deepeval 3.6.7__tar.gz → 3.6.8__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {deepeval-3.6.7 → deepeval-3.6.8}/PKG-INFO +1 -1
- deepeval-3.6.8/deepeval/_version.py +1 -0
- deepeval-3.6.8/deepeval/errors.py +24 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/evaluate/execute.py +725 -217
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/evaluate/types.py +1 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/evaluate/utils.py +13 -3
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/integrations/crewai/__init__.py +2 -1
- deepeval-3.6.8/deepeval/integrations/crewai/tool.py +71 -0
- deepeval-3.6.8/deepeval/integrations/llama_index/__init__.py +6 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/integrations/llama_index/handler.py +20 -21
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/integrations/pydantic_ai/instrumentator.py +125 -76
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/__init__.py +13 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/base_metric.py +1 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/contextual_precision/contextual_precision.py +27 -21
- deepeval-3.6.8/deepeval/metrics/conversational_g_eval/__init__.py +3 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/conversational_g_eval/conversational_g_eval.py +11 -7
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/dag/schema.py +1 -1
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/dag/templates.py +2 -2
- deepeval-3.6.8/deepeval/metrics/goal_accuracy/__init__.py +1 -0
- deepeval-3.6.8/deepeval/metrics/goal_accuracy/goal_accuracy.py +349 -0
- deepeval-3.6.8/deepeval/metrics/goal_accuracy/schema.py +17 -0
- deepeval-3.6.8/deepeval/metrics/goal_accuracy/template.py +235 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/hallucination/hallucination.py +8 -8
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/mcp/mcp_task_completion.py +7 -2
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/mcp/multi_turn_mcp_use_metric.py +16 -6
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/mcp_use_metric/mcp_use_metric.py +2 -1
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/multimodal_contextual_precision/multimodal_contextual_precision.py +32 -24
- deepeval-3.6.8/deepeval/metrics/plan_adherence/__init__.py +1 -0
- deepeval-3.6.8/deepeval/metrics/plan_adherence/plan_adherence.py +292 -0
- deepeval-3.6.8/deepeval/metrics/plan_adherence/schema.py +11 -0
- deepeval-3.6.8/deepeval/metrics/plan_adherence/template.py +170 -0
- deepeval-3.6.8/deepeval/metrics/plan_quality/__init__.py +1 -0
- deepeval-3.6.8/deepeval/metrics/plan_quality/plan_quality.py +292 -0
- deepeval-3.6.8/deepeval/metrics/plan_quality/schema.py +11 -0
- deepeval-3.6.8/deepeval/metrics/plan_quality/template.py +101 -0
- deepeval-3.6.8/deepeval/metrics/step_efficiency/__init__.py +1 -0
- deepeval-3.6.8/deepeval/metrics/step_efficiency/schema.py +11 -0
- deepeval-3.6.8/deepeval/metrics/step_efficiency/step_efficiency.py +234 -0
- deepeval-3.6.8/deepeval/metrics/step_efficiency/template.py +256 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/task_completion/task_completion.py +1 -0
- deepeval-3.6.8/deepeval/metrics/tool_correctness/schema.py +6 -0
- deepeval-3.6.8/deepeval/metrics/tool_correctness/template.py +88 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/tool_correctness/tool_correctness.py +226 -22
- deepeval-3.6.8/deepeval/metrics/tool_use/__init__.py +1 -0
- deepeval-3.6.8/deepeval/metrics/tool_use/schema.py +19 -0
- deepeval-3.6.8/deepeval/metrics/tool_use/template.py +220 -0
- deepeval-3.6.8/deepeval/metrics/tool_use/tool_use.py +458 -0
- deepeval-3.6.8/deepeval/metrics/topic_adherence/__init__.py +1 -0
- deepeval-3.6.8/deepeval/metrics/topic_adherence/schema.py +16 -0
- deepeval-3.6.8/deepeval/metrics/topic_adherence/template.py +162 -0
- deepeval-3.6.8/deepeval/metrics/topic_adherence/topic_adherence.py +355 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/embedding_models/azure_embedding_model.py +37 -36
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/embedding_models/local_embedding_model.py +30 -32
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/embedding_models/ollama_embedding_model.py +18 -20
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/embedding_models/openai_embedding_model.py +22 -31
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/openai/extractors.py +61 -16
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/openai/patch.py +8 -12
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/openai/types.py +1 -1
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/openai/utils.py +108 -1
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/prompt/prompt.py +1 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/prompt/utils.py +43 -14
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/synthesizer/synthesizer.py +11 -10
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/test_case/llm_test_case.py +6 -2
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/test_run/test_run.py +190 -207
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/tracing/__init__.py +2 -1
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/tracing/otel/exporter.py +3 -4
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/tracing/otel/utils.py +23 -4
- deepeval-3.6.8/deepeval/tracing/trace_context.py +98 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/tracing/tracing.py +23 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/tracing/types.py +16 -14
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/utils.py +21 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/pyproject.toml +1 -1
- deepeval-3.6.7/deepeval/_version.py +0 -1
- deepeval-3.6.7/deepeval/errors.py +0 -6
- deepeval-3.6.7/deepeval/integrations/llama_index/__init__.py +0 -10
- deepeval-3.6.7/deepeval/integrations/llama_index/agent/patched.py +0 -68
- deepeval-3.6.7/deepeval/synthesizer/chunking/__init__.py +0 -0
- deepeval-3.6.7/deepeval/tracing/message_types/__init__.py +0 -10
- deepeval-3.6.7/deepeval/tracing/message_types/base.py +0 -6
- deepeval-3.6.7/deepeval/tracing/message_types/messages.py +0 -14
- deepeval-3.6.7/deepeval/tracing/message_types/tools.py +0 -18
- deepeval-3.6.7/deepeval/tracing/trace_context.py +0 -83
