CHANGELOG.md
MANIFEST.in
NOTICE.txt
README.md
TROUBLESHOOTING.md
migration_guide.md
pyproject.toml
setup.py
azure/__init__.py
azure/ai/__init__.py
azure/ai/evaluation/__init__.py
azure/ai/evaluation/_constants.py
azure/ai/evaluation/_eval_mapping.py
azure/ai/evaluation/_evaluator_definition.py
azure/ai/evaluation/_exceptions.py
azure/ai/evaluation/_http_utils.py
azure/ai/evaluation/_model_configurations.py
azure/ai/evaluation/_user_agent.py
azure/ai/evaluation/_version.py
azure/ai/evaluation/py.typed
azure/ai/evaluation/_aoai/__init__.py
azure/ai/evaluation/_aoai/aoai_grader.py
azure/ai/evaluation/_aoai/label_grader.py
azure/ai/evaluation/_aoai/python_grader.py
azure/ai/evaluation/_aoai/score_model_grader.py
azure/ai/evaluation/_aoai/string_check_grader.py
azure/ai/evaluation/_aoai/text_similarity_grader.py
azure/ai/evaluation/_azure/__init__.py
azure/ai/evaluation/_azure/_clients.py
azure/ai/evaluation/_azure/_envs.py
azure/ai/evaluation/_azure/_models.py
azure/ai/evaluation/_azure/_token_manager.py
azure/ai/evaluation/_common/__init__.py
azure/ai/evaluation/_common/_experimental.py
azure/ai/evaluation/_common/constants.py
azure/ai/evaluation/_common/evaluation_onedp_client.py
azure/ai/evaluation/_common/math.py
azure/ai/evaluation/_common/rai_service.py
azure/ai/evaluation/_common/utils.py
azure/ai/evaluation/_common/onedp/__init__.py
azure/ai/evaluation/_common/onedp/_client.py
azure/ai/evaluation/_common/onedp/_configuration.py
azure/ai/evaluation/_common/onedp/_model_base.py
azure/ai/evaluation/_common/onedp/_patch.py
azure/ai/evaluation/_common/onedp/_serialization.py
azure/ai/evaluation/_common/onedp/_types.py
azure/ai/evaluation/_common/onedp/_validation.py
azure/ai/evaluation/_common/onedp/_vendor.py
azure/ai/evaluation/_common/onedp/_version.py
azure/ai/evaluation/_common/onedp/py.typed
azure/ai/evaluation/_common/onedp/_utils/__init__.py
azure/ai/evaluation/_common/onedp/_utils/model_base.py
azure/ai/evaluation/_common/onedp/_utils/serialization.py
azure/ai/evaluation/_common/onedp/aio/__init__.py
azure/ai/evaluation/_common/onedp/aio/_client.py
azure/ai/evaluation/_common/onedp/aio/_configuration.py
azure/ai/evaluation/_common/onedp/aio/_patch.py
azure/ai/evaluation/_common/onedp/aio/operations/__init__.py
azure/ai/evaluation/_common/onedp/aio/operations/_operations.py
azure/ai/evaluation/_common/onedp/aio/operations/_patch.py
azure/ai/evaluation/_common/onedp/models/__init__.py
azure/ai/evaluation/_common/onedp/models/_enums.py
azure/ai/evaluation/_common/onedp/models/_models.py
azure/ai/evaluation/_common/onedp/models/_patch.py
azure/ai/evaluation/_common/onedp/operations/__init__.py
azure/ai/evaluation/_common/onedp/operations/_operations.py
azure/ai/evaluation/_common/onedp/operations/_patch.py
azure/ai/evaluation/_common/onedp/servicepatterns/__init__.py
azure/ai/evaluation/_common/onedp/servicepatterns/aio/__init__.py
azure/ai/evaluation/_common/onedp/servicepatterns/aio/operations/__init__.py
azure/ai/evaluation/_common/onedp/servicepatterns/aio/operations/_operations.py
azure/ai/evaluation/_common/onedp/servicepatterns/aio/operations/_patch.py
azure/ai/evaluation/_common/onedp/servicepatterns/buildingblocks/__init__.py
azure/ai/evaluation/_common/onedp/servicepatterns/buildingblocks/aio/__init__.py
azure/ai/evaluation/_common/onedp/servicepatterns/buildingblocks/aio/operations/__init__.py
azure/ai/evaluation/_common/onedp/servicepatterns/buildingblocks/aio/operations/_operations.py
