deepeval 4.3.3__tar.gz → 4.3.4__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.
Files changed (1039) hide show
  1. {deepeval-4.3.3 → deepeval-4.3.4}/PKG-INFO +4 -4
  2. {deepeval-4.3.3 → deepeval-4.3.4}/README.md +1 -1
  3. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/__init__.py +6 -10
  4. deepeval-4.3.4/deepeval/_version.py +1 -0
  5. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/anthropic/__init__.py +2 -2
  6. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/config/settings.py +10 -0
  7. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/constants.py +0 -1
  8. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/errors.py +1 -2
  9. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/evaluate/execute/_common.py +9 -44
  10. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/evaluate/execute/agentic.py +3 -2
  11. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/evaluate/execute/loop.py +8 -2
  12. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/evaluate/execute/trace_scope.py +5 -2
  13. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/evaluate/utils.py +2 -3
  14. deepeval-4.3.4/deepeval/integrations/README.md +49 -0
  15. deepeval-4.3.4/deepeval/integrations/agentcore/__init__.py +3 -0
  16. deepeval-4.3.4/deepeval/integrations/agentcore/otel.py +42 -0
  17. deepeval-4.3.4/deepeval/integrations/crewai/handler.py +167 -0
  18. deepeval-4.3.4/deepeval/integrations/crewai/subs.py +135 -0
  19. deepeval-4.3.4/deepeval/integrations/crewai/tool.py +43 -0
  20. deepeval-4.3.4/deepeval/integrations/google_adk/otel.py +41 -0
  21. deepeval-4.3.4/deepeval/integrations/langchain/callback.py +165 -0
  22. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/integrations/langchain/patch.py +5 -6
  23. deepeval-4.3.4/deepeval/integrations/llama_index/handler.py +28 -0
  24. deepeval-4.3.4/deepeval/integrations/openinference/otel.py +50 -0
  25. deepeval-4.3.4/deepeval/integrations/pydantic_ai/instrumentator.py +147 -0
  26. deepeval-4.3.4/deepeval/integrations/pydantic_ai/otel.py +23 -0
  27. deepeval-4.3.4/deepeval/integrations/strands/__init__.py +3 -0
  28. deepeval-4.3.4/deepeval/integrations/strands/otel.py +41 -0
  29. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/argument_correctness/argument_correctness.py +10 -2
  30. deepeval-4.3.4/deepeval/metrics/argument_correctness/utils.py +128 -0
  31. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/conversational_dag/nodes.py +15 -13
  32. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/dag/nodes.py +15 -12
  33. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/base_model.py +1 -0
  34. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/stt/_audio.py +2 -1
  35. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/tts/cartesia/cartesia.py +2 -1
  36. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/tts/deepgram/deepgram.py +2 -1
  37. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/tts/elevenlabs/elevenlabs.py +2 -1
  38. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/tts/openai/openai.py +2 -1
  39. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/openai/__init__.py +2 -2
  40. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/openai_agents/__init__.py +0 -2
  41. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/openai_agents/agent.py +3 -1
  42. deepeval-4.3.4/deepeval/openai_agents/callback_handler.py +94 -0
  43. deepeval-4.3.4/deepeval/openai_agents/patch.py +212 -0
  44. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/plugins/plugin.py +8 -2
  45. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/simulator/conversation_simulator.py +176 -40
  46. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/test_case/api.py +1 -0
  47. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/test_case/llm_test_case.py +2 -0
  48. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/test_run/api.py +1 -0
  49. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/test_run/cache.py +36 -1
  50. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/tracing/api.py +0 -17
  51. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/tracing/context.py +185 -48
  52. deepeval-4.3.4/deepeval/tracing/internal.py +82 -0
  53. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/tracing/offline_evals/span.py +2 -11
  54. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/tracing/offline_evals/thread.py +2 -11
  55. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/tracing/offline_evals/trace.py +2 -11
  56. deepeval-4.3.4/deepeval/tracing/otel/__init__.py +2 -0
  57. deepeval-4.3.4/deepeval/tracing/otel/adapters/__init__.py +39 -0
  58. deepeval-4.3.4/deepeval/tracing/otel/adapters/base.py +42 -0
  59. deepeval-4.3.4/deepeval/tracing/otel/adapters/google_adk.py +196 -0
  60. deepeval-4.3.4/deepeval/tracing/otel/adapters/llamaindex.py +27 -0
  61. deepeval-4.3.4/deepeval/tracing/otel/adapters/openinference.py +221 -0
  62. deepeval-4.3.4/deepeval/tracing/otel/adapters/pydantic_ai.py +57 -0
  63. deepeval-4.3.4/deepeval/tracing/otel/adapters/strands.py +110 -0
  64. deepeval-4.3.4/deepeval/tracing/otel/attribute_values.py +159 -0
  65. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/tracing/otel/attributes.py +31 -14
  66. deepeval-4.3.4/deepeval/tracing/otel/bridge.py +681 -0
  67. deepeval-4.3.4/deepeval/tracing/otel/converter.py +538 -0
  68. deepeval-4.3.4/deepeval/tracing/otel/messages.py +276 -0
  69. deepeval-4.3.4/deepeval/tracing/otel/setup.py +631 -0
  70. deepeval-4.3.4/deepeval/tracing/otel/utils.py +159 -0
  71. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/tracing/trace_context.py +21 -5
  72. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/tracing/tracing.py +308 -607
  73. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/tracing/types.py +1 -36
  74. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/tracing/utils.py +15 -0
  75. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/audio_utils.py +8 -0
  76. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/providers/livekit/connector.py +153 -14
  77. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/duplex.py +17 -5
  78. {deepeval-4.3.3 → deepeval-4.3.4}/pyproject.toml +3 -2
  79. deepeval-4.3.3/deepeval/_version.py +0 -1
  80. deepeval-4.3.3/deepeval/anthropic/extractors.py +0 -94
  81. deepeval-4.3.3/deepeval/anthropic/patch.py +0 -169
  82. deepeval-4.3.3/deepeval/anthropic/utils.py +0 -225
  83. deepeval-4.3.3/deepeval/integrations/README.md +0 -68
  84. deepeval-4.3.3/deepeval/integrations/agentcore/__init__.py +0 -4
  85. deepeval-4.3.3/deepeval/integrations/agentcore/instrumentator.py +0 -917
  86. deepeval-4.3.3/deepeval/integrations/agentcore/otel.py +0 -168
  87. deepeval-4.3.3/deepeval/integrations/crewai/handler.py +0 -493
  88. deepeval-4.3.3/deepeval/integrations/crewai/subs.py +0 -64
  89. deepeval-4.3.3/deepeval/integrations/crewai/tool.py +0 -91
  90. deepeval-4.3.3/deepeval/integrations/crewai/wrapper.py +0 -196
  91. deepeval-4.3.3/deepeval/integrations/google_adk/otel.py +0 -98
  92. deepeval-4.3.3/deepeval/integrations/langchain/callback.py +0 -942
  93. deepeval-4.3.3/deepeval/integrations/langchain/utils.py +0 -499
  94. deepeval-4.3.3/deepeval/integrations/llama_index/handler.py +0 -414
  95. deepeval-4.3.3/deepeval/integrations/llama_index/utils.py +0 -107
  96. deepeval-4.3.3/deepeval/integrations/openinference/instrumentator.py +0 -865
  97. deepeval-4.3.3/deepeval/integrations/openinference/otel.py +0 -173
  98. deepeval-4.3.3/deepeval/integrations/pydantic_ai/README.md +0 -1049
  99. deepeval-4.3.3/deepeval/integrations/pydantic_ai/instrumentator.py +0 -741
  100. deepeval-4.3.3/deepeval/integrations/pydantic_ai/otel.py +0 -80
  101. deepeval-4.3.3/deepeval/integrations/strands/__init__.py +0 -4
  102. deepeval-4.3.3/deepeval/integrations/strands/instrumentator.py +0 -937
  103. deepeval-4.3.3/deepeval/integrations/strands/otel.py +0 -178
  104. deepeval-4.3.3/deepeval/model_integrations/types.py +0 -20
  105. deepeval-4.3.3/deepeval/model_integrations/utils.py +0 -120
  106. deepeval-4.3.3/deepeval/openai/extractors.py +0 -198
  107. deepeval-4.3.3/deepeval/openai/patch.py +0 -309
  108. deepeval-4.3.3/deepeval/openai/utils.py +0 -211
  109. deepeval-4.3.3/deepeval/openai_agents/callback_handler.py +0 -173
  110. deepeval-4.3.3/deepeval/openai_agents/extractors.py +0 -455
  111. deepeval-4.3.3/deepeval/openai_agents/patch.py +0 -402
  112. deepeval-4.3.3/deepeval/openai_agents/runner.py +0 -348
  113. deepeval-4.3.3/deepeval/synthesizer/chunking/__init__.py +0 -0
  114. deepeval-4.3.3/deepeval/tracing/internal.py +0 -36
  115. deepeval-4.3.3/deepeval/tracing/otel/__init__.py +0 -7
  116. deepeval-4.3.3/deepeval/tracing/otel/context_aware_processor.py +0 -204
  117. deepeval-4.3.3/deepeval/tracing/otel/exporter.py +0 -899
  118. deepeval-4.3.3/deepeval/tracing/otel/test_exporter.py +0 -35
  119. deepeval-4.3.3/deepeval/tracing/otel/utils.py +0 -846
  120. {deepeval-4.3.3 → deepeval-4.3.4}/LICENSE.md +0 -0
  121. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/annotation/__init__.py +0 -0
  122. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/annotation/annotation.py +0 -0
  123. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/annotation/api.py +0 -0
  124. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/__init__.py +0 -0
  125. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/arc/__init__.py +0 -0
  126. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/arc/arc.py +0 -0