- {deepeval-3.6.7 → deepeval-3.6.8}/LICENSE.md +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/README.md +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/annotation/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/annotation/annotation.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/annotation/api.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/arc/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/arc/arc.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/arc/mode.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/arc/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/base_benchmark.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/bbq/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/bbq/bbq.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/bbq/task.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/bbq/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/big_bench_hard.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/cot_prompts/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/cot_prompts/boolean_expressions.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/cot_prompts/causal_judgement.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/cot_prompts/date_understanding.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/cot_prompts/disambiguation_qa.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/cot_prompts/dyck_languages.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/cot_prompts/formal_fallacies.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/cot_prompts/geometric_shapes.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/cot_prompts/hyperbaton.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/cot_prompts/logical_deduction_five_objects.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/cot_prompts/logical_deduction_seven_objects.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/cot_prompts/logical_deduction_three_objects.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/cot_prompts/movie_recommendation.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/cot_prompts/multistep_arithmetic_two.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/cot_prompts/navigate.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/cot_prompts/object_counting.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/cot_prompts/penguins_in_a_table.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/cot_prompts/reasoning_about_colored_objects.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/cot_prompts/ruin_names.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/cot_prompts/salient_translation_error_detection.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/cot_prompts/snarks.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/cot_prompts/sports_understanding.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/cot_prompts/temporal_sequences.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/cot_prompts/tracking_shuffled_objects_five_objects.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/cot_prompts/tracking_shuffled_objects_seven_objects.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/cot_prompts/tracking_shuffled_objects_three_objects.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/cot_prompts/web_of_lies.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/cot_prompts/word_sorting.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/shot_prompts/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/shot_prompts/boolean_expressions.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/shot_prompts/causal_judgement.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/shot_prompts/date_understanding.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/shot_prompts/disambiguation_qa.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/shot_prompts/dyck_languages.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/shot_prompts/formal_fallacies.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/shot_prompts/geometric_shapes.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/shot_prompts/hyperbaton.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/shot_prompts/logical_deduction_five_objects.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/shot_prompts/logical_deduction_seven_objects.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/shot_prompts/logical_deduction_three_objects.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/shot_prompts/movie_recommendation.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/shot_prompts/multistep_arithmetic_two.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/shot_prompts/navigate.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/shot_prompts/object_counting.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/shot_prompts/penguins_in_a_table.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/shot_prompts/reasoning_about_colored_objects.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/shot_prompts/ruin_names.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/shot_prompts/salient_translation_error_detection.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/shot_prompts/snarks.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/shot_prompts/sports_understanding.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/shot_prompts/temporal_sequences.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/shot_prompts/tracking_shuffled_objects_five_objects.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/shot_prompts/tracking_shuffled_objects_seven_objects.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/shot_prompts/tracking_shuffled_objects_three_objects.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/shot_prompts/web_of_lies.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/shot_prompts/word_sorting.txt +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/task.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/big_bench_hard/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/bool_q/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/bool_q/bool_q.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/bool_q/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/drop/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/drop/drop.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/drop/task.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/drop/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/equity_med_qa/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/equity_med_qa/equity_med_qa.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/equity_med_qa/task.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/equity_med_qa/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/gsm8k/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/gsm8k/gsm8k.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/gsm8k/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/hellaswag/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/hellaswag/hellaswag.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/hellaswag/task.