.dockerignore
.gitattributes
.gitignore
.pre-commit-config.yaml
.readthedocs.yml
CLAUDE.md
CODE_OF_CONDUCT.md
CONTRIBUTING.md
LICENSE
Makefile
README.md
SECURITY.md
mkdocs.yml
pyproject.toml
.claude/commands/create-pr.md
.claude/commands/fix-github-issue.md
.cursor/worktrees.json
.cursor/commands/git-pr.md
.cursor/rules/docs-diataxis-guidelines.mdc
.cursor/rules/docs-structure.mdc
.cursor/rules/project-structure.mdc
.cursor/rules/update-guide.mdc
.cursor/rules/use-uv-cli.mdc
.github/pull_request_template.md
.github/ISSUE_TEMPLATE/bug_report.md
.github/ISSUE_TEMPLATE/feature_request.md
.github/ISSUE_TEMPLATE/question.md
.github/workflows/ci.yaml
.github/workflows/claude-code-review.yml
.github/workflows/claude.yml
.github/workflows/issue-manager.yaml
.github/workflows/publish-examples.yml
.github/workflows/python-publish.yml
docs/INSTALL
docs/Makefile
docs/alfred.py
docs/index.md
docs/ipynb_to_md.py
docs/make.bat
docs/quoted_spans_metric.md
docs/_static/annotated_data.json
docs/_static/architecture.png
docs/_static/bar_plot.png
docs/_static/edited_chain_runs.json
docs/_static/favicon.ico
docs/_static/langsmith-dataset.png
docs/_static/langsmith-evaluation.png
docs/_static/langsmith-feedback.png
docs/_static/langsmith-ragas-chain-trace.png
docs/_static/langsmith_dashboard.png
docs/_static/list-score-traces-ragas.png
docs/_static/qasper_data_collection.png
docs/_static/r2r_integration_ragas_app.png
docs/_static/radar_plot.png
docs/_static/ragas_app.gif
docs/_static/sample_annotated_summary.json
docs/_static/traces-score-ragas.png
docs/_static/css/highlight_ipython3.css
docs/_static/css/highlight_ipython3_dark.css
docs/_static/css/highlight_ipython3_light.css
docs/_static/css/highlight_python.css
docs/_static/css/highlight_python_dark.css
docs/_static/css/highlight_python_light.css
docs/_static/css/ragas.css
docs/_static/imgs/_langgraph_agent_evaluation_28_0.jpg
docs/_static/imgs/after_training.png
docs/_static/imgs/annotation.png
docs/_static/imgs/bar-graph.svg
docs/_static/imgs/before_training.png
docs/_static/imgs/compare-emb-results.png
docs/_static/imgs/compare-embeddings.jpeg
docs/_static/imgs/compare-llm-result.png
docs/_static/imgs/compare-llms-front.jpeg
docs/_static/imgs/compare-llms-testset.png
docs/_static/imgs/component-wise-metrics.png
docs/_static/imgs/eval-evolve.png
docs/_static/imgs/howto_improve_rag_mlflow.png
docs/_static/imgs/kg_rag.png
docs/_static/imgs/langsmith-tracing-faithfullness.png
docs/_static/imgs/langsmith-tracing-overview.png
docs/_static/imgs/logo-black.svg
docs/_static/imgs/logo.png
docs/_static/imgs/metrics_mindmap.png
docs/_static/imgs/question_types.png
docs/_static/imgs/quickstart-output.png
docs/_static/imgs/ragas-logo.png
docs/_static/imgs/ragas_workflow_white.png
docs/_static/imgs/scenario_rag.png
docs/_static/imgs/testset_output.png
docs/_static/imgs/trace-langsmith.png
docs/_static/imgs/experiments_quickstart/hello_world.gif
docs/_static/imgs/experiments_quickstart/output_first_experiment.png
docs/_static/imgs/results/rag_eval_result.png
docs/_static/js/commonroom.js
docs/_static/js/header_border.js
docs/_static/js/mathjax.js
docs/_static/js/mendable_chat_bubble.js
docs/_static/js/toggle.js
docs/community/index.md
docs/concepts/datasets.md
docs/concepts/experimentation.md
docs/concepts/index.md
docs/concepts/components/eval_dataset.md
docs/concepts/components/eval_sample.md
docs/concepts/components/index.md
docs/concepts/components/prompt.md
docs/concepts/feedback/index.md
docs/concepts/metrics/index.md
docs/concepts/metrics/available_metrics/agents.md