  127. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/arc/mode.py +0 -0
  128. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/arc/template.py +0 -0
  129. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/base_benchmark.py +0 -0
  130. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/bbq/__init__.py +0 -0
  131. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/bbq/bbq.py +0 -0
  132. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/bbq/task.py +0 -0
  133. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/bbq/template.py +0 -0
  134. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/__init__.py +0 -0
  135. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/big_bench_hard.py +0 -0
  136. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/cot_prompts/__init__.py +0 -0
  137. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/cot_prompts/boolean_expressions.txt +0 -0
  138. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/cot_prompts/causal_judgement.txt +0 -0
  139. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/cot_prompts/date_understanding.txt +0 -0
  140. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/cot_prompts/disambiguation_qa.txt +0 -0
  141. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/cot_prompts/dyck_languages.txt +0 -0
  142. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/cot_prompts/formal_fallacies.txt +0 -0
  143. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/cot_prompts/geometric_shapes.txt +0 -0
  144. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/cot_prompts/hyperbaton.txt +0 -0
  145. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/cot_prompts/logical_deduction_five_objects.txt +0 -0
  146. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/cot_prompts/logical_deduction_seven_objects.txt +0 -0
  147. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/cot_prompts/logical_deduction_three_objects.txt +0 -0
  148. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/cot_prompts/movie_recommendation.txt +0 -0
  149. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/cot_prompts/multistep_arithmetic_two.txt +0 -0
  150. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/cot_prompts/navigate.txt +0 -0
  151. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/cot_prompts/object_counting.txt +0 -0
  152. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/cot_prompts/penguins_in_a_table.txt +0 -0
  153. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/cot_prompts/reasoning_about_colored_objects.txt +0 -0
  154. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/cot_prompts/ruin_names.txt +0 -0
  155. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/cot_prompts/salient_translation_error_detection.txt +0 -0
  156. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/cot_prompts/snarks.txt +0 -0
  157. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/cot_prompts/sports_understanding.txt +0 -0
  158. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/cot_prompts/temporal_sequences.txt +0 -0
  159. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/cot_prompts/tracking_shuffled_objects_five_objects.txt +0 -0
  160. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/cot_prompts/tracking_shuffled_objects_seven_objects.txt +0 -0
  161. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/cot_prompts/tracking_shuffled_objects_three_objects.txt +0 -0
  162. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/cot_prompts/web_of_lies.txt +0 -0
  163. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/cot_prompts/word_sorting.txt +0 -0
  164. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/shot_prompts/__init__.py +0 -0
  165. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/shot_prompts/boolean_expressions.txt +0 -0
  166. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/shot_prompts/causal_judgement.txt +0 -0
  167. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/shot_prompts/date_understanding.txt +0 -0
  168. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/shot_prompts/disambiguation_qa.txt +0 -0
  169. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/shot_prompts/dyck_languages.txt +0 -0
  170. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/shot_prompts/formal_fallacies.txt +0 -0
  171. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/shot_prompts/geometric_shapes.txt +0 -0
  172. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/shot_prompts/hyperbaton.txt +0 -0
  173. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/shot_prompts/logical_deduction_five_objects.txt +0 -0
  174. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/shot_prompts/logical_deduction_seven_objects.txt +0 -0
  175. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/shot_prompts/logical_deduction_three_objects.txt +0 -0
  176. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/shot_prompts/movie_recommendation.txt +0 -0
  177. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/shot_prompts/multistep_arithmetic_two.txt +0 -0
  178. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/shot_prompts/navigate.txt +0 -0
  179. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/shot_prompts/object_counting.txt +0 -0
  180. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/shot_prompts/penguins_in_a_table.txt +0 -0
  181. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/shot_prompts/reasoning_about_colored_objects.txt +0 -0
  182. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/shot_prompts/ruin_names.txt +0 -0
  183. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/shot_prompts/salient_translation_error_detection.txt +0 -0
  184. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/shot_prompts/snarks.txt +0 -0
  185. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/shot_prompts/sports_understanding.txt +0 -0
  186. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/shot_prompts/temporal_sequences.txt +0 -0
  187. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/shot_prompts/tracking_shuffled_objects_five_objects.txt +0 -0
  188. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/shot_prompts/tracking_shuffled_objects_seven_objects.txt +0 -0
  189. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/shot_prompts/tracking_shuffled_objects_three_objects.txt +0 -0
  190. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/shot_prompts/web_of_lies.txt +0 -0
  191. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/shot_prompts/word_sorting.txt +0 -0
  192. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/task.py +0 -0
  193. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/big_bench_hard/template.py +0 -0
  194. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/bool_q/__init__.py +0 -0
  195. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/bool_q/bool_q.py +0 -0
  196. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/bool_q/template.py +0 -0
  197. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/drop/__init__.py +0 -0
  198. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/drop/drop.py +0 -0
  199. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/drop/task.py +0 -0
  200. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/drop/template.py +0 -0
  201. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/equity_med_qa/__init__.py +0 -0
  202. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/equity_med_qa/equity_med_qa.py +0 -0
  203. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/equity_med_qa/task.py +0 -0
  204. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/equity_med_qa/template.py +0 -0
  205. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/gsm8k/__init__.py +0 -0
  206. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/gsm8k/gsm8k.py +0 -0
  207. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/gsm8k/template.py +0 -0
  208. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/hellaswag/__init__.py +0 -0
  209. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/hellaswag/hellaswag.py +0 -0
  210. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/hellaswag/task.py +0 -0
  211. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/hellaswag/template.py +0 -0
  212. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/human_eval/__init__.py +0 -0
  213. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/human_eval/human_eval.py +0 -0
  214. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/human_eval/task.py +0 -0
  215. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/human_eval/template.py +0 -0
  216. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/ifeval/__init__.py +0 -0
  217. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/ifeval/ifeval.py +0 -0
  218. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/ifeval/template.py +0 -0
  219. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/lambada/__init__.py +0 -0
  220. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/lambada/lambada.py +0 -0
  221. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/lambada/template.py +0 -0
  222. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/logi_qa/__init__.py +0 -0
  223. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/logi_qa/logi_qa.py +0 -0
  224. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/logi_qa/task.py +0 -0
  225. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/logi_qa/template.py +0 -0
  226. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/math_qa/__init__.py +0 -0