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/hellaswag/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/human_eval/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/human_eval/human_eval.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/human_eval/task.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/human_eval/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/ifeval/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/ifeval/ifeval.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/ifeval/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/lambada/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/lambada/lambada.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/lambada/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/logi_qa/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/logi_qa/logi_qa.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/logi_qa/task.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/logi_qa/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/math_qa/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/math_qa/math_qa.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/math_qa/task.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/math_qa/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/mmlu/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/mmlu/mmlu.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/mmlu/task.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/mmlu/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/modes/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/results.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/squad/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/squad/squad.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/squad/task.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/squad/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/tasks/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/truthful_qa/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/truthful_qa/mode.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/truthful_qa/task.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/truthful_qa/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/truthful_qa/truthful_qa.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/utils.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/winogrande/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/winogrande/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/benchmarks/winogrande/winogrande.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/cli/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/cli/dotenv_handler.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/cli/main.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/cli/server.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/cli/test.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/cli/types.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/cli/utils.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/confident/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/confident/api.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/confident/types.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/config/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/config/logging.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/config/settings.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/config/settings_manager.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/config/utils.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/constants.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/contextvars.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/dataset/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/dataset/api.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/dataset/dataset.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/dataset/golden.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/dataset/test_run_tracer.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/dataset/types.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/dataset/utils.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/evaluate/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/evaluate/api.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/evaluate/compare.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/evaluate/configs.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/evaluate/evaluate.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/integrations/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/integrations/crewai/handler.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/integrations/crewai/subs.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/integrations/crewai/wrapper.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/integrations/hugging_face/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/integrations/hugging_face/callback.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/integrations/hugging_face/rich_manager.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/integrations/hugging_face/tests/test_callbacks.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/integrations/hugging_face/utils.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/integrations/langchain/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/integrations/langchain/callback.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/integrations/langchain/patch.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/integrations/langchain/utils.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/integrations/llama_index/utils.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/integrations/pydantic_ai/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/integrations/pydantic_ai/agent.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/integrations/pydantic_ai/otel.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/integrations/pydantic_ai/test_instrumentator.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/key_handler.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/answer_relevancy/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/answer_relevancy/answer_relevancy.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/answer_relevancy/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/answer_relevancy/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/api.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/arena_g_eval/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/arena_g_eval/arena_g_eval.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/arena_g_eval/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/arena_g_eval/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/arena_g_eval/utils.