metrics.json
• evals/old/graphiti_updated/hotpot_qa_graphiti_results_old_aggregate_metrics_direct_llm.json
• evals/old/graphiti_updated/hotpot_qa_graphiti_results_old_metrics.json
• evals/old/graphiti_updated/hotpot_qa_graphiti_results_old_metrics_direct_llm.json
• evals/old/hotpot_50_corpus.json
• evals/old/hotpot_50_qa_pairs.json
• evals/old/hotpot_qa_24_2025/README.md
• evals/old/hotpot_qa_24_2025/benchmark_summary_cognee.json
• evals/old/hotpot_qa_24_2025/benchmark_summary_competition.json
• evals/old/hotpot_qa_24_2025/plot_metrics.py
• evals/old/hotpot_qa_24_2025/requirements.txt
• evals/old/hotpot_qa_24_2025/src/analysis/analyze_results.py
• evals/old/hotpot_qa_24_2025/src/analysis/analyze_single_benchmark.py
• evals/old/hotpot_qa_24_2025/src/analysis/get_results.py
• evals/old/hotpot_qa_24_2025/src/analysis/process_results.py
• evals/old/hotpot_qa_24_2025/src/create_benchmark_summary_json.py
• evals/old/hotpot_qa_24_2025/src/helpers/calculate_aggregate_metrics.py
• evals/old/hotpot_qa_24_2025/src/helpers/convert_metrics.py
• evals/old/hotpot_qa_24_2025/src/helpers/modal_evaluate_answers.py
• evals/old/hotpot_qa_24_2025/src/hotpot_qa_24_corpus.json
• evals/old/hotpot_qa_24_2025/src/hotpot_qa_24_instance_filter.json
• evals/old/hotpot_qa_24_2025/src/hotpot_qa_24_qa_pairs.json
• evals/old/hotpot_qa_24_2025/src/hotpotqa_instances.py
• evals/old/hotpot_qa_24_2025/src/modal_apps/__init__.py
• evals/old/hotpot_qa_24_2025/src/modal_apps/modal_evaluate_qa.py
• evals/old/hotpot_qa_24_2025/src/modal_apps/modal_image.py
• evals/old/hotpot_qa_24_2025/src/modal_apps/modal_qa_benchmark_cognee.py
• evals/old/hotpot_qa_24_2025/src/modal_apps/modal_qa_benchmark_graphiti.py
• evals/old/hotpot_qa_24_2025/src/modal_apps/modal_qa_benchmark_lightrag.py
• evals/old/hotpot_qa_24_2025/src/modal_apps/modal_qa_benchmark_mem0.py
• evals/old/hotpot_qa_24_2025/src/modal_apps/test_neo4j_server.py
• evals/old/hotpot_qa_24_2025/src/pyproject.toml
• evals/old/hotpot_qa_24_2025/src/qa/__init__.py
• evals/old/hotpot_qa_24_2025/src/qa/qa_benchmark_base.py
• evals/old/hotpot_qa_24_2025/src/qa/qa_benchmark_cognee.py
• evals/old/hotpot_qa_24_2025/src/qa/qa_benchmark_graphiti.py
• evals/old/hotpot_qa_24_2025/src/qa/qa_benchmark_lightrag.py
• evals/old/hotpot_qa_24_2025/src/qa/qa_benchmark_mem0.py
• evals/old/hotpot_qa_24_2025/src/qa/run_graphiti_benchmark.py
• evals/old/hotpot_qa_24_2025/src/run_cross_benchmark_analysis.py
• evals/old/hotpot_qa_24_2025/src/visualize_benchmarks.py
• evals/old/mem0_01042025/aggregate_metrics_mem0.json
• evals/old/mem0_01042025/aggregate_metrics_mem0_direct_llm.json
• evals/old/mem0_01042025/hotpot_qa_mem0.py
• evals/old/mem0_01042025/metrics_output_mem0.json
• evals/old/mem0_01042025/metrics_output_mem0_direct_llm.json
• evals/old/mem0_01042025/metrics_output_mem0_human_eval.json