azure/ai/evaluation/_common/onedp/servicepatterns/buildingblocks/aio/operations/_patch.py
azure/ai/evaluation/_common/onedp/servicepatterns/buildingblocks/operations/__init__.py
azure/ai/evaluation/_common/onedp/servicepatterns/buildingblocks/operations/_operations.py
azure/ai/evaluation/_common/onedp/servicepatterns/buildingblocks/operations/_patch.py
azure/ai/evaluation/_common/onedp/servicepatterns/operations/__init__.py
azure/ai/evaluation/_common/onedp/servicepatterns/operations/_operations.py
azure/ai/evaluation/_common/onedp/servicepatterns/operations/_patch.py
azure/ai/evaluation/_common/raiclient/__init__.py
azure/ai/evaluation/_common/raiclient/_client.py
azure/ai/evaluation/_common/raiclient/_configuration.py
azure/ai/evaluation/_common/raiclient/_model_base.py
azure/ai/evaluation/_common/raiclient/_patch.py
azure/ai/evaluation/_common/raiclient/_serialization.py
azure/ai/evaluation/_common/raiclient/_version.py
azure/ai/evaluation/_common/raiclient/py.typed
azure/ai/evaluation/_common/raiclient/aio/__init__.py
azure/ai/evaluation/_common/raiclient/aio/_client.py
azure/ai/evaluation/_common/raiclient/aio/_configuration.py
azure/ai/evaluation/_common/raiclient/aio/_patch.py
azure/ai/evaluation/_common/raiclient/aio/operations/__init__.py
azure/ai/evaluation/_common/raiclient/aio/operations/_operations.py
azure/ai/evaluation/_common/raiclient/aio/operations/_patch.py
azure/ai/evaluation/_common/raiclient/models/__init__.py
azure/ai/evaluation/_common/raiclient/models/_enums.py
azure/ai/evaluation/_common/raiclient/models/_models.py
azure/ai/evaluation/_common/raiclient/models/_patch.py
azure/ai/evaluation/_common/raiclient/operations/__init__.py
azure/ai/evaluation/_common/raiclient/operations/_operations.py
azure/ai/evaluation/_common/raiclient/operations/_patch.py
azure/ai/evaluation/_converters/__init__.py
azure/ai/evaluation/_converters/_ai_services.py
azure/ai/evaluation/_converters/_models.py
azure/ai/evaluation/_converters/_sk_services.py
azure/ai/evaluation/_evaluate/__init__.py
azure/ai/evaluation/_evaluate/_eval_run.py
azure/ai/evaluation/_evaluate/_evaluate.py
azure/ai/evaluation/_evaluate/_evaluate_aoai.py
azure/ai/evaluation/_evaluate/_utils.py
azure/ai/evaluation/_evaluate/_batch_run/__init__.py
azure/ai/evaluation/_evaluate/_batch_run/_run_submitter_client.py
azure/ai/evaluation/_evaluate/_batch_run/batch_clients.py
azure/ai/evaluation/_evaluate/_batch_run/code_client.py
azure/ai/evaluation/_evaluate/_batch_run/eval_run_context.py
azure/ai/evaluation/_evaluate/_batch_run/proxy_client.py
azure/ai/evaluation/_evaluate/_batch_run/target_run_context.py
azure/ai/evaluation/_evaluate/_telemetry/__init__.py
azure/ai/evaluation/_evaluators/__init__.py
azure/ai/evaluation/_evaluators/_bleu/__init__.py
azure/ai/evaluation/_evaluators/_bleu/_bleu.py
azure/ai/evaluation/_evaluators/_code_vulnerability/__init__.py
azure/ai/evaluation/_evaluators/_code_vulnerability/_code_vulnerability.py
azure/ai/evaluation/_evaluators/_coherence/__init__.py
azure/ai/evaluation/_evaluators/_coherence/_coherence.py
azure/ai/evaluation/_evaluators/_coherence/coherence.prompty
azure/ai/evaluation/_evaluators/_common/__init__.py
azure/ai/evaluation/_evaluators/_common/_base_eval.py
azure/ai/evaluation/_evaluators/_common/_base_multi_eval.py
azure/ai/evaluation/_evaluators/_common/_base_prompty_eval.py
azure/ai/evaluation/_evaluators/_common/_base_rai_svc_eval.py
azure/ai/evaluation/_evaluators/_common/_conversation_aggregators.py