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/argument_correctness/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/argument_correctness/argument_correctness.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/argument_correctness/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/argument_correctness/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/bias/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/bias/bias.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/bias/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/bias/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/contextual_precision/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/contextual_precision/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/contextual_precision/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/contextual_recall/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/contextual_recall/contextual_recall.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/contextual_recall/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/contextual_recall/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/contextual_relevancy/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/contextual_relevancy/contextual_relevancy.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/contextual_relevancy/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/contextual_relevancy/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/conversation_completeness/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/conversation_completeness/conversation_completeness.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/conversation_completeness/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/conversation_completeness/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/conversational_dag/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/conversational_dag/conversational_dag.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/conversational_dag/nodes.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/conversational_dag/templates.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/conversational_g_eval/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/conversational_g_eval/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/dag/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/dag/dag.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/dag/graph.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/dag/nodes.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/dag/utils.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/faithfulness/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/faithfulness/faithfulness.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/faithfulness/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/faithfulness/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/g_eval/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/g_eval/g_eval.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/g_eval/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/g_eval/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/g_eval/utils.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/hallucination/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/hallucination/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/hallucination/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/indicator.py +0 -0
- {deepeval-3.6.7/deepeval/metrics/conversational_g_eval → deepeval-3.6.8/deepeval/metrics/json_correctness}/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/json_correctness/json_correctness.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/json_correctness/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/json_correctness/template.py +0 -0
- {deepeval-3.6.7/deepeval/metrics/json_correctness → deepeval-3.6.8/deepeval/metrics/knowledge_retention}/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/knowledge_retention/knowledge_retention.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/knowledge_retention/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/knowledge_retention/template.py +0 -0
- {deepeval-3.6.7/deepeval/metrics/knowledge_retention → deepeval-3.6.8/deepeval/metrics/mcp}/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/mcp/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/mcp/template.py +0 -0
- {deepeval-3.6.7/deepeval/metrics/mcp → deepeval-3.6.8/deepeval/metrics/mcp_use_metric}/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/mcp_use_metric/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/mcp_use_metric/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/misuse/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/misuse/misuse.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/misuse/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/misuse/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/__init__.py +0 -0
- {deepeval-3.6.7/deepeval/metrics/mcp_use_metric → deepeval-3.6.8/deepeval/metrics/multimodal_metrics/image_coherence}/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/image_coherence/image_coherence.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/image_coherence/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/image_coherence/template.py +0 -0
- {deepeval-3.6.7/deepeval/metrics/multimodal_metrics/image_coherence → deepeval-3.6.8/deepeval/metrics/multimodal_metrics/image_editing}/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/image_editing/image_editing.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/image_editing/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/image_editing/template.py +0 -0
- {deepeval-3.6.7/deepeval/metrics/multimodal_metrics/image_editing → deepeval-3.6.8/deepeval/metrics/multimodal_metrics/image_helpfulness}/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/image_helpfulness/image_helpfulness.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/image_helpfulness/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/image_helpfulness/template.py +0 -0
- {deepeval-3.6.7/deepeval/metrics/multimodal_metrics/image_helpfulness → deepeval-3.6.8/deepeval/metrics/multimodal_metrics/image_reference}/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/image_reference/image_reference.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/image_reference/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/image_reference/template.py +0 -0
- {deepeval-3.6.7/deepeval/metrics/multimodal_metrics/image_reference → deepeval-3.6.8/deepeval/metrics/multimodal_metrics/multimodal_answer_relevancy}/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/multimodal_answer_relevancy/multimodal_answer_relevancy.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/multimodal_answer_relevancy/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/multimodal_answer_relevancy/template.py +0 -0