docs/concepts/metrics/available_metrics/answer_correctness.md
docs/concepts/metrics/available_metrics/answer_relevance.md
docs/concepts/metrics/available_metrics/aspect_critic.md
docs/concepts/metrics/available_metrics/context_entities_recall.md
docs/concepts/metrics/available_metrics/context_precision.md
docs/concepts/metrics/available_metrics/context_recall.md
docs/concepts/metrics/available_metrics/factual_correctness.md
docs/concepts/metrics/available_metrics/faithfulness.md
docs/concepts/metrics/available_metrics/general_purpose.md
docs/concepts/metrics/available_metrics/index.md
docs/concepts/metrics/available_metrics/multi_modal_faithfulness.md
docs/concepts/metrics/available_metrics/multi_modal_relevance.md
docs/concepts/metrics/available_metrics/noise_sensitivity.md
docs/concepts/metrics/available_metrics/nvidia_metrics.md
docs/concepts/metrics/available_metrics/rubrics_based.md
docs/concepts/metrics/available_metrics/semantic_similarity.md
docs/concepts/metrics/available_metrics/sql.md
docs/concepts/metrics/available_metrics/summarization_score.md
docs/concepts/metrics/available_metrics/traditional.md
docs/concepts/metrics/overview/index.md
docs/concepts/test_data_generation/agents.md
docs/concepts/test_data_generation/index.md
docs/concepts/test_data_generation/rag.md
docs/extra/ragas-modern.css
docs/extra/style.css
docs/extra/components/choose_evaluator_llm.md
docs/extra/components/choose_generator_llm.md
docs/extra/fonts/Satoshi-Variable.ttf
docs/extra/fonts/Satoshi-VariableItalic.ttf
docs/extra/overrides/main.html
docs/getstarted/eval_mistake1.png
docs/getstarted/evals.md
docs/getstarted/experiments_quickstart.md
docs/getstarted/index.md
docs/getstarted/install.md
docs/getstarted/quickstart.md
docs/getstarted/rag_eval.gif
docs/getstarted/rag_eval.md
docs/getstarted/rag_testset_generation.md
docs/getstarted/raga_evaluation_output.png
docs/getstarted/ragas_evaluation_output_dashboard.png
docs/getstarted/ragas_get_started_evals.gif
docs/getstarted/testset_output.png
docs/getstarted/testset_output_dashboard.png
docs/howtos/index.md
docs/howtos/llm-adapters.md
docs/howtos/observability.md
docs/howtos/applications/_cost.md
docs/howtos/applications/add_to_ci.md
docs/howtos/applications/align-llm-as-judge.md
docs/howtos/applications/benchmark_llm.md
docs/howtos/applications/compare_embeddings.md
docs/howtos/applications/compare_llms.md
docs/howtos/applications/cost.ipynb
docs/howtos/applications/evaluate-and-improve-rag.md
docs/howtos/applications/evaluating_multi_turn_conversations.md
docs/howtos/applications/index.md
docs/howtos/applications/iterate_prompt.md
docs/howtos/applications/metrics_llm_calls.png
docs/howtos/applications/prompt_optimization.md
docs/howtos/applications/singlehop_testset_gen.md
docs/howtos/applications/text2sql.md
docs/howtos/applications/vertexai_alignment.md
docs/howtos/applications/vertexai_model_comparision.md
docs/howtos/applications/vertexai_x_ragas.md
docs/howtos/customizations/_caching.md
docs/howtos/customizations/_run_config.md
docs/howtos/customizations/caching.ipynb
docs/howtos/customizations/cancellation.md
docs/howtos/customizations/customize_models.md
docs/howtos/customizations/index.md
docs/howtos/customizations/run_config.ipynb
docs/howtos/customizations/metrics/_cost.md
docs/howtos/customizations/metrics/_metrics_language_adaptation.md
docs/howtos/customizations/metrics/_modifying-prompts-metrics.md
docs/howtos/customizations/metrics/_write_your_own_metric.md
docs/howtos/customizations/metrics/_write_your_own_metric_advanced.md
docs/howtos/customizations/metrics/cost.ipynb