  227. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/math_qa/math_qa.py +0 -0
  228. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/math_qa/task.py +0 -0
  229. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/math_qa/template.py +0 -0
  230. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/mmlu/__init__.py +0 -0
  231. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/mmlu/mmlu.py +0 -0
  232. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/mmlu/task.py +0 -0
  233. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/mmlu/template.py +0 -0
  234. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/modes/__init__.py +0 -0
  235. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/results.py +0 -0
  236. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/schema.py +0 -0
  237. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/squad/__init__.py +0 -0
  238. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/squad/squad.py +0 -0
  239. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/squad/task.py +0 -0
  240. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/squad/template.py +0 -0
  241. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/tasks/__init__.py +0 -0
  242. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/truthful_qa/__init__.py +0 -0
  243. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/truthful_qa/mode.py +0 -0
  244. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/truthful_qa/task.py +0 -0
  245. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/truthful_qa/template.py +0 -0
  246. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/truthful_qa/truthful_qa.py +0 -0
  247. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/utils.py +0 -0
  248. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/winogrande/__init__.py +0 -0
  249. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/winogrande/template.py +0 -0
  250. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/benchmarks/winogrande/winogrande.py +0 -0
  251. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/classifiers/__init__.py +0 -0
  252. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/classifiers/abstention.py +0 -0
  253. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/classifiers/base_classifier.py +0 -0
  254. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/classifiers/clarification.py +0 -0
  255. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/classifiers/classifier/__init__.py +0 -0
  256. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/classifiers/classifier/classifier.py +0 -0
  257. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/classifiers/classifier/schema.py +0 -0
  258. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/classifiers/classifier/templates/_experimental_system_one_classify.txt +0 -0
  259. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/classifiers/classifier/templates/class.txt +0 -0
  260. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/classifiers/classifier/templates/classify_multi_turn.txt +0 -0
  261. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/classifiers/classifier/templates/classify_single_turn.txt +0 -0
  262. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/classifiers/data_leakage.py +0 -0
  263. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/classifiers/escalation.py +0 -0
  264. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/classifiers/forbidden_commitments.py +0 -0
  265. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/classifiers/instruction_completeness.py +0 -0
  266. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/classifiers/prompt_injection.py +0 -0
  267. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/classifiers/refusal.py +0 -0
  268. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/classifiers/required_disclosure.py +0 -0
  269. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/classifiers/resolution.py +0 -0
  270. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/classifiers/response_language.py +0 -0
  271. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/classifiers/scope_adherence.py +0 -0
  272. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/classifiers/tone_adherence.py +0 -0
  273. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/classifiers/utils.py +0 -0
  274. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/__init__.py +0 -0
  275. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/app.py +0 -0
  276. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/auth/__init__.py +0 -0
  277. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/auth/api.py +0 -0
  278. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/auth/command.py +0 -0
  279. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/auth/flow.py +0 -0
  280. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/diagnose/__init__.py +0 -0
  281. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/diagnose/diagnose.py +0 -0
  282. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/dotenv_handler.py +0 -0
  283. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/generate/__init__.py +0 -0
  284. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/generate/command.py +0 -0
  285. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/generate/utils.py +0 -0
  286. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/inspect.py +0 -0
  287. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/main.py +0 -0
  288. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/providers/__init__.py +0 -0
  289. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/providers/_speech.py +0 -0
  290. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/providers/llms/__init__.py +0 -0
  291. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/providers/llms/anthropic.py +0 -0
  292. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/providers/llms/azure.py +0 -0
  293. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/providers/llms/bedrock.py +0 -0
  294. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/providers/llms/deepseek.py +0 -0
  295. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/providers/llms/gemini.py +0 -0
  296. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/providers/llms/grok.py +0 -0
  297. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/providers/llms/litellm.py +0 -0
  298. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/providers/llms/local_embeddings.py +0 -0
  299. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/providers/llms/local_model.py +0 -0
  300. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/providers/llms/moonshot.py +0 -0
  301. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/providers/llms/ollama.py +0 -0
  302. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/providers/llms/openai.py +0 -0
  303. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/providers/llms/openrouter.py +0 -0
  304. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/providers/llms/portkey.py +0 -0
  305. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/providers/stt/__init__.py +0 -0
  306. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/providers/stt/command.py +0 -0
  307. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/providers/system_one/__init__.py +0 -0
  308. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/providers/system_one/typesafe.py +0 -0
  309. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/providers/tts/__init__.py +0 -0
  310. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/providers/tts/command.py +0 -0
  311. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/setup/__init__.py +0 -0
  312. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/setup/command.py +0 -0
  313. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/setup/launcher.py +0 -0
  314. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/test/__init__.py +0 -0
  315. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/test/command.py +0 -0
  316. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/types.py +0 -0
  317. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/cli/utils.py +0 -0
  318. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/confident/__init__.py +0 -0
  319. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/confident/api.py +0 -0
  320. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/confident/types.py +0 -0
  321. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/config/__init__.py +0 -0
  322. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/config/dotenv_handler.py +0 -0
  323. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/config/eval_mode.py +0 -0
  324. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/config/logging.py +0 -0
  325. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/config/mode.py +0 -0
  326. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/config/settings_manager.py +0 -0
  327. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/config/utils.py +0 -0
  328. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/contextvars.py +0 -0
  329. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/dataset/__init__.py +0 -0
  330. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/dataset/api.py +0 -0
  331. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/dataset/dataset.py +0 -0
  332. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/dataset/expectations.py +0 -0
  333. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/dataset/golden.py +0 -0