azure/ai/evaluation/_evaluators/_common/_validators/__init__.py
azure/ai/evaluation/_evaluators/_common/_validators/_conversation_validator.py
azure/ai/evaluation/_evaluators/_common/_validators/_task_navigation_efficiency_validator.py
azure/ai/evaluation/_evaluators/_common/_validators/_tool_calls_validator.py
azure/ai/evaluation/_evaluators/_common/_validators/_tool_definitions_validator.py
azure/ai/evaluation/_evaluators/_common/_validators/_validation_constants.py
azure/ai/evaluation/_evaluators/_common/_validators/_validator_interface.py
azure/ai/evaluation/_evaluators/_content_safety/__init__.py
azure/ai/evaluation/_evaluators/_content_safety/_content_safety.py
azure/ai/evaluation/_evaluators/_content_safety/_hate_unfairness.py
azure/ai/evaluation/_evaluators/_content_safety/_self_harm.py
azure/ai/evaluation/_evaluators/_content_safety/_sexual.py
azure/ai/evaluation/_evaluators/_content_safety/_violence.py
azure/ai/evaluation/_evaluators/_document_retrieval/__init__.py
azure/ai/evaluation/_evaluators/_document_retrieval/_document_retrieval.py
azure/ai/evaluation/_evaluators/_eci/__init__.py
azure/ai/evaluation/_evaluators/_eci/_eci.py
azure/ai/evaluation/_evaluators/_f1_score/__init__.py
azure/ai/evaluation/_evaluators/_f1_score/_f1_score.py
azure/ai/evaluation/_evaluators/_fluency/__init__.py
azure/ai/evaluation/_evaluators/_fluency/_fluency.py
azure/ai/evaluation/_evaluators/_fluency/fluency.prompty
azure/ai/evaluation/_evaluators/_gleu/__init__.py
azure/ai/evaluation/_evaluators/_gleu/_gleu.py
azure/ai/evaluation/_evaluators/_groundedness/__init__.py
azure/ai/evaluation/_evaluators/_groundedness/_groundedness.py
azure/ai/evaluation/_evaluators/_groundedness/groundedness_with_query.prompty
azure/ai/evaluation/_evaluators/_groundedness/groundedness_without_query.prompty
azure/ai/evaluation/_evaluators/_intent_resolution/__init__.py
azure/ai/evaluation/_evaluators/_intent_resolution/_intent_resolution.py
azure/ai/evaluation/_evaluators/_intent_resolution/intent_resolution.prompty
azure/ai/evaluation/_evaluators/_meteor/__init__.py
azure/ai/evaluation/_evaluators/_meteor/_meteor.py
azure/ai/evaluation/_evaluators/_protected_material/__init__.py
azure/ai/evaluation/_evaluators/_protected_material/_protected_material.py
azure/ai/evaluation/_evaluators/_qa/__init__.py
azure/ai/evaluation/_evaluators/_qa/_qa.py
azure/ai/evaluation/_evaluators/_relevance/__init__.py
azure/ai/evaluation/_evaluators/_relevance/_relevance.py
azure/ai/evaluation/_evaluators/_relevance/relevance.prompty
azure/ai/evaluation/_evaluators/_response_completeness/__init__.py
azure/ai/evaluation/_evaluators/_response_completeness/_response_completeness.py
azure/ai/evaluation/_evaluators/_response_completeness/response_completeness.prompty
azure/ai/evaluation/_evaluators/_retrieval/__init__.py
azure/ai/evaluation/_evaluators/_retrieval/_retrieval.py
azure/ai/evaluation/_evaluators/_retrieval/retrieval.prompty
azure/ai/evaluation/_evaluators/_rouge/__init__.py
azure/ai/evaluation/_evaluators/_rouge/_rouge.py
azure/ai/evaluation/_evaluators/_service_groundedness/__init__.py
azure/ai/evaluation/_evaluators/_service_groundedness/_service_groundedness.py
azure/ai/evaluation/_evaluators/_similarity/__init__.py
azure/ai/evaluation/_evaluators/_similarity/_similarity.py
azure/ai/evaluation/_evaluators/_similarity/similarity.prompty
azure/ai/evaluation/_evaluators/_task_adherence/__init__.py