docs/howtos/customizations/metrics/metrics_language_adaptation.ipynb
docs/howtos/customizations/metrics/modifying-prompts-metrics.ipynb
docs/howtos/customizations/metrics/tracing.md
docs/howtos/customizations/metrics/write_your_own_metric.ipynb
docs/howtos/customizations/metrics/write_your_own_metric_advanced.ipynb
docs/howtos/customizations/testgenerator/_language_adaptation.md
docs/howtos/customizations/testgenerator/_persona_generator.md
docs/howtos/customizations/testgenerator/_testgen-custom-single-hop.md
docs/howtos/customizations/testgenerator/_testgen-customisation.md
docs/howtos/customizations/testgenerator/index.md
docs/howtos/customizations/testgenerator/language_adaptation.ipynb
docs/howtos/customizations/testgenerator/persona_generator.ipynb
docs/howtos/customizations/testgenerator/testgen-custom-single-hop.ipynb
docs/howtos/customizations/testgenerator/testgen-customisation.ipynb
docs/howtos/integrations/_arize.md
docs/howtos/integrations/_athina.md
docs/howtos/integrations/_haystack.md
docs/howtos/integrations/_helicone.md
docs/howtos/integrations/_langchain.md
docs/howtos/integrations/_langfuse.md
docs/howtos/integrations/_langgraph_agent_evaluation.md
docs/howtos/integrations/_langsmith.md
docs/howtos/integrations/_llamaindex.md
docs/howtos/integrations/_openlayer.md
docs/howtos/integrations/_opik.md
docs/howtos/integrations/_tonic-validate.md
docs/howtos/integrations/_zeno.md
docs/howtos/integrations/amazon_bedrock.md
docs/howtos/integrations/arize.ipynb
docs/howtos/integrations/athina.ipynb
docs/howtos/integrations/gemini.md
docs/howtos/integrations/griptape.md
docs/howtos/integrations/haystack.ipynb
docs/howtos/integrations/haystack.md
docs/howtos/integrations/helicone.ipynb
docs/howtos/integrations/index.md
docs/howtos/integrations/langchain.ipynb
docs/howtos/integrations/langchain.md
docs/howtos/integrations/langfuse.ipynb
docs/howtos/integrations/langgraph_agent_evaluation.ipynb
docs/howtos/integrations/langsmith.ipynb
docs/howtos/integrations/langsmith.md
docs/howtos/integrations/llama_stack.md
docs/howtos/integrations/llamaindex.ipynb
docs/howtos/integrations/llamaindex_agents.md
docs/howtos/integrations/oci_genai.md
docs/howtos/integrations/openlayer.ipynb
docs/howtos/integrations/opik.ipynb
docs/howtos/integrations/r2r.md
docs/howtos/integrations/swarm_agent_evaluation.md
docs/howtos/integrations/tonic-validate.ipynb
docs/howtos/integrations/zeno.ipynb
docs/howtos/integrations/_langgraph_agent_evaluation_files/_langgraph_agent_evaluation_23_0.jpg
docs/howtos/integrations/nyc_wikipedia/nyc_text.txt
docs/howtos/migrations/migrate_from_v01_to_v02.md
docs/howtos/migrations/migrate_from_v03_to_v04.md
docs/references/aevaluate.md
docs/references/cache.md
docs/references/embeddings.md
docs/references/evaluate.md
docs/references/evaluation_schema.md
docs/references/executor.md
docs/references/generate.md
docs/references/graph.md
docs/references/index.md
docs/references/integrations.md
docs/references/llms.md
docs/references/metrics.md
docs/references/prompt.md
docs/references/run_config.md
docs/references/synthesizers.md
docs/references/testset_schema.md
docs/references/transforms.md
docs/tutorials/agent.md
docs/tutorials/index.md
docs/tutorials/prompt.md
docs/tutorials/rag.md
docs/tutorials/workflow.md
examples/LICENSE
examples/README.md
examples/gdrive_append_example.py
examples/gdrive_backend_example.py
examples/oci_genai_example.py
examples/pyproject.toml
examples/iterate_prompt/__init__.py
examples/iterate_prompt/evals.py
examples/iterate_prompt/promptv1.txt
examples/iterate_prompt/promptv2_fewshot.txt
examples/iterate_prompt/run_prompt.py
examples/iterate_prompt/datasets/support_triage.csv
examples/ragas_examples/__init__.py
examples/ragas_examples/agent_evals/__init__.py
examples/ragas_examples/agent_evals/agent.py
examples/ragas_examples/agent_evals/evals.py
examples/ragas_examples/benchmark_llm/__init__.py
examples/ragas_examples/benchmark_llm/evals.py
examples/ragas_examples/benchmark_llm/prompt.py
examples/ragas_examples/benchmark_llm/datasets/discount_benchmark.csv
examples/ragas_examples/improve_rag/__init__.py
examples/ragas_examples/improve_rag/evals.py
examples/ragas_examples/improve_rag/rag.py
examples/ragas_examples/improve_rag/datasets/hf_doc_qa_eval.csv
examples/ragas_examples/judge_alignment/__init__.py
examples/ragas_examples/judge_alignment/evals.py
examples/ragas_examples/llamaIndex_agent_evals/__init__.py
examples/ragas_examples/llamaIndex_agent_evals/evals.py
examples/ragas_examples/llamaIndex_agent_evals/llamaindex_agent.py
examples/ragas_examples/llamaIndex_agent_evals/contexts/ambiguous_removal_request.json
examples/ragas_examples/llamaIndex_agent_evals/contexts/duplicate_addition.json
examples/ragas_examples/llamaIndex_agent_evals/contexts/repeated_removal.json
examples/ragas_examples/prompt_evals/__init__.py
examples/ragas_examples/prompt_evals/evals.py
examples/ragas_examples/prompt_evals/prompt.py
examples/ragas_examples/rag_eval/__init__.py
examples/ragas_examples/rag_eval/evals.py
examples/ragas_examples/rag_eval/pyproject.toml
examples/ragas_examples/rag_eval/rag.py
examples/ragas_examples/text2sql/__init__.py
examples/ragas_examples/text2sql/analyze_errors.py
examples/ragas_examples/text2sql/data_utils.py
examples/ragas_examples/text2sql/db_utils.py
examples/ragas_examples/text2sql/evals.py
examples/ragas_examples/text2sql/prompt.txt
examples/ragas_examples/text2sql/prompt_v2.txt
examples/ragas_examples/text2sql/prompt_v3.txt
examples/ragas_examples/text2sql/text2sql_agent.py
examples/ragas_examples/text2sql/validate_sql_dataset.py
examples/ragas_examples/text2sql/datasets/booksql_sample.csv
examples/ragas_examples/workflow_eval/__init__.py
examples/ragas_examples/workflow_eval/evals.py
examples/ragas_examples/workflow_eval/workflow.py
scripts/dev_docs.sh
src/ragas/__init__.py
src/ragas/_analytics.py
src/ragas/_version.py
src/ragas/async_utils.py
src/ragas/cache.py
src/ragas/callbacks.py
src/ragas/cli.py
src/ragas/config.py
src/ragas/cost.py
src/ragas/dataset.py
src/ragas/dataset_schema.py
src/ragas/evaluation.py
src/ragas/exceptions.py
src/ragas/executor.py
src/ragas/experiment.py
src/ragas/losses.py
src/ragas/messages.py
src/ragas/py.typed
src/ragas/run_config.py
src/ragas/sdk.py
src/ragas/utils.py
src/ragas/validation.py
src/ragas.egg-info/PKG-INFO
src/ragas.egg-info/SOURCES.txt
src/ragas.egg-info/dependency_links.txt
src/ragas.egg-info/entry_points.txt
src/ragas.egg-info/requires.txt
src/ragas.egg-info/top_level.txt
src/ragas/backends/README.md
src/ragas/backends/__init__.py
src/ragas/backends/base.py
src/ragas/backends/gdrive_backend.md
src/ragas/backends/gdrive_backend.py
src/ragas/backends/inmemory.py
src/ragas/backends/local_csv.py
src/ragas/backends/local_jsonl.py
src/ragas/backends/registry.py
src/ragas/backends/utils.py
src/ragas/embeddings/__init__.py
src/ragas/embeddings/base.py
src/ragas/embeddings/google_provider.py
src/ragas/embeddings/haystack_wrapper.py
src/ragas/embeddings/huggingface_provider.py
src/ragas/embeddings/litellm_provider.py
src/ragas/embeddings/openai_provider.py
src/ragas/embeddings/utils.py
src/ragas/integrations/__init__.py
src/ragas/integrations/amazon_bedrock.py
src/ragas/integrations/griptape.py
src/ragas/integrations/helicone.py
src/ragas/integrations/langchain.py
src/ragas/integrations/langgraph.py
src/ragas/integrations/langsmith.py
src/ragas/integrations/llama_index.py
src/ragas/integrations/opik.py
src/ragas/integrations/r2r.py
src/ragas/integrations/swarm.py
src/ragas/integrations/tracing/__init__.py
src/ragas/integrations/tracing/langfuse.py
src/ragas/integrations/tracing/mlflow.py
src/ragas/llms/__init__.py
src/ragas/llms/base.py
src/ragas/llms/haystack_wrapper.py
src/ragas/llms/litellm_llm.py
src/ragas/llms/oci_genai_wrapper.py
src/ragas/llms/adapters/__init__.py
src/ragas/llms/adapters/base.py
src/ragas/llms/adapters/instructor.py
src/ragas/llms/adapters/litellm.py
src/ragas/metrics/__init__.py
src/ragas/metrics/_answer_correctness.py
src/ragas/metrics/_answer_relevance.py
src/ragas/metrics/_answer_similarity.py
src/ragas/metrics/_aspect_critic.py
src/ragas/metrics/_bleu_score.py
src/ragas/metrics/_chrf_score.py
src/ragas/metrics/_context_entities_recall.py
src/ragas/metrics/_context_precision.py
src/ragas/metrics/_context_recall.py
src/ragas/metrics/_datacompy_score.py
src/ragas/metrics/_domain_specific_rubrics.py
src/ragas/metrics/_factual_correctness.py
src/ragas/metrics/_faithfulness.py
src/ragas/metrics/_goal_accuracy.py
src/ragas/metrics/_instance_specific_rubrics.py
src/ragas/metrics/_multi_modal_faithfulness.py
src/ragas/metrics/_multi_modal_relevance.py
src/ragas/metrics/_noise_sensitivity.py
src/ragas/metrics/_nv_metrics.py
src/ragas/metrics/_rouge_score.py
src/ragas/metrics/_simple_criteria.py
src/ragas/metrics/_sql_semantic_equivalence.py
src/ragas/metrics/_string.py
src/ragas/metrics/_summarization.py
src/ragas/metrics/_tool_call_accuracy.py
src/ragas/metrics/_tool_call_f1.py
src/ragas/metrics/_topic_adherence.py
src/ragas/metrics/base.py
src/ragas/metrics/decorator.py
src/ragas/metrics/discrete.py
src/ragas/metrics/numeric.py
src/ragas/metrics/quoted_spans.py
src/ragas/metrics/ranking.py
src/ragas/metrics/result.py
src/ragas/metrics/utils.py
src/ragas/metrics/validators.py
src/ragas/metrics/collections/__init__.py
src/ragas/metrics/collections/_bleu_score.py
src/ragas/metrics/collections/_rouge_score.py
src/ragas/metrics/collections/_semantic_similarity.py
src/ragas/metrics/collections/_string.py
src/ragas/metrics/collections/base.py
src/ragas/metrics/collections/example_metric.py
src/ragas/metrics/collections/answer_accuracy/__init__.py
src/ragas/metrics/collections/answer_accuracy/metric.py
src/ragas/metrics/collections/answer_accuracy/util.py
src/ragas/metrics/collections/answer_correctness/__init__.py
src/ragas/metrics/collections/answer_correctness/metric.py
src/ragas/metrics/collections/answer_correctness/util.py
src/ragas/metrics/collections/answer_relevancy/__init__.py
src/ragas/metrics/collections/answer_relevancy/metric.py
src/ragas/metrics/collections/answer_relevancy/util.py
src/ragas/metrics/collections/context_entity_recall/__init__.py
src/ragas/metrics/collections/context_entity_recall/metric.py
src/ragas/metrics/collections/context_entity_recall/util.py
src/ragas/metrics/collections/context_precision/__init__.py
src/ragas/metrics/collections/context_precision/metric.py
src/ragas/metrics/collections/context_precision/util.py
src/ragas/metrics/collections/context_recall/__init__.py
src/ragas/metrics/collections/context_recall/metric.py
src/ragas/metrics/collections/context_recall/util.py
src/ragas/metrics/collections/context_relevance/__init__.py
src/ragas/metrics/collections/context_relevance/metric.py
src/ragas/metrics/collections/context_relevance/util.py
src/ragas/metrics/collections/factual_correctness/__init__.py
src/ragas/metrics/collections/factual_correctness/metric.py
src/ragas/metrics/collections/factual_correctness/util.py
src/ragas/metrics/collections/faithfulness/__init__.py
src/ragas/metrics/collections/faithfulness/metric.py
src/ragas/metrics/collections/faithfulness/util.py
src/ragas/metrics/collections/noise_sensitivity/__init__.py
src/ragas/metrics/collections/noise_sensitivity/metric.py
src/ragas/metrics/collections/noise_sensitivity/util.py
src/ragas/metrics/collections/response_groundedness/__init__.py
src/ragas/metrics/collections/response_groundedness/metric.py
src/ragas/metrics/collections/response_groundedness/util.py
src/ragas/metrics/collections/summary_score/__init__.py
src/ragas/metrics/collections/summary_score/metric.py
src/ragas/metrics/collections/summary_score/util.py
src/ragas/optimizers/__init__.py
src/ragas/optimizers/base.py
src/ragas/optimizers/genetic.py
src/ragas/optimizers/utils.py
src/ragas/prompt/__init__.py
src/ragas/prompt/base.py
src/ragas/prompt/dynamic_few_shot.py
src/ragas/prompt/few_shot_pydantic_prompt.py
src/ragas/prompt/mixin.py
src/ragas/prompt/multi_modal_prompt.py
src/ragas/prompt/prompt-formats.md
src/ragas/prompt/pydantic_prompt.py
src/ragas/prompt/simple_prompt.py
src/ragas/prompt/utils.py
src/ragas/prompt/metrics/__init__.py
src/ragas/prompt/metrics/answer_accuracy.py
src/ragas/prompt/metrics/answer_correctness.py
src/ragas/prompt/metrics/answer_relevance.py
src/ragas/prompt/metrics/base_prompt.py
src/ragas/prompt/metrics/common.py
src/ragas/prompt/metrics/context_entity_recall.py
src/ragas/prompt/metrics/context_recall.py
src/ragas/prompt/metrics/context_relevance.py
src/ragas/prompt/metrics/factual_correctness.py
src/ragas/prompt/metrics/noise_sensitivity.py
src/ragas/prompt/metrics/response_groundedness.py
src/ragas/prompt/metrics/summary_score.py
src/ragas/testset/__init__.py
src/ragas/testset/graph.py
src/ragas/testset/graph_queries.py
src/ragas/testset/persona.py
src/ragas/testset/synthesizers/__init__.py
src/ragas/testset/synthesizers/base.py
src/ragas/testset/synthesizers/generate.py
src/ragas/testset/synthesizers/prompts.py
src/ragas/testset/synthesizers/testset_schema.py
src/ragas/testset/synthesizers/utils.py
src/ragas/testset/synthesizers/multi_hop/__init__.py
src/ragas/testset/synthesizers/multi_hop/abstract.py
src/ragas/testset/synthesizers/multi_hop/base.py
src/ragas/testset/synthesizers/multi_hop/prompts.py
src/ragas/testset/synthesizers/multi_hop/specific.py
src/ragas/testset/synthesizers/single_hop/__init__.py
src/ragas/testset/synthesizers/single_hop/base.py
src/ragas/testset/synthesizers/single_hop/prompts.py
src/ragas/testset/synthesizers/single_hop/specific.py
src/ragas/testset/transforms/__init__.py
src/ragas/testset/transforms/base.py
src/ragas/testset/transforms/default.py
src/ragas/testset/transforms/engine.py
src/ragas/testset/transforms/filters.py
src/ragas/testset/transforms/extractors/__init__.py
src/ragas/testset/transforms/extractors/embeddings.py
src/ragas/testset/transforms/extractors/llm_based.py
src/ragas/testset/transforms/extractors/regex_based.py
src/ragas/testset/transforms/relationship_builders/__init__.py
src/ragas/testset/transforms/relationship_builders/cosine.py
src/ragas/testset/transforms/relationship_builders/traditional.py
src/ragas/testset/transforms/splitters/__init__.py
src/ragas/testset/transforms/splitters/headline.py
tests/__init__.py
tests/conftest.py
tests/test_quoted_spans.py
tests/benchmarks/Dockerfile
tests/benchmarks/benchmark_eval.py
tests/benchmarks/benchmark_testsetgen.py
tests/benchmarks/utils.py
tests/e2e/__init__.py
tests/e2e/test_adaptation.py
tests/e2e/test_amnesty_in_ci.py
tests/e2e/test_dataset_utils.py
tests/e2e/test_fullflow.py
tests/e2e/test_langchain_llm_attributes.py
tests/e2e/test_testset_generation.py
tests/e2e/metrics_migration/__init__.py
tests/e2e/metrics_migration/base_migration_test.py
tests/e2e/metrics_migration/conftest.py
tests/e2e/metrics_migration/metric_score_diff.ipynb
tests/e2e/metrics_migration/plan-for-metrics-migration.md
tests/e2e/metrics_migration/test_answer_accuracy_migration.py
tests/e2e/metrics_migration/test_answer_correctness_migration.py
tests/e2e/metrics_migration/test_answer_relevancy_migration.py
tests/e2e/metrics_migration/test_bleu_migration.py
tests/e2e/metrics_migration/test_context_entity_recall_migration.py
tests/e2e/metrics_migration/test_context_precision_migration.py
tests/e2e/metrics_migration/test_context_recall_migration.py
tests/e2e/metrics_migration/test_context_relevance_migration.py
tests/e2e/metrics_migration/test_factual_correctness_migration.py
tests/e2e/metrics_migration/test_faithfulness_migration.py
tests/e2e/metrics_migration/test_noise_sensitivity_migration.py
tests/e2e/metrics_migration/test_response_groundedness_migration.py
tests/e2e/metrics_migration/test_rouge_migration.py
tests/e2e/metrics_migration/test_semantic_similarity_migration.py
tests/e2e/metrics_migration/test_string_migration.py
tests/e2e/metrics_migration/test_summary_score_migration.py
tests/e2e/metrics_migration/test_utils.py
tests/unit/test_analytics.py
tests/unit/test_async_evaluation.py
tests/unit/test_async_utils.py
tests/unit/test_cache.py
tests/unit/test_cancellation.py
tests/unit/test_chrf_score.py
tests/unit/test_cli.py
tests/unit/test_cosine_relationship_builders.py
tests/unit/test_cost.py
tests/unit/test_dataset_schema.py
tests/unit/test_datatable_inheritance.py
tests/unit/test_embeddings.py
tests/unit/test_engine.py
tests/unit/test_executor.py
tests/unit/test_executor_in_jupyter.ipynb
tests/unit/test_experiment.py
tests/unit/test_graph.py
tests/unit/test_import.py
tests/unit/test_knowledge_graph_clusters.py
tests/unit/test_knowledge_graph_save.py
tests/unit/test_langgraph.py
tests/unit/test_metric.py
tests/unit/test_metric_decorators.py
tests/unit/test_multi_hop_query_synthesizer.py
tests/unit/test_oci_genai_wrapper.py
tests/unit/test_optimizer_config.py
tests/unit/test_prompt.py
tests/unit/test_run_config.py
tests/unit/test_simple.py
tests/unit/test_simple_llm_metric_persistence.py
tests/unit/test_single_hop_query_synthesizer.py
tests/unit/test_testset_schema.py
tests/unit/test_tool_call_accuracy.py
tests/unit/test_tool_call_f1.py
tests/unit/test_traditional_relationship_builders.py
tests/unit/test_utils.py
tests/unit/test_uvloop_compatibility.py
tests/unit/test_validation.py
tests/unit/backends/test_gdrive_backend.py
tests/unit/backends/test_inmemory.py
tests/unit/backends/test_local_csv.py
tests/unit/backends/test_local_jsonl.py
tests/unit/integrations/test_tracing.py
tests/unit/integrations/test_tracing_simple.py
tests/unit/llms/test_adapters.py
tests/unit/llms/test_instructor_factory.py
tests/unit/llms/test_llm.py
tests/unit/prompt/test_dynamic_few_shot_prompt.py
tests/unit/prompt/test_prompt_mixin.py
tests/unit/prompt/test_prompt_save_load.py
tests/unit/prompt/test_prompt_utils.py
tests/utils/__init__.py
tests/utils/llm_setup.py
tests/utils/metric_comparison.py