  334. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/dataset/types.py +0 -0
  335. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/dataset/utils.py +0 -0
  336. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/evaluate/__init__.py +0 -0
  337. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/evaluate/api.py +0 -0
  338. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/evaluate/compare.py +0 -0
  339. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/evaluate/configs.py +0 -0
  340. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/evaluate/console_report.py +0 -0
  341. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/evaluate/evaluate.py +0 -0
  342. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/evaluate/execute/__init__.py +0 -0
  343. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/evaluate/execute/e2e.py +0 -0
  344. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/evaluate/expectations.py +0 -0
  345. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/evaluate/inspect_prompt.py +0 -0
  346. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/evaluate/local_store.py +0 -0
  347. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/evaluate/types.py +0 -0
  348. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/inspect/__init__.py +0 -0
  349. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/inspect/__main__.py +0 -0
  350. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/inspect/app.py +0 -0
  351. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/inspect/fixtures/test_run_sample.json +0 -0
  352. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/inspect/loader.py +0 -0
  353. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/inspect/styles.tcss +0 -0
  354. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/inspect/types.py +0 -0
  355. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/inspect/widgets/__init__.py +0 -0
  356. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/inspect/widgets/_styling.py +0 -0
  357. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/inspect/widgets/details.py +0 -0
  358. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/inspect/widgets/header_bar.py +0 -0
  359. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/inspect/widgets/help_modal.py +0 -0
  360. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/inspect/widgets/search_bar.py +0 -0
  361. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/inspect/widgets/span_tree.py +0 -0
  362. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/integrations/__init__.py +0 -0
  363. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/integrations/crewai/__init__.py +0 -0
  364. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/integrations/google_adk/__init__.py +0 -0
  365. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/integrations/hugging_face/__init__.py +0 -0
  366. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/integrations/hugging_face/callback.py +0 -0
  367. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/integrations/hugging_face/rich_manager.py +0 -0
  368. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/integrations/hugging_face/tests/test_callbacks.py +0 -0
  369. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/integrations/hugging_face/utils.py +0 -0
  370. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/integrations/langchain/__init__.py +0 -0
  371. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/integrations/llama_index/__init__.py +0 -0
  372. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/integrations/openinference/__init__.py +0 -0
  373. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/integrations/pydantic_ai/__init__.py +0 -0
  374. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/key_handler.py +0 -0
  375. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/README.md +0 -0
  376. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/__init__.py +0 -0
  377. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/agent_loop_detection/__init__.py +0 -0
  378. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/agent_loop_detection/agent_loop_detection.py +0 -0
  379. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/answer_relevancy/__init__.py +0 -0
  380. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/answer_relevancy/answer_relevancy.py +0 -0
  381. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/answer_relevancy/schema.py +0 -0
  382. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/answer_relevancy/templates/_experimental_system_one_questions.txt +0 -0
  383. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/answer_relevancy/templates/_experimental_system_one_verdict.txt +0 -0
  384. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/answer_relevancy/templates/class.txt +0 -0
  385. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/answer_relevancy/templates/generate_reason.txt +0 -0
  386. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/answer_relevancy/templates/generate_statements.txt +0 -0
  387. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/answer_relevancy/templates/generate_verdicts.txt +0 -0
  388. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/arena_g_eval/__init__.py +0 -0
  389. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/arena_g_eval/arena_g_eval.py +0 -0
  390. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/arena_g_eval/schema.py +0 -0
  391. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/arena_g_eval/templates/class.txt +0 -0
  392. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/arena_g_eval/templates/generate_arena_winner.txt +0 -0
  393. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/arena_g_eval/templates/generate_evaluation_steps.txt +0 -0
  394. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/arena_g_eval/templates/rewrite_reason.txt +0 -0
  395. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/arena_g_eval/utils.py +0 -0
  396. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/argument_correctness/__init__.py +0 -0
  397. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/argument_correctness/schema.py +0 -0
  398. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/argument_correctness/templates/_experimental_system_one_questions.txt +0 -0
  399. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/argument_correctness/templates/_experimental_system_one_verdict.txt +0 -0
  400. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/argument_correctness/templates/class.txt +0 -0
  401. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/argument_correctness/templates/generate_reason.txt +0 -0
  402. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/argument_correctness/templates/generate_verdicts.txt +0 -0
  403. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/audio_glitch/__init__.py +0 -0
  404. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/audio_glitch/_detectors.py +0 -0
  405. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/audio_glitch/audio_glitch.py +0 -0
  406. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/audio_glitch/schema.py +0 -0
  407. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/audio_glitch/templates/class.txt +0 -0
  408. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/audio_glitch/templates/generate_reason.txt +0 -0
  409. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/base_metric.py +0 -0
  410. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/bias/__init__.py +0 -0
  411. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/bias/bias.py +0 -0
  412. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/bias/schema.py +0 -0
  413. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/bias/templates/_experimental_system_one_questions.txt +0 -0
  414. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/bias/templates/_experimental_system_one_verdict.txt +0 -0
  415. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/bias/templates/class.txt +0 -0
  416. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/bias/templates/generate_opinions.txt +0 -0
  417. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/bias/templates/generate_reason.txt +0 -0
  418. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/bias/templates/generate_verdicts.txt +0 -0
  419. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/community/__init__.py +0 -0
  420. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/community/citation_faithfulness/__init__.py +0 -0
  421. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/community/citation_faithfulness/citation_faithfulness.py +0 -0
  422. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/community/citation_faithfulness/schema.py +0 -0
  423. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/community/citation_faithfulness/template.py +0 -0
  424. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/contextual_precision/__init__.py +0 -0
  425. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/contextual_precision/contextual_precision.py +0 -0
  426. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/contextual_precision/schema.py +0 -0
  427. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/contextual_precision/templates/_experimental_system_one_questions.txt +0 -0
  428. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/contextual_precision/templates/_experimental_system_one_verdict.txt +0 -0
  429. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/contextual_precision/templates/class.txt +0 -0
