deepeval 3.6.7__py3-none-any.whl → 3.6.8__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.
Files changed (80) hide show
  1. deepeval/_version.py +1 -1
  2. deepeval/errors.py +20 -2
  3. deepeval/evaluate/execute.py +725 -217
  4. deepeval/evaluate/types.py +1 -0
  5. deepeval/evaluate/utils.py +13 -3
  6. deepeval/integrations/crewai/__init__.py +2 -1
  7. deepeval/integrations/crewai/tool.py +71 -0
  8. deepeval/integrations/llama_index/__init__.py +0 -4
  9. deepeval/integrations/llama_index/handler.py +20 -21
  10. deepeval/integrations/pydantic_ai/instrumentator.py +125 -76
  11. deepeval/metrics/__init__.py +13 -0
  12. deepeval/metrics/base_metric.py +1 -0
  13. deepeval/metrics/contextual_precision/contextual_precision.py +27 -21
  14. deepeval/metrics/conversational_g_eval/__init__.py +3 -0
  15. deepeval/metrics/conversational_g_eval/conversational_g_eval.py +11 -7
  16. deepeval/metrics/dag/schema.py +1 -1
  17. deepeval/metrics/dag/templates.py +2 -2
  18. deepeval/metrics/goal_accuracy/__init__.py +1 -0
  19. deepeval/metrics/goal_accuracy/goal_accuracy.py +349 -0
  20. deepeval/metrics/goal_accuracy/schema.py +17 -0
  21. deepeval/metrics/goal_accuracy/template.py +235 -0
  22. deepeval/metrics/hallucination/hallucination.py +8 -8
  23. deepeval/metrics/mcp/mcp_task_completion.py +7 -2
  24. deepeval/metrics/mcp/multi_turn_mcp_use_metric.py +16 -6
  25. deepeval/metrics/mcp_use_metric/mcp_use_metric.py +2 -1
  26. deepeval/metrics/multimodal_metrics/multimodal_contextual_precision/multimodal_contextual_precision.py +32 -24
  27. deepeval/metrics/plan_adherence/__init__.py +1 -0
  28. deepeval/metrics/plan_adherence/plan_adherence.py +292 -0
  29. deepeval/metrics/plan_adherence/schema.py +11 -0
  30. deepeval/metrics/plan_adherence/template.py +170 -0
  31. deepeval/metrics/plan_quality/__init__.py +1 -0
  32. deepeval/metrics/plan_quality/plan_quality.py +292 -0
  33. deepeval/metrics/plan_quality/schema.py +11 -0
  34. deepeval/metrics/plan_quality/template.py +101 -0
  35. deepeval/metrics/step_efficiency/__init__.py +1 -0
  36. deepeval/metrics/step_efficiency/schema.py +11 -0
  37. deepeval/metrics/step_efficiency/step_efficiency.py +234 -0
  38. deepeval/metrics/step_efficiency/template.py +256 -0
  39. deepeval/metrics/task_completion/task_completion.py +1 -0
  40. deepeval/metrics/tool_correctness/schema.py +6 -0
  41. deepeval/metrics/tool_correctness/template.py +88 -0
  42. deepeval/metrics/tool_correctness/tool_correctness.py +226 -22
  43. deepeval/metrics/tool_use/__init__.py +1 -0
  44. deepeval/metrics/tool_use/schema.py +19 -0
  45. deepeval/metrics/tool_use/template.py +220 -0
  46. deepeval/metrics/tool_use/tool_use.py +458 -0
  47. deepeval/metrics/topic_adherence/__init__.py +1 -0
  48. deepeval/metrics/topic_adherence/schema.py +16 -0
  49. deepeval/metrics/topic_adherence/template.py +162 -0
  50. deepeval/metrics/topic_adherence/topic_adherence.py +355 -0
  51. deepeval/models/embedding_models/azure_embedding_model.py +37 -36
  52. deepeval/models/embedding_models/local_embedding_model.py +30 -32
  53. deepeval/models/embedding_models/ollama_embedding_model.py +18 -20
  54. deepeval/models/embedding_models/openai_embedding_model.py +22 -31
  55. deepeval/openai/extractors.py +61 -16
  56. deepeval/openai/patch.py +8 -12
  57. deepeval/openai/types.py +1 -1
  58. deepeval/openai/utils.py +108 -1
  59. deepeval/prompt/prompt.py +1 -0
  60. deepeval/prompt/utils.py +43 -14
  61. deepeval/synthesizer/synthesizer.py +11 -10
  62. deepeval/test_case/llm_test_case.py +6 -2
  63. deepeval/test_run/test_run.py +190 -207
  64. deepeval/tracing/__init__.py +2 -1
  65. deepeval/tracing/otel/exporter.py +3 -4
  66. deepeval/tracing/otel/utils.py +23 -4
  67. deepeval/tracing/trace_context.py +53 -38
  68. deepeval/tracing/tracing.py +23 -0
  69. deepeval/tracing/types.py +16 -14
  70. deepeval/utils.py +21 -0
  71. {deepeval-3.6.7.dist-info → deepeval-3.6.8.dist-info}/METADATA +1 -1
  72. {deepeval-3.6.7.dist-info → deepeval-3.6.8.dist-info}/RECORD +75 -53
  73. deepeval/integrations/llama_index/agent/patched.py +0 -68
  74. deepeval/tracing/message_types/__init__.py +0 -10
  75. deepeval/tracing/message_types/base.py +0 -6
  76. deepeval/tracing/message_types/messages.py +0 -14
  77. deepeval/tracing/message_types/tools.py +0 -18
  78. {deepeval-3.6.7.dist-info → deepeval-3.6.8.dist-info}/LICENSE.md +0 -0
  79. {deepeval-3.6.7.dist-info → deepeval-3.6.8.dist-info}/WHEEL +0 -0
  80. {deepeval-3.6.7.dist-info → deepeval-3.6.8.dist-info}/entry_points.txt +0 -0
deepeval/_version.py CHANGED
@@ -1 +1 @@
1
- __version__: str = "3.6.7"
1
+ __version__: str = "3.6.8"
deepeval/errors.py CHANGED
@@ -1,6 +1,24 @@
1
- class MissingTestCaseParamsError(Exception):
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
+
2
18
  pass
3
19
 
4
20
 
5
- class MismatchedTestCaseInputsError(Exception):
21
+ class MismatchedTestCaseInputsError(DeepEvalError):
22
+ """Inputs provided to a metric or test case are inconsistent or invalid."""
23
+
6
24
  pass