LICENSE
NOTICE
README.md
pyproject.toml
backend/__init__.py
backend/api/__init__.py
backend/api/compare.py
backend/api/main.py
backend/core/__init__.py
backend/core/agent.py
backend/core/bedrock_client.py
backend/core/chat.py
backend/core/database.py
backend/core/document_chunking.py
backend/core/eval_results.py
backend/core/inspect_viewer.py
backend/core/judge_config.py
backend/core/judge_prompt_builder.py
backend/core/judge_tools.py
backend/core/jury_scoring.py
backend/core/logging_utils.py
backend/core/mcp_client.py
backend/core/pdf_report.py
backend/core/pipeline_stages.py
backend/core/pricing.py
backend/core/s3_client.py
backend/core/user_storage.py
backend/mcp_servers/__init__.py
backend/mcp_servers/server.py
backend/mcp_servers/dataset/__init__.py
backend/mcp_servers/dataset/agent.py
backend/mcp_servers/dataset/server_http.py
backend/mcp_servers/dataset/tools/__init__.py
backend/mcp_servers/dataset/tools/analyze_dataset.py
backend/mcp_servers/dataset/tools/save_dataset.py
backend/mcp_servers/providers/external_providers.py
backend/mcp_servers/providers/server_http.py
backend/mcp_servers/synthetic/__init__.py
backend/mcp_servers/synthetic/server_http.py
backend/mcp_servers/synthetic/tools/__init__.py
backend/mcp_servers/synthetic/tools/analyze_agent_image.py
backend/mcp_servers/synthetic/tools/analyze_agent_path.py
backend/mcp_servers/synthetic/tools/create_agent_eval_config.py
backend/mcp_servers/synthetic/tools/create_eval_config.py
backend/mcp_servers/synthetic/tools/create_pipeline_eval_config.py
backend/mcp_servers/synthetic/tools/generate_judge.py
backend/mcp_servers/synthetic/tools/generate_qa_pairs.py
backend/mcp_servers/synthetic/tools/get_evaluation_details.py
backend/mcp_servers/synthetic/tools/list_datasets.py
backend/mcp_servers/synthetic/tools/list_eval_configs.py
backend/mcp_servers/synthetic/tools/list_evaluations.py
backend/mcp_servers/synthetic/tools/list_judges.py
backend/mcp_servers/synthetic/tools/run_evaluation.py
eval_mcp/INSTALL.md
eval_mcp/__init__.py
eval_mcp/__main__.py
eval_mcp/bedrock.py
eval_mcp/bedrock_capture.py
eval_mcp/cli.py
eval_mcp/config.py
eval_mcp/judge_config.py
eval_mcp/pricing.py
eval_mcp/provider_pricing.json
eval_mcp/s3_sync.py
eval_mcp/server.py
eval_mcp/storage.py
eval_mcp/viewer.py
eval_mcp/core/__init__.py
eval_mcp/core/bedrock_client.py
eval_mcp/core/document_chunking.py
eval_mcp/core/eval_results.py
eval_mcp/core/judge_config.py
eval_mcp/core/logging_utils.py
eval_mcp/core/pdf_report.py
eval_mcp/core/pipeline_stages.py
eval_mcp/core/pricing.py
eval_mcp/core/provider_pricing.json
eval_mcp/core/s3_client.py
eval_mcp/core/user_storage.py
eval_mcp/tools/__init__.py
eval_mcp/tools/agent.py
eval_mcp/tools/analyze_agent_image.py
eval_mcp/tools/analyze_agent_path.py
eval_mcp/tools/analyze_dataset.py
eval_mcp/tools/create_agent_eval_config.py
eval_mcp/tools/create_config.py
eval_mcp/tools/create_pipeline_eval_config.py
eval_mcp/tools/external_providers.py
eval_mcp/tools/generate_judge.py
eval_mcp/tools/generate_qa.py
eval_mcp/tools/generate_report.py
eval_mcp/tools/get_evaluation_details.py
eval_mcp/tools/list_datasets.py
eval_mcp/tools/list_eval_configs.py
eval_mcp/tools/list_evaluations.py
eval_mcp/tools/list_judges.py
eval_mcp/tools/models.py
eval_mcp/tools/run_eval.py
eval_mcp/tools/save_dataset.py
eval_mcp/tools/server_http.py
eval_mcp/viewer_static/404.html
eval_mcp/viewer_static/chat.html
eval_mcp/viewer_static/chat.txt
eval_mcp/viewer_static/history.html
eval_mcp/viewer_static/history.txt
eval_mcp/viewer_static/index.html
eval_mcp/viewer_static/index.txt
eval_mcp/viewer_static/results.html
eval_mcp/viewer_static/results.txt
eval_mcp/viewer_static/_next/static/Mg1hQ5KJGpS7hl9NEzqRZ/_buildManifest.js
eval_mcp/viewer_static/_next/static/Mg1hQ5KJGpS7hl9NEzqRZ/_ssgManifest.js
eval_mcp/viewer_static/_next/static/chunks/255-6b79f309a27fb98b.js
eval_mcp/viewer_static/_next/static/chunks/4bd1b696-c023c6e3521b1417.js
eval_mcp/viewer_static/_next/static/chunks/633-0030f140570bab76.js
eval_mcp/viewer_static/_next/static/chunks/709-cf33b6ccc6fdbb71.js
eval_mcp/viewer_static/_next/static/chunks/framework-292291387d6b2e39.js
eval_mcp/viewer_static/_next/static/chunks/main-app-446b6bab9e866ff3.js
eval_mcp/viewer_static/_next/static/chunks/main-c05c20f710fed608.js
eval_mcp/viewer_static/_next/static/chunks/polyfills-42372ed130431b0a.js
eval_mcp/viewer_static/_next/static/chunks/webpack-3844d017889aa547.js
eval_mcp/viewer_static/_next/static/chunks/app/layout-eaaa69189c17325d.js
eval_mcp/viewer_static/_next/static/chunks/app/page-e6485ae15d5da087.js
eval_mcp/viewer_static/_next/static/chunks/app/_not-found/page-cd5373c361106a7f.js
eval_mcp/viewer_static/_next/static/chunks/app/chat/page-44b7594ba1469fcc.js
eval_mcp/viewer_static/_next/static/chunks/app/history/page-94442c60a89495e2.js
eval_mcp/viewer_static/_next/static/chunks/app/results/page-4cc299acecefa446.js
eval_mcp/viewer_static/_next/static/chunks/pages/_app-7d307437aca18ad4.js
eval_mcp/viewer_static/_next/static/chunks/pages/_error-cb2a52f75f2162e2.js
eval_mcp/viewer_static/_next/static/css/635eece9e6209c32.css
llm_evaluation_system.egg-info/PKG-INFO
llm_evaluation_system.egg-info/SOURCES.txt
llm_evaluation_system.egg-info/dependency_links.txt
llm_evaluation_system.egg-info/entry_points.txt
llm_evaluation_system.egg-info/requires.txt
llm_evaluation_system.egg-info/top_level.txt
tests/test_generate_qa_pairs.py
tests/test_generate_test_cases.py
tests/test_http_server.py
tests/test_multi_mcp.py