deepeval 3.7.5__py3-none-any.whl → 3.7.7__py3-none-any.whl
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/_version.py +1 -1
- deepeval/cli/main.py +2022 -759
- deepeval/cli/utils.py +208 -36
- deepeval/config/dotenv_handler.py +19 -0
- deepeval/config/settings.py +675 -245
- deepeval/config/utils.py +9 -1
- deepeval/dataset/api.py +23 -1
- deepeval/dataset/golden.py +106 -21
- deepeval/evaluate/evaluate.py +0 -3
- deepeval/evaluate/execute.py +162 -315
- deepeval/evaluate/utils.py +6 -30
- deepeval/key_handler.py +124 -51
- deepeval/metrics/__init__.py +0 -4
- deepeval/metrics/answer_relevancy/answer_relevancy.py +89 -132
- deepeval/metrics/answer_relevancy/template.py +102 -179
- deepeval/metrics/arena_g_eval/arena_g_eval.py +98 -96
- deepeval/metrics/arena_g_eval/template.py +17 -1
- deepeval/metrics/argument_correctness/argument_correctness.py +81 -87
- deepeval/metrics/argument_correctness/template.py +19 -2
- deepeval/metrics/base_metric.py +19 -41
- deepeval/metrics/bias/bias.py +102 -108
- deepeval/metrics/bias/template.py +14 -2
- deepeval/metrics/contextual_precision/contextual_precision.py +56 -92
- deepeval/metrics/contextual_recall/contextual_recall.py +58 -85
- deepeval/metrics/contextual_relevancy/contextual_relevancy.py +53 -83
- deepeval/metrics/conversation_completeness/conversation_completeness.py +101 -119
- deepeval/metrics/conversation_completeness/template.py +23 -3
- deepeval/metrics/conversational_dag/conversational_dag.py +12 -8
- deepeval/metrics/conversational_dag/nodes.py +66 -123
- deepeval/metrics/conversational_dag/templates.py +16 -0
- deepeval/metrics/conversational_g_eval/conversational_g_eval.py +47 -66
- deepeval/metrics/dag/dag.py +10 -0
- deepeval/metrics/dag/nodes.py +63 -126
- deepeval/metrics/dag/templates.py +14 -0
- deepeval/metrics/exact_match/exact_match.py +9 -1
- deepeval/metrics/faithfulness/faithfulness.py +82 -136
- deepeval/metrics/g_eval/g_eval.py +93 -79
- deepeval/metrics/g_eval/template.py +18 -1
- deepeval/metrics/g_eval/utils.py +7 -6
- deepeval/metrics/goal_accuracy/goal_accuracy.py +91 -76
- deepeval/metrics/goal_accuracy/template.py +21 -3
- deepeval/metrics/hallucination/hallucination.py +60 -75
- deepeval/metrics/hallucination/template.py +13 -0
- deepeval/metrics/indicator.py +11 -10
- deepeval/metrics/json_correctness/json_correctness.py +40 -38
- deepeval/metrics/json_correctness/template.py +10 -0
- deepeval/metrics/knowledge_retention/knowledge_retention.py +60 -97
- deepeval/metrics/knowledge_retention/schema.py +9 -3
- deepeval/metrics/knowledge_retention/template.py +12 -0
- deepeval/metrics/mcp/mcp_task_completion.py +72 -43
- deepeval/metrics/mcp/multi_turn_mcp_use_metric.py +93 -75
- deepeval/metrics/mcp/schema.py +4 -0
- deepeval/metrics/mcp/template.py +59 -0
- deepeval/metrics/mcp_use_metric/mcp_use_metric.py +58 -64
- deepeval/metrics/mcp_use_metric/template.py +12 -0
- deepeval/metrics/misuse/misuse.py +77 -97
- deepeval/metrics/misuse/template.py +15 -0
- deepeval/metrics/multimodal_metrics/__init__.py +0 -1
- deepeval/metrics/multimodal_metrics/image_coherence/image_coherence.py +37 -38
- deepeval/metrics/multimodal_metrics/image_editing/image_editing.py +55 -76
- deepeval/metrics/multimodal_metrics/image_helpfulness/image_helpfulness.py +37 -38
- deepeval/metrics/multimodal_metrics/image_reference/image_reference.py +37 -38
- deepeval/metrics/multimodal_metrics/text_to_image/text_to_image.py +57 -76
- deepeval/metrics/non_advice/non_advice.py +79 -105
- deepeval/metrics/non_advice/template.py +12 -0
- deepeval/metrics/pattern_match/pattern_match.py +12 -4
- deepeval/metrics/pii_leakage/pii_leakage.py +75 -106
- deepeval/metrics/pii_leakage/template.py +14 -0
- deepeval/metrics/plan_adherence/plan_adherence.py +63 -89
- deepeval/metrics/plan_adherence/template.py +11 -0
- deepeval/metrics/plan_quality/plan_quality.py +63 -87
- deepeval/metrics/plan_quality/template.py +9 -0
- deepeval/metrics/prompt_alignment/prompt_alignment.py +78 -86
- deepeval/metrics/prompt_alignment/template.py +12 -0
- deepeval/metrics/role_adherence/role_adherence.py +48 -71
- deepeval/metrics/role_adherence/template.py +14 -0
- deepeval/metrics/role_violation/role_violation.py +75 -108
- deepeval/metrics/role_violation/template.py +12 -0
- deepeval/metrics/step_efficiency/step_efficiency.py +55 -65
- deepeval/metrics/step_efficiency/template.py +11 -0
- deepeval/metrics/summarization/summarization.py +115 -183
- deepeval/metrics/summarization/template.py +19 -0
- deepeval/metrics/task_completion/task_completion.py +67 -73
- deepeval/metrics/tool_correctness/tool_correctness.py +43 -42
- deepeval/metrics/tool_use/schema.py +4 -0
- deepeval/metrics/tool_use/template.py +16 -2
- deepeval/metrics/tool_use/tool_use.py +72 -94
- deepeval/metrics/topic_adherence/schema.py +4 -0
- deepeval/metrics/topic_adherence/template.py +21 -1
- deepeval/metrics/topic_adherence/topic_adherence.py +68 -81
- deepeval/metrics/toxicity/template.py +13 -0
- deepeval/metrics/toxicity/toxicity.py +80 -99
- deepeval/metrics/turn_contextual_precision/schema.py +3 -3
- deepeval/metrics/turn_contextual_precision/template.py +9 -2
- deepeval/metrics/turn_contextual_precision/turn_contextual_precision.py +154 -154
- deepeval/metrics/turn_contextual_recall/schema.py +3 -3
- deepeval/metrics/turn_contextual_recall/template.py +8 -1
- deepeval/metrics/turn_contextual_recall/turn_contextual_recall.py +148 -143
- deepeval/metrics/turn_contextual_relevancy/schema.py +2 -2
- deepeval/metrics/turn_contextual_relevancy/template.py +8 -1
- deepeval/metrics/turn_contextual_relevancy/turn_contextual_relevancy.py +154 -157
- deepeval/metrics/turn_faithfulness/schema.py +1 -1
- deepeval/metrics/turn_faithfulness/template.py +8 -1
- deepeval/metrics/turn_faithfulness/turn_faithfulness.py +180 -203
- deepeval/metrics/turn_relevancy/template.py +14 -0
- deepeval/metrics/turn_relevancy/turn_relevancy.py +56 -69
- deepeval/metrics/utils.py +161 -91
- deepeval/models/__init__.py +2 -0
- deepeval/models/base_model.py +44 -6
- deepeval/models/embedding_models/azure_embedding_model.py +34 -12
- deepeval/models/embedding_models/local_embedding_model.py +22 -7
- deepeval/models/embedding_models/ollama_embedding_model.py +17 -6
- deepeval/models/embedding_models/openai_embedding_model.py +3 -2
- deepeval/models/llms/__init__.py +2 -0
- deepeval/models/llms/amazon_bedrock_model.py +229 -73
- deepeval/models/llms/anthropic_model.py +143 -48
- deepeval/models/llms/azure_model.py +169 -95
- deepeval/models/llms/constants.py +2032 -0
- deepeval/models/llms/deepseek_model.py +82 -35
- deepeval/models/llms/gemini_model.py +126 -67
- deepeval/models/llms/grok_model.py +128 -65
- deepeval/models/llms/kimi_model.py +129 -87
- deepeval/models/llms/litellm_model.py +94 -18
- deepeval/models/llms/local_model.py +115 -16
- deepeval/models/llms/ollama_model.py +97 -76
- deepeval/models/llms/openai_model.py +169 -311
- deepeval/models/llms/portkey_model.py +58 -16
- deepeval/models/llms/utils.py +5 -2
- deepeval/models/retry_policy.py +10 -5
- deepeval/models/utils.py +56 -4
- deepeval/simulator/conversation_simulator.py +49 -2
- deepeval/simulator/template.py +16 -1
- deepeval/synthesizer/synthesizer.py +19 -17
- deepeval/test_case/api.py +24 -45
- deepeval/test_case/arena_test_case.py +7 -2
- deepeval/test_case/conversational_test_case.py +55 -6
- deepeval/test_case/llm_test_case.py +60 -6
- deepeval/test_run/api.py +3 -0
- deepeval/test_run/test_run.py +6 -1
- deepeval/utils.py +26 -0
- {deepeval-3.7.5.dist-info → deepeval-3.7.7.dist-info}/METADATA +3 -3
- {deepeval-3.7.5.dist-info → deepeval-3.7.7.dist-info}/RECORD +145 -148
- deepeval/metrics/multimodal_metrics/multimodal_g_eval/__init__.py +0 -0
- deepeval/metrics/multimodal_metrics/multimodal_g_eval/multimodal_g_eval.py +0 -386
- deepeval/metrics/multimodal_metrics/multimodal_g_eval/schema.py +0 -11
- deepeval/metrics/multimodal_metrics/multimodal_g_eval/template.py +0 -133
- deepeval/metrics/multimodal_metrics/multimodal_g_eval/utils.py +0 -68
- {deepeval-3.7.5.dist-info → deepeval-3.7.7.dist-info}/LICENSE.md +0 -0
- {deepeval-3.7.5.dist-info → deepeval-3.7.7.dist-info}/WHEEL +0 -0
- {deepeval-3.7.5.dist-info → deepeval-3.7.7.dist-info}/entry_points.txt +0 -0
deepeval/_version.py
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
__version__: str = "3.7.
|
|
1
|
+
__version__: str = "3.7.7"
|