- {deepeval-3.6.7/deepeval/metrics/multimodal_metrics/multimodal_answer_relevancy → deepeval-3.6.8/deepeval/metrics/multimodal_metrics/multimodal_contextual_precision}/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/multimodal_contextual_precision/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/multimodal_contextual_precision/template.py +0 -0
- {deepeval-3.6.7/deepeval/metrics/multimodal_metrics/multimodal_contextual_precision → deepeval-3.6.8/deepeval/metrics/multimodal_metrics/multimodal_contextual_recall}/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/multimodal_contextual_recall/multimodal_contextual_recall.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/multimodal_contextual_recall/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/multimodal_contextual_recall/template.py +0 -0
- {deepeval-3.6.7/deepeval/metrics/multimodal_metrics/multimodal_contextual_recall → deepeval-3.6.8/deepeval/metrics/multimodal_metrics/multimodal_contextual_relevancy}/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/multimodal_contextual_relevancy/multimodal_contextual_relevancy.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/multimodal_contextual_relevancy/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/multimodal_contextual_relevancy/template.py +0 -0
- {deepeval-3.6.7/deepeval/metrics/multimodal_metrics/multimodal_contextual_relevancy → deepeval-3.6.8/deepeval/metrics/multimodal_metrics/multimodal_faithfulness}/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/multimodal_faithfulness/multimodal_faithfulness.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/multimodal_faithfulness/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/multimodal_faithfulness/template.py +0 -0
- {deepeval-3.6.7/deepeval/metrics/multimodal_metrics/multimodal_faithfulness → deepeval-3.6.8/deepeval/metrics/multimodal_metrics/multimodal_g_eval}/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/multimodal_g_eval/multimodal_g_eval.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/multimodal_g_eval/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/multimodal_g_eval/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/multimodal_g_eval/utils.py +0 -0
- {deepeval-3.6.7/deepeval/metrics/multimodal_metrics/multimodal_g_eval → deepeval-3.6.8/deepeval/metrics/multimodal_metrics/multimodal_tool_correctness}/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/multimodal_tool_correctness/multimodal_tool_correctness.py +0 -0
- {deepeval-3.6.7/deepeval/metrics/multimodal_metrics/multimodal_tool_correctness → deepeval-3.6.8/deepeval/metrics/multimodal_metrics/text_to_image}/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/text_to_image/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/text_to_image/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/multimodal_metrics/text_to_image/text_to_image.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/non_advice/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/non_advice/non_advice.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/non_advice/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/non_advice/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/pii_leakage/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/pii_leakage/pii_leakage.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/pii_leakage/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/pii_leakage/template.py +0 -0
- {deepeval-3.6.7/deepeval/metrics/multimodal_metrics/text_to_image → deepeval-3.6.8/deepeval/metrics/prompt_alignment}/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/prompt_alignment/prompt_alignment.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/prompt_alignment/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/prompt_alignment/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/ragas.py +0 -0
- {deepeval-3.6.7/deepeval/metrics/prompt_alignment → deepeval-3.6.8/deepeval/metrics/role_adherence}/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/role_adherence/role_adherence.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/role_adherence/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/role_adherence/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/role_violation/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/role_violation/role_violation.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/role_violation/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/role_violation/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/summarization/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/summarization/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/summarization/summarization.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/summarization/template.py +0 -0
- {deepeval-3.6.7/deepeval/metrics/role_adherence → deepeval-3.6.8/deepeval/metrics/task_completion}/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/task_completion/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/task_completion/template.py +0 -0
- {deepeval-3.6.7/deepeval/metrics/task_completion → deepeval-3.6.8/deepeval/metrics/tool_correctness}/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/toxicity/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/toxicity/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/toxicity/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/toxicity/toxicity.py +0 -0
- {deepeval-3.6.7/deepeval/metrics/tool_correctness → deepeval-3.6.8/deepeval/metrics/turn_relevancy}/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/turn_relevancy/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/turn_relevancy/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/turn_relevancy/turn_relevancy.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/metrics/utils.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/_summac_model.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/answer_relevancy_model.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/base_model.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/detoxify_model.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/embedding_models/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/hallucination_model.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/llms/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/llms/amazon_bedrock_model.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/llms/anthropic_model.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/llms/azure_model.