  430. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/contextual_precision/templates/generate_reason.txt +0 -0
  431. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/contextual_precision/templates/generate_verdicts.txt +0 -0
  432. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/contextual_recall/__init__.py +0 -0
  433. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/contextual_recall/contextual_recall.py +0 -0
  434. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/contextual_recall/schema.py +0 -0
  435. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/contextual_recall/templates/_experimental_system_one_questions.txt +0 -0
  436. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/contextual_recall/templates/_experimental_system_one_verdict.txt +0 -0
  437. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/contextual_recall/templates/class.txt +0 -0
  438. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/contextual_recall/templates/generate_reason.txt +0 -0
  439. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/contextual_recall/templates/generate_verdicts.txt +0 -0
  440. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/contextual_relevancy/__init__.py +0 -0
  441. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/contextual_relevancy/contextual_relevancy.py +0 -0
  442. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/contextual_relevancy/schema.py +0 -0
  443. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/contextual_relevancy/templates/_experimental_system_one_questions.txt +0 -0
  444. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/contextual_relevancy/templates/_experimental_system_one_verdict.txt +0 -0
  445. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/contextual_relevancy/templates/class.txt +0 -0
  446. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/contextual_relevancy/templates/generate_reason.txt +0 -0
  447. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/contextual_relevancy/templates/generate_verdicts.txt +0 -0
  448. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/conversation_completeness/__init__.py +0 -0
  449. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/conversation_completeness/conversation_completeness.py +0 -0
  450. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/conversation_completeness/schema.py +0 -0
  451. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/conversation_completeness/templates/_experimental_system_one_questions.txt +0 -0
  452. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/conversation_completeness/templates/_experimental_system_one_verdict.txt +0 -0
  453. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/conversation_completeness/templates/class.txt +0 -0
  454. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/conversation_completeness/templates/extract_user_intentions.txt +0 -0
  455. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/conversation_completeness/templates/generate_reason.txt +0 -0
  456. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/conversation_completeness/templates/generate_verdicts.txt +0 -0
  457. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/conversational_dag/__init__.py +0 -0
  458. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/conversational_dag/conversational_dag.py +0 -0
  459. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/conversational_dag/templates/ConversationalBinaryJudgement/generate_binary_verdict.txt +0 -0
  460. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/conversational_dag/templates/ConversationalNonBinaryJudgement/generate_non_binary_verdict.txt +0 -0
  461. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/conversational_dag/templates/ConversationalTaskNode/generate_task_output.txt +0 -0
  462. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/conversational_dag/templates/ConversationalVerdictNode/generate_reason.txt +0 -0
  463. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/conversational_g_eval/__init__.py +0 -0
  464. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/conversational_g_eval/conversational_g_eval.py +0 -0
  465. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/conversational_g_eval/schema.py +0 -0
  466. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/conversational_g_eval/templates/class.txt +0 -0
  467. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/conversational_g_eval/templates/generate_evaluation_results.txt +0 -0
  468. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/conversational_g_eval/templates/generate_evaluation_steps.txt +0 -0
  469. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/conversational_jev_eval/__init__.py +0 -0
  470. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/conversational_jev_eval/conversational_jev_eval.py +0 -0
  471. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/dag/__init__.py +0 -0
  472. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/dag/dag.py +0 -0
  473. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/dag/graph.py +0 -0
  474. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/dag/runner.py +0 -0
  475. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/dag/schema.py +0 -0
  476. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/dag/serialization/__init__.py +0 -0
  477. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/dag/serialization/registry.py +0 -0
  478. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/dag/serialization/serialization.py +0 -0
  479. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/dag/serialization/types.py +0 -0
  480. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/dag/templates/BinaryJudgement/generate_binary_verdict.txt +0 -0
  481. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/dag/templates/NonBinaryJudgement/generate_non_binary_verdict.txt +0 -0
  482. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/dag/templates/TaskNode/generate_task_output.txt +0 -0
  483. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/dag/templates/VerdictNode/generate_reason.txt +0 -0
  484. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/dag/utils.py +0 -0
  485. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/exact_match/__init__.py +0 -0
  486. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/exact_match/exact_match.py +0 -0
  487. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/faithfulness/__init__.py +0 -0
  488. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/faithfulness/faithfulness.py +0 -0
  489. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/faithfulness/schema.py +0 -0
  490. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/faithfulness/templates/_experimental_system_one_questions.txt +0 -0
  491. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/faithfulness/templates/_experimental_system_one_verdict.txt +0 -0
  492. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/faithfulness/templates/class.txt +0 -0
  493. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/faithfulness/templates/generate_claims.txt +0 -0
  494. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/faithfulness/templates/generate_reason.txt +0 -0
  495. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/faithfulness/templates/generate_truths.txt +0 -0
  496. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/faithfulness/templates/generate_verdicts.txt +0 -0
  497. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/g_eval/__init__.py +0 -0
  498. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/g_eval/g_eval.py +0 -0
  499. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/g_eval/schema.py +0 -0
  500. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/g_eval/templates/class.txt +0 -0
  501. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/g_eval/templates/generate_evaluation_results.txt +0 -0
  502. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/g_eval/templates/generate_evaluation_steps.txt +0 -0
  503. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/g_eval/templates/generate_strict_evaluation_results.txt +0 -0
  504. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/g_eval/templates/generate_strict_trace_evaluation_results.txt +0 -0
  505. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/g_eval/templates/generate_trace_evaluation_results.txt +0 -0
  506. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/g_eval/templates/generate_trace_evaluation_steps.txt +0 -0
  507. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/g_eval/utils.py +0 -0
  508. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/goal_accuracy/__init__.py +0 -0
  509. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/goal_accuracy/goal_accuracy.py +0 -0
  510. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/goal_accuracy/schema.py +0 -0
  511. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/goal_accuracy/templates/_experimental_system_one_goal_score.txt +0 -0
  512. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/goal_accuracy/templates/_experimental_system_one_plan_score.txt +0 -0
  513. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/goal_accuracy/templates/_experimental_system_one_questions.txt +0 -0
  514. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/goal_accuracy/templates/class.txt +0 -0
  515. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/goal_accuracy/templates/get_accuracy_score.txt +0 -0
  516. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/goal_accuracy/templates/get_final_reason.txt +0 -0