azure/ai/evaluation/_evaluators/_task_adherence/_task_adherence.py
azure/ai/evaluation/_evaluators/_task_adherence/task_adherence.prompty
azure/ai/evaluation/_evaluators/_task_completion/__init__.py
azure/ai/evaluation/_evaluators/_task_completion/_task_completion.py
azure/ai/evaluation/_evaluators/_task_completion/task_completion.prompty
azure/ai/evaluation/_evaluators/_task_navigation_efficiency/__init__.py
azure/ai/evaluation/_evaluators/_task_navigation_efficiency/_task_navigation_efficiency.py
azure/ai/evaluation/_evaluators/_tool_call_accuracy/__init__.py
azure/ai/evaluation/_evaluators/_tool_call_accuracy/_tool_call_accuracy.py
azure/ai/evaluation/_evaluators/_tool_call_accuracy/tool_call_accuracy.prompty
azure/ai/evaluation/_evaluators/_tool_call_success/__init__.py
azure/ai/evaluation/_evaluators/_tool_call_success/_tool_call_success.py
azure/ai/evaluation/_evaluators/_tool_call_success/tool_call_success.prompty
azure/ai/evaluation/_evaluators/_tool_input_accuracy/__init__.py
azure/ai/evaluation/_evaluators/_tool_input_accuracy/_tool_input_accuracy.py
azure/ai/evaluation/_evaluators/_tool_input_accuracy/tool_input_accuracy.prompty
azure/ai/evaluation/_evaluators/_tool_output_utilization/__init__.py
azure/ai/evaluation/_evaluators/_tool_output_utilization/_tool_output_utilization.py
azure/ai/evaluation/_evaluators/_tool_output_utilization/tool_output_utilization.prompty
azure/ai/evaluation/_evaluators/_tool_selection/__init__.py
azure/ai/evaluation/_evaluators/_tool_selection/_tool_selection.py
azure/ai/evaluation/_evaluators/_tool_selection/tool_selection.prompty
azure/ai/evaluation/_evaluators/_ungrounded_attributes/__init__.py
azure/ai/evaluation/_evaluators/_ungrounded_attributes/_ungrounded_attributes.py
azure/ai/evaluation/_evaluators/_xpia/__init__.py
azure/ai/evaluation/_evaluators/_xpia/xpia.py
azure/ai/evaluation/_legacy/__init__.py
azure/ai/evaluation/_legacy/_adapters/__init__.py
azure/ai/evaluation/_legacy/_adapters/_check.py
azure/ai/evaluation/_legacy/_adapters/_configuration.py
azure/ai/evaluation/_legacy/_adapters/_constants.py
azure/ai/evaluation/_legacy/_adapters/_errors.py
azure/ai/evaluation/_legacy/_adapters/_flows.py
azure/ai/evaluation/_legacy/_adapters/_service.py
azure/ai/evaluation/_legacy/_adapters/client.py
azure/ai/evaluation/_legacy/_adapters/entities.py
azure/ai/evaluation/_legacy/_adapters/tracing.py
azure/ai/evaluation/_legacy/_adapters/types.py
azure/ai/evaluation/_legacy/_adapters/utils.py
azure/ai/evaluation/_legacy/_batch_engine/__init__.py
azure/ai/evaluation/_legacy/_batch_engine/_config.py
azure/ai/evaluation/_legacy/_batch_engine/_engine.py
azure/ai/evaluation/_legacy/_batch_engine/_exceptions.py
azure/ai/evaluation/_legacy/_batch_engine/_openai_injector.py
azure/ai/evaluation/_legacy/_batch_engine/_result.py
azure/ai/evaluation/_legacy/_batch_engine/_run.py
azure/ai/evaluation/_legacy/_batch_engine/_run_storage.py
azure/ai/evaluation/_legacy/_batch_engine/_run_submitter.py
azure/ai/evaluation/_legacy/_batch_engine/_status.py
azure/ai/evaluation/_legacy/_batch_engine/_trace.py
azure/ai/evaluation/_legacy/_batch_engine/_utils.py
azure/ai/evaluation/_legacy/_batch_engine/_utils_deprecated.py
azure/ai/evaluation/_legacy/_common/__init__.py
azure/ai/evaluation/_legacy/_common/_async_token_provider.py
azure/ai/evaluation/_legacy/_common/_logging.py
azure/ai/evaluation/_legacy/_common/_thread_pool_executor_with_context.py
azure/ai/evaluation/_legacy/prompty/__init__.py
azure/ai/evaluation/_legacy/prompty/_connection.py
azure/ai/evaluation/_legacy/prompty/_exceptions.py
azure/ai/evaluation/_legacy/prompty/_prompty.py
azure/ai/evaluation/_legacy/prompty/_utils.py
azure/ai/evaluation/_legacy/prompty/_yaml_utils.py
azure/ai/evaluation/_safety_evaluation/__init__.py
azure/ai/evaluation/_safety_evaluation/_generated_rai_client.py
azure/ai/evaluation/_safety_evaluation/_safety_evaluation.py
azure/ai/evaluation/_vendor/__init__.py
azure/ai/evaluation/_vendor/rouge_score/__init__.py
azure/ai/evaluation/_vendor/rouge_score/rouge_scorer.py
azure/ai/evaluation/_vendor/rouge_score/scoring.py
azure/ai/evaluation/_vendor/rouge_score/tokenize.py
azure/ai/evaluation/_vendor/rouge_score/tokenizers.py
azure/ai/evaluation/red_team/__init__.py
azure/ai/evaluation/red_team/_attack_objective_generator.py
azure/ai/evaluation/red_team/_attack_strategy.py
azure/ai/evaluation/red_team/_callback_chat_target.py
azure/ai/evaluation/red_team/_default_converter.py
azure/ai/evaluation/red_team/_evaluation_processor.py
azure/ai/evaluation/red_team/_mlflow_integration.py
azure/ai/evaluation/red_team/_orchestrator_manager.py
azure/ai/evaluation/red_team/_red_team.py
azure/ai/evaluation/red_team/_red_team_result.py
azure/ai/evaluation/red_team/_result_processor.py
azure/ai/evaluation/red_team/_agent/__init__.py
azure/ai/evaluation/red_team/_agent/_agent_functions.py
azure/ai/evaluation/red_team/_agent/_agent_tools.py
azure/ai/evaluation/red_team/_agent/_agent_utils.py
azure/ai/evaluation/red_team/_agent/_semantic_kernel_plugin.py
azure/ai/evaluation/red_team/_foundry/__init__.py
azure/ai/evaluation/red_team/_foundry/_dataset_builder.py
azure/ai/evaluation/red_team/_foundry/_execution_manager.py
azure/ai/evaluation/red_team/_foundry/_foundry_result_processor.py
azure/ai/evaluation/red_team/_foundry/_rai_scorer.py
azure/ai/evaluation/red_team/_foundry/_scenario_orchestrator.py
azure/ai/evaluation/red_team/_foundry/_strategy_mapping.py
azure/ai/evaluation/red_team/_utils/__init__.py
azure/ai/evaluation/red_team/_utils/_rai_service_eval_chat_target.py
azure/ai/evaluation/red_team/_utils/_rai_service_target.py
azure/ai/evaluation/red_team/_utils/_rai_service_true_false_scorer.py
azure/ai/evaluation/red_team/_utils/constants.py
azure/ai/evaluation/red_team/_utils/exception_utils.py
azure/ai/evaluation/red_team/_utils/file_utils.py
azure/ai/evaluation/red_team/_utils/formatting_utils.py
azure/ai/evaluation/red_team/_utils/logging_utils.py
azure/ai/evaluation/red_team/_utils/metric_mapping.py
azure/ai/evaluation/red_team/_utils/objective_utils.py
azure/ai/evaluation/red_team/_utils/progress_utils.py
azure/ai/evaluation/red_team/_utils/retry_utils.py
azure/ai/evaluation/red_team/_utils/strategy_utils.py
azure/ai/evaluation/simulator/__init__.py
azure/ai/evaluation/simulator/_adversarial_scenario.py
azure/ai/evaluation/simulator/_adversarial_simulator.py
azure/ai/evaluation/simulator/_constants.py
azure/ai/evaluation/simulator/_direct_attack_simulator.py
azure/ai/evaluation/simulator/_indirect_attack_simulator.py
azure/ai/evaluation/simulator/_simulator.py
azure/ai/evaluation/simulator/_utils.py
azure/ai/evaluation/simulator/_conversation/__init__.py
azure/ai/evaluation/simulator/_conversation/_conversation.py
azure/ai/evaluation/simulator/_conversation/constants.py
azure/ai/evaluation/simulator/_data_sources/__init__.py
azure/ai/evaluation/simulator/_data_sources/grounding.json
azure/ai/evaluation/simulator/_helpers/__init__.py
azure/ai/evaluation/simulator/_helpers/_language_suffix_mapping.py
azure/ai/evaluation/simulator/_helpers/_simulator_data_classes.py
azure/ai/evaluation/simulator/_model_tools/__init__.py
azure/ai/evaluation/simulator/_model_tools/_generated_rai_client.py
azure/ai/evaluation/simulator/_model_tools/_identity_manager.py
azure/ai/evaluation/simulator/_model_tools/_proxy_completion_model.py
azure/ai/evaluation/simulator/_model_tools/_rai_client.py
azure/ai/evaluation/simulator/_model_tools/_template_handler.py
azure/ai/evaluation/simulator/_model_tools/models.py
azure/ai/evaluation/simulator/_prompty/__init__.py
azure/ai/evaluation/simulator/_prompty/task_query_response.prompty
azure/ai/evaluation/simulator/_prompty/task_simulate.prompty
azure_ai_evaluation.egg-info/PKG-INFO
azure_ai_evaluation.egg-info/SOURCES.txt
azure_ai_evaluation.egg-info/dependency_links.txt
azure_ai_evaluation.egg-info/not-zip-safe
azure_ai_evaluation.egg-info/requires.txt
azure_ai_evaluation.egg-info/top_level.txt
samples/README.md
samples/aoai_score_model_grader_sample.py
samples/evaluation_samples_common.py
samples/evaluation_samples_evaluate.py
samples/evaluation_samples_evaluate_fdp.py
samples/evaluation_samples_safety_evaluation.py
samples/evaluation_samples_simulate.py
samples/evaluation_samples_threshold.py
samples/red_team_agent_tool_sample.py
samples/red_team_samples.py
samples/red_team_skip_upload.py
samples/semantic_kernel_red_team_agent_sample.py
samples/agent_evaluators/agent_evaluation.ipynb
samples/agent_evaluators/coherence.ipynb
samples/agent_evaluators/fluency.ipynb
samples/agent_evaluators/groundedness.ipynb
samples/agent_evaluators/instructions.md
samples/agent_evaluators/intent_resolution.ipynb
samples/agent_evaluators/relevance.ipynb
samples/agent_evaluators/response_completeness.ipynb
samples/agent_evaluators/sample_synthetic_conversations.jsonl
samples/agent_evaluators/task_adherence.ipynb
samples/agent_evaluators/task_completion.ipynb
samples/agent_evaluators/task_navigation_efficiency.ipynb
samples/agent_evaluators/tool_call_accuracy.ipynb
samples/agent_evaluators/tool_input_accuracy.ipynb
samples/agent_evaluators/tool_output_utilization.ipynb
samples/agent_evaluators/tool_selection.ipynb
samples/agent_evaluators/tool_success.ipynb
samples/agent_evaluators/user_functions.py
samples/data/custom_objectives_with_context_example.json
samples/data/evaluate_test_data.jsonl
samples/score_model_multimodal/aoai_score_model_grader_sample_audio.py
samples/score_model_multimodal/aoai_score_model_grader_sample_audio_file.py
samples/score_model_multimodal/aoai_score_model_grader_sample_image.py
samples/score_model_multimodal/chat_compeletion_audio.py
samples/score_model_multimodal/image.jpg
samples/score_model_multimodal/input_audio.wav
tests/__init__.py
tests/__openai_patcher.py
tests/conftest.py
tests/converters/ai_agent_converter/serialization_helper.py
tests/converters/ai_agent_converter/test_ai_agent_converter_internals.py
tests/converters/ai_agent_converter/test_run_ids_from_conversation.py
tests/converters/ai_agent_converter/test_sk_agent_converter_internals.py
tests/converters/ai_agent_converter/test_sk_turn_idxs_from_conversation.py
tests/e2etests/__init__.py
tests/e2etests/target_fn.py
tests/e2etests/test_adv_simulator.py
tests/e2etests/test_aoai_graders.py
tests/e2etests/test_builtin_evaluators.py
tests/e2etests/test_evaluate.py
tests/e2etests/test_lite_management_client.py
tests/e2etests/test_mass_evaluate.py
tests/e2etests/test_metrics_upload.py
tests/e2etests/test_prompty_async.py
tests/e2etests/test_red_team.py
tests/e2etests/test_red_team_foundry.py
tests/e2etests/test_remote_evaluation.py
tests/e2etests/test_sim_and_eval.py
tests/e2etests/custom_evaluators/answer_length_with_aggregation.py
tests/unittests/test_agent_evaluators.py
tests/unittests/test_aoai_alignment_missing_rows.py
tests/unittests/test_aoai_data_source.py
tests/unittests/test_aoai_evaluation_pagination.py
tests/unittests/test_aoai_integration_features.py
tests/unittests/test_aoai_nested_integration.py
tests/unittests/test_aoai_python_grader.py
tests/unittests/test_aoai_score_model_grader.py
tests/unittests/test_batch_run_context.py
tests/unittests/test_built_in_evaluator.py
tests/unittests/test_completeness_evaluator.py
tests/unittests/test_content_safety_defect_rate.py
tests/unittests/test_content_safety_rai_script.py
tests/unittests/test_document_retrieval_evaluator.py
tests/unittests/test_eval_run.py
tests/unittests/test_evaluate.py
tests/unittests/test_evaluate_aoai.py
tests/unittests/test_evaluate_mismatch.py
tests/unittests/test_evaluate_performance.py
tests/unittests/test_evaluator_scoring_patterns.py
tests/unittests/test_groundedness_evaluator.py
tests/unittests/test_inline_image_fallback.py
tests/unittests/test_jailbreak_simulator.py
tests/unittests/test_jinja_sandbox.py
tests/unittests/test_lazy_imports.py
tests/unittests/test_logging.py
tests/unittests/test_mlflow_integration.py
tests/unittests/test_non_adv_simulator.py
tests/unittests/test_qa_evaluator.py
tests/unittests/test_remote_evaluation_features.py
tests/unittests/test_safety_evaluation.py
tests/unittests/test_save_eval.py
tests/unittests/test_simulator.py
tests/unittests/test_synthetic_callback_conv_bot.py
tests/unittests/test_synthetic_conversation_bot.py
tests/unittests/test_task_completion_evaluator.py
tests/unittests/test_task_navigation_efficiency_evaluators.py
tests/unittests/test_tool_call_accuracy_evaluator.py
tests/unittests/test_tool_input_accuracy_evaluator.py
tests/unittests/test_tool_selection_evaluator.py
tests/unittests/test_utils.py
tests/unittests/test_evaluators/slow_eval.py
tests/unittests/test_evaluators/test_conversation_thresholds.py
tests/unittests/test_evaluators/test_inputs_evaluators.py
tests/unittests/test_evaluators/test_service_evaluator_thresholds.py
tests/unittests/test_evaluators/test_threshold_behavior.py
tests/unittests/test_redteam/__init__.py
tests/unittests/test_redteam/test_attack_objective_generator.py
tests/unittests/test_redteam/test_attack_strategy.py
tests/unittests/test_redteam/test_callback_chat_target.py
tests/unittests/test_redteam/test_constants.py
tests/unittests/test_redteam/test_dataset_builder_binary_path.py
tests/unittests/test_redteam/test_formatting_utils.py
tests/unittests/test_redteam/test_foundry.py
tests/unittests/test_redteam/test_pyrit_workarounds.py
tests/unittests/test_redteam/test_rai_service_eval_chat_target.py
tests/unittests/test_redteam/test_rai_service_target.py
tests/unittests/test_redteam/test_rai_service_true_false_scorer.py
tests/unittests/test_redteam/test_red_team.py
tests/unittests/test_redteam/test_red_team_language_support.py
tests/unittests/test_redteam/test_red_team_result.py
tests/unittests/test_redteam/test_result_processor.py
tests/unittests/test_redteam/test_result_processor_criteria.py
tests/unittests/test_redteam/test_strategy_utils.py