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/llms/deepseek_model.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/llms/gemini_model.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/llms/grok_model.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/llms/kimi_model.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/llms/litellm_model.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/llms/local_model.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/llms/ollama_model.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/llms/openai_model.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/llms/utils.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/mlllms/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/mlllms/gemini_model.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/mlllms/ollama_model.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/mlllms/openai_model.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/retry_policy.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/summac_model.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/unbias_model.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/models/utils.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/openai/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/openai_agents/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/openai_agents/agent.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/openai_agents/callback_handler.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/openai_agents/extractors.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/openai_agents/patch.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/openai_agents/runner.py +0 -0
- {deepeval-3.6.7/deepeval/metrics/turn_relevancy → deepeval-3.6.8/deepeval/plugins}/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/plugins/plugin.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/progress_context.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/prompt/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/prompt/api.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/py.typed +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/red_teaming/README.md +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/scorer/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/scorer/scorer.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/simulator/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/simulator/conversation_simulator.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/simulator/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/simulator/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/singleton.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/synthesizer/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/synthesizer/base_synthesizer.py +0 -0
- {deepeval-3.6.7/deepeval/plugins → deepeval-3.6.8/deepeval/synthesizer/chunking}/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/synthesizer/chunking/context_generator.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/synthesizer/chunking/doc_chunker.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/synthesizer/config.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/synthesizer/schema.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/synthesizer/templates/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/synthesizer/templates/template.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/synthesizer/templates/template_extraction.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/synthesizer/templates/template_prompt.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/synthesizer/types.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/synthesizer/utils.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/telemetry.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/test_case/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/test_case/api.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/test_case/arena_test_case.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/test_case/conversational_test_case.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/test_case/mcp.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/test_case/mllm_test_case.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/test_case/utils.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/test_run/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/test_run/api.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/test_run/cache.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/test_run/hooks.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/test_run/hyperparameters.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/tracing/api.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/tracing/context.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/tracing/offline_evals/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/tracing/offline_evals/api.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/tracing/offline_evals/span.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/tracing/offline_evals/thread.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/tracing/offline_evals/trace.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/tracing/otel/__init__.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/tracing/otel/test_exporter.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/tracing/patchers.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/tracing/perf_epoch_bridge.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/tracing/trace_test_manager.py +0 -0
- {deepeval-3.6.7 → deepeval-3.6.8}/deepeval/tracing/utils.py +0 -0
|
@@ -0,0 +1 @@
|
|
|
1
|
+
__version__: str = "3.6.8"
|
|
@@ -0,0 +1,24 @@
|
|
|
1
|
+
class DeepEvalError(Exception):
|
|
2
|
+
"""Base class for framework-originated errors.
|
|
3
|
+
If raised and not handled, it will abort the current operation.
|
|
4
|
+
We may also stringify instances of this class and attach them to traces or spans to surface
|
|
5
|
+
non-fatal diagnostics while allowing the run to continue.
|
|
6
|
+
"""
|
|
7
|
+
|
|
8
|
+
|
|
9
|
+
class UserAppError(Exception):
|
|
10
|
+
"""Represents exceptions thrown by user LLM apps/tools.
|
|
11
|
+
We record these on traces or spans and keep the overall evaluation run alive.
|
|
12
|
+
"""
|
|
13
|
+
|
|
14
|
+
|
|
15
|
+
class MissingTestCaseParamsError(DeepEvalError):
|
|
16
|
+
"""Required test case fields are missing."""
|
|
17
|
+
|
|
18
|
+
pass
|
|
19
|
+
|
|
20
|
+
|
|
21
|
+
class MismatchedTestCaseInputsError(DeepEvalError):
|
|
22
|
+
"""Inputs provided to a metric or test case are inconsistent or invalid."""
|
|
23
|
+
|
|
24
|
+
pass
|