  517. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/goal_accuracy/templates/get_plan_evaluation_score.txt +0 -0
  518. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/hallucination/__init__.py +0 -0
  519. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/hallucination/hallucination.py +0 -0
  520. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/hallucination/schema.py +0 -0
  521. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/hallucination/templates/_experimental_system_one_questions.txt +0 -0
  522. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/hallucination/templates/_experimental_system_one_verdict.txt +0 -0
  523. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/hallucination/templates/class.txt +0 -0
  524. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/hallucination/templates/generate_reason.txt +0 -0
  525. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/hallucination/templates/generate_verdicts.txt +0 -0
  526. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/indicator.py +0 -0
  527. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/jev_eval/__init__.py +0 -0
  528. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/jev_eval/jev_eval.py +0 -0
  529. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/jev_eval/questions.py +0 -0
  530. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/jev_eval/utils.py +0 -0
  531. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/json_correctness/__init__.py +0 -0
  532. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/json_correctness/json_correctness.py +0 -0
  533. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/json_correctness/schema.py +0 -0
  534. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/json_correctness/templates/class.txt +0 -0
  535. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/json_correctness/templates/generate_reason.txt +0 -0
  536. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/knowledge_retention/__init__.py +0 -0
  537. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/knowledge_retention/knowledge_retention.py +0 -0
  538. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/knowledge_retention/schema.py +0 -0
  539. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/knowledge_retention/templates/_experimental_system_one_questions.txt +0 -0
  540. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/knowledge_retention/templates/_experimental_system_one_verdict.txt +0 -0
  541. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/knowledge_retention/templates/class.txt +0 -0
  542. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/knowledge_retention/templates/extract_data.txt +0 -0
  543. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/knowledge_retention/templates/generate_reason.txt +0 -0
  544. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/knowledge_retention/templates/generate_verdict.txt +0 -0
  545. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/mcp/__init__.py +0 -0
  546. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/mcp/mcp_task_completion.py +0 -0
  547. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/mcp/multi_turn_mcp_use_metric.py +0 -0
  548. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/mcp/schema.py +0 -0
  549. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/mcp/templates/_experimental_system_one_mcp_use_args_score.txt +0 -0
  550. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/mcp/templates/_experimental_system_one_mcp_use_primitive_score.txt +0 -0
  551. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/mcp/templates/_experimental_system_one_mcp_use_questions.txt +0 -0
  552. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/mcp/templates/_experimental_system_one_questions.txt +0 -0
  553. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/mcp/templates/_experimental_system_one_score.txt +0 -0
  554. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/mcp/templates/class.txt +0 -0
  555. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/mcp/templates/generate_final_reason.txt +0 -0
  556. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/mcp/templates/get_args_correctness_score.txt +0 -0
  557. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/mcp/templates/get_task_completion_score.txt +0 -0
  558. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/mcp/templates/get_tool_correctness_score.txt +0 -0
  559. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/mcp/utils.py +0 -0
  560. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/mcp_use_metric/__init__.py +0 -0
  561. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/mcp_use_metric/mcp_use_metric.py +0 -0
  562. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/mcp_use_metric/schema.py +0 -0
  563. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/mcp_use_metric/templates/_experimental_system_one_args_score.txt +0 -0
  564. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/mcp_use_metric/templates/_experimental_system_one_primitive_score.txt +0 -0
  565. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/mcp_use_metric/templates/_experimental_system_one_questions.txt +0 -0
  566. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/mcp_use_metric/templates/class.txt +0 -0
  567. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/mcp_use_metric/templates/get_mcp_argument_correctness_prompt.txt +0 -0
  568. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/mcp_use_metric/templates/get_primitive_correctness_prompt.txt +0 -0
  569. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/misuse/__init__.py +0 -0
  570. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/misuse/misuse.py +0 -0
  571. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/misuse/schema.py +0 -0
  572. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/misuse/templates/_experimental_system_one_questions.txt +0 -0
  573. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/misuse/templates/_experimental_system_one_verdict.txt +0 -0
  574. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/misuse/templates/class.txt +0 -0
  575. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/misuse/templates/generate_misuses.txt +0 -0
  576. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/misuse/templates/generate_reason.txt +0 -0
  577. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/misuse/templates/generate_verdicts.txt +0 -0
  578. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/multimodal_metrics/__init__.py +0 -0
  579. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/multimodal_metrics/image_coherence/__init__.py +0 -0
  580. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/multimodal_metrics/image_coherence/image_coherence.py +0 -0
  581. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/multimodal_metrics/image_coherence/schema.py +0 -0
  582. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/multimodal_metrics/image_coherence/templates/class.txt +0 -0
  583. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/multimodal_metrics/image_coherence/templates/evaluate_image_coherence.txt +0 -0
  584. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/multimodal_metrics/image_editing/__init__.py +0 -0
  585. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/multimodal_metrics/image_editing/image_editing.py +0 -0
  586. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/multimodal_metrics/image_editing/schema.py +0 -0
  587. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/multimodal_metrics/image_editing/templates/class.txt +0 -0
  588. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/multimodal_metrics/image_editing/templates/generate_perceptual_quality_evaluation_results.txt +0 -0
  589. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/multimodal_metrics/image_editing/templates/generate_semantic_consistency_evaluation_results.txt +0 -0
  590. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/multimodal_metrics/image_helpfulness/__init__.py +0 -0
  591. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/multimodal_metrics/image_helpfulness/image_helpfulness.py +0 -0
  592. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/multimodal_metrics/image_helpfulness/schema.py +0 -0
  593. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/multimodal_metrics/image_helpfulness/templates/class.txt +0 -0
  594. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/multimodal_metrics/image_helpfulness/templates/evaluate_image_helpfulness.txt +0 -0
  595. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/multimodal_metrics/image_reference/__init__.py +0 -0
  596. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/multimodal_metrics/image_reference/image_reference.py +0 -0
  597. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/multimodal_metrics/image_reference/schema.py +0 -0
  598. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/multimodal_metrics/image_reference/templates/class.txt +0 -0
  599. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/multimodal_metrics/image_reference/templates/evaluate_image_reference.txt +0 -0
  600. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/multimodal_metrics/text_to_image/__init__.py +0 -0
  601. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/multimodal_metrics/text_to_image/schema.py +0 -0
  602. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/multimodal_metrics/text_to_image/templates/class.txt +0 -0
  603. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/multimodal_metrics/text_to_image/templates/generate_perceptual_quality_evaluation_results.txt +0 -0
  604. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/multimodal_metrics/text_to_image/templates/generate_semantic_consistency_evaluation_results.txt +0 -0
  605. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/multimodal_metrics/text_to_image/text_to_image.py +0 -0
  606. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/non_advice/__init__.py +0 -0
  607. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/non_advice/non_advice.py +0 -0
  608. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/non_advice/schema.py +0 -0
  609. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/non_advice/templates/_experimental_system_one_questions.txt +0 -0
  610. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/non_advice/templates/_experimental_system_one_verdict.txt +0 -0
  611. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/non_advice/templates/class.txt +0 -0
  612. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/non_advice/templates/generate_advices.txt +0 -0
  613. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/non_advice/templates/generate_reason.txt +0 -0
  614. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/non_advice/templates/generate_verdicts.txt +0 -0
  615. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/pattern_match/__init__.py +0 -0
  616. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/pattern_match/pattern_match.py +0 -0
  617. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/pii_leakage/__init__.py +0 -0
  618. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/pii_leakage/pii_leakage.py +0 -0
  619. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/pii_leakage/schema.py +0 -0
  620. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/pii_leakage/templates/_experimental_system_one_questions.txt +0 -0
  621. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/pii_leakage/templates/_experimental_system_one_verdict.txt +0 -0
  622. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/pii_leakage/templates/class.txt +0 -0
  623. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/pii_leakage/templates/extract_pii.txt +0 -0
  624. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/pii_leakage/templates/generate_reason.txt +0 -0
  625. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/pii_leakage/templates/generate_verdicts.txt +0 -0
  626. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/plan_adherence/__init__.py +0 -0
  627. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/plan_adherence/plan_adherence.py +0 -0
  628. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/plan_adherence/schema.py +0 -0
  629. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/plan_adherence/templates/_experimental_system_one_questions.txt +0 -0
  630. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/plan_adherence/templates/_experimental_system_one_score.txt +0 -0
  631. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/plan_adherence/templates/class.txt +0 -0
  632. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/plan_adherence/templates/evaluate_adherence.txt +0 -0
  633. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/plan_adherence/templates/extract_plan_from_trace.txt +0 -0
  634. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/plan_quality/__init__.py +0 -0
  635. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/plan_quality/plan_quality.py +0 -0
  636. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/plan_quality/schema.py +0 -0
  637. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/plan_quality/templates/_experimental_system_one_questions.txt +0 -0
  638. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/plan_quality/templates/_experimental_system_one_score.txt +0 -0
  639. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/plan_quality/templates/class.txt +0 -0
  640. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/plan_quality/templates/evaluate_plan_quality.txt +0 -0
  641. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/prompt_alignment/__init__.py +0 -0
  642. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/prompt_alignment/prompt_alignment.py +0 -0
  643. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/prompt_alignment/schema.py +0 -0
  644. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/prompt_alignment/templates/_experimental_system_one_questions.txt +0 -0
  645. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/prompt_alignment/templates/_experimental_system_one_verdict.txt +0 -0
  646. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/prompt_alignment/templates/class.txt +0 -0
  647. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/prompt_alignment/templates/generate_reason.txt +0 -0
  648. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/prompt_alignment/templates/generate_verdicts.txt +0 -0
  649. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/ragas.py +0 -0
  650. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/retrieval_context_display.py +0 -0
  651. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/role_adherence/__init__.py +0 -0
  652. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/role_adherence/role_adherence.py +0 -0
  653. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/role_adherence/schema.py +0 -0
  654. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/role_adherence/templates/_experimental_system_one_questions.txt +0 -0
  655. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/role_adherence/templates/_experimental_system_one_verdict.txt +0 -0
  656. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/role_adherence/templates/class.txt +0 -0
  657. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/role_adherence/templates/extract_out_of_character_response_verdicts.txt +0 -0
  658. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/role_adherence/templates/generate_reason.txt +0 -0
  659. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/role_violation/__init__.py +0 -0
  660. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/role_violation/role_violation.py +0 -0
  661. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/role_violation/schema.py +0 -0
  662. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/role_violation/templates/_experimental_system_one_questions.txt +0 -0
  663. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/role_violation/templates/_experimental_system_one_verdict.txt +0 -0
  664. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/role_violation/templates/class.txt +0 -0
  665. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/role_violation/templates/detect_role_violations.txt +0 -0
  666. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/role_violation/templates/generate_reason.txt +0 -0
  667. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/role_violation/templates/generate_verdicts.txt +0 -0
  668. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/step_efficiency/__init__.py +0 -0
  669. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/step_efficiency/schema.py +0 -0
  670. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/step_efficiency/step_efficiency.py +0 -0
  671. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/step_efficiency/templates/_experimental_system_one_questions.txt +0 -0
  672. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/step_efficiency/templates/_experimental_system_one_score.txt +0 -0
  673. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/step_efficiency/templates/class.txt +0 -0
  674. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/step_efficiency/templates/extract_task_from_trace.txt +0 -0
  675. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/step_efficiency/templates/get_execution_efficiency.txt +0 -0
  676. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/summarization/__init__.py +0 -0
  677. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/summarization/schema.py +0 -0
  678. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/summarization/summarization.py +0 -0
  679. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/summarization/templates/_experimental_system_one_questions.txt +0 -0
  680. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/summarization/templates/_experimental_system_one_verdict.txt +0 -0
  681. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/summarization/templates/class.txt +0 -0
  682. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/summarization/templates/generate_alignment_verdicts.txt +0 -0
  683. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/summarization/templates/generate_answers.txt +0 -0
  684. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/summarization/templates/generate_questions.txt +0 -0
  685. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/summarization/templates/generate_reason.txt +0 -0
  686. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/task_completion/__init__.py +0 -0
  687. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/task_completion/schema.py +0 -0
  688. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/task_completion/task_completion.py +0 -0
  689. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/task_completion/templates/_experimental_system_one_questions.txt +0 -0
  690. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/task_completion/templates/_experimental_system_one_score.txt +0 -0
  691. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/task_completion/templates/class.txt +0 -0
  692. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/task_completion/templates/extract_goal_and_outcome.txt +0 -0
  693. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/task_completion/templates/extract_task_and_outcome_from_trace.txt +0 -0
  694. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/task_completion/templates/generate_verdict.txt +0 -0
  695. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/tool_correctness/__init__.py +0 -0
  696. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/tool_correctness/schema.py +0 -0
  697. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/tool_correctness/templates/_experimental_system_one_tool_selection_score.txt +0 -0
  698. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/tool_correctness/templates/class.txt +0 -0
  699. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/tool_correctness/templates/get_tool_selection_score.txt +0 -0
  700. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/tool_correctness/tool_correctness.py +0 -0
  701. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/tool_permission/__init__.py +0 -0
  702. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/tool_permission/tool_permission.py +0 -0
  703. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/tool_use/__init__.py +0 -0
  704. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/tool_use/schema.py +0 -0
  705. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/tool_use/templates/_experimental_system_one_argument_correctness_score.txt +0 -0
  706. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/tool_use/templates/_experimental_system_one_questions.txt +0 -0
  707. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/tool_use/templates/_experimental_system_one_tool_selection_score.txt +0 -0
  708. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/tool_use/templates/class.txt +0 -0
  709. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/tool_use/templates/get_argument_correctness_score.txt +0 -0
  710. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/tool_use/templates/get_tool_argument_final_reason.txt +0 -0
  711. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/tool_use/templates/get_tool_selection_final_reason.txt +0 -0
  712. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/tool_use/templates/get_tool_selection_score.txt +0 -0
  713. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/tool_use/tool_use.py +0 -0
  714. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/topic_adherence/__init__.py +0 -0
  715. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/topic_adherence/schema.py +0 -0
  716. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/topic_adherence/templates/_experimental_system_one_answered_verdict.txt +0 -0
  717. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/topic_adherence/templates/_experimental_system_one_on_topic_verdict.txt +0 -0
  718. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/topic_adherence/templates/_experimental_system_one_questions.txt +0 -0
  719. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/topic_adherence/templates/class.txt +0 -0
  720. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/topic_adherence/templates/generate_reason.txt +0 -0
  721. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/topic_adherence/templates/get_qa_pair_verdict.txt +0 -0
  722. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/topic_adherence/templates/get_qa_pairs.txt +0 -0
  723. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/topic_adherence/topic_adherence.py +0 -0
  724. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/toxicity/__init__.py +0 -0
  725. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/toxicity/schema.py +0 -0
  726. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/toxicity/templates/_experimental_system_one_questions.txt +0 -0
  727. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/toxicity/templates/_experimental_system_one_verdict.txt +0 -0
  728. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/toxicity/templates/class.txt +0 -0
  729. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/toxicity/templates/generate_opinions.txt +0 -0
  730. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/toxicity/templates/generate_reason.txt +0 -0
  731. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/toxicity/templates/generate_verdicts.txt +0 -0
  732. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/toxicity/toxicity.py +0 -0
  733. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/transcription_accuracy/__init__.py +0 -0
  734. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/transcription_accuracy/schema.py +0 -0
  735. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/transcription_accuracy/templates/_experimental_system_one_audio_questions.txt +0 -0
  736. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/transcription_accuracy/templates/_experimental_system_one_audio_verdict.txt +0 -0
  737. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/transcription_accuracy/templates/_experimental_system_one_questions.txt +0 -0
  738. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/transcription_accuracy/templates/_experimental_system_one_verdict.txt +0 -0
  739. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/transcription_accuracy/templates/class.txt +0 -0
  740. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/transcription_accuracy/templates/generate_audio_reason.txt +0 -0
  741. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/transcription_accuracy/templates/generate_audio_verdicts.txt +0 -0
  742. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/transcription_accuracy/templates/generate_reason.txt +0 -0
  743. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/transcription_accuracy/templates/generate_verdicts.txt +0 -0
  744. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/transcription_accuracy/transcription_accuracy.py +0 -0
  745. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_contextual_precision/__init__.py +0 -0
  746. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_contextual_precision/schema.py +0 -0
  747. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_contextual_precision/templates/_experimental_system_one_questions.txt +0 -0
  748. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_contextual_precision/templates/_experimental_system_one_verdict.txt +0 -0
  749. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_contextual_precision/templates/class.txt +0 -0
  750. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_contextual_precision/templates/generate_final_reason.txt +0 -0
  751. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_contextual_precision/templates/generate_reason.txt +0 -0
  752. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_contextual_precision/templates/generate_verdicts.txt +0 -0
  753. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_contextual_precision/turn_contextual_precision.py +0 -0
  754. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_contextual_recall/__init__.py +0 -0
  755. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_contextual_recall/schema.py +0 -0
  756. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_contextual_recall/templates/_experimental_system_one_questions.txt +0 -0
  757. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_contextual_recall/templates/_experimental_system_one_verdict.txt +0 -0
  758. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_contextual_recall/templates/class.txt +0 -0
  759. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_contextual_recall/templates/generate_final_reason.txt +0 -0
  760. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_contextual_recall/templates/generate_reason.txt +0 -0
  761. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_contextual_recall/templates/generate_verdicts.txt +0 -0
  762. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_contextual_recall/turn_contextual_recall.py +0 -0
  763. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_contextual_relevancy/__init__.py +0 -0
  764. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_contextual_relevancy/schema.py +0 -0
  765. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_contextual_relevancy/templates/_experimental_system_one_questions.txt +0 -0
  766. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_contextual_relevancy/templates/_experimental_system_one_verdict.txt +0 -0
  767. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_contextual_relevancy/templates/class.txt +0 -0
  768. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_contextual_relevancy/templates/generate_final_reason.txt +0 -0
  769. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_contextual_relevancy/templates/generate_reason.txt +0 -0
  770. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_contextual_relevancy/templates/generate_verdicts.txt +0 -0
  771. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_contextual_relevancy/turn_contextual_relevancy.py +0 -0
  772. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_faithfulness/__init__.py +0 -0
  773. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_faithfulness/schema.py +0 -0
  774. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_faithfulness/templates/_experimental_system_one_questions.txt +0 -0
  775. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_faithfulness/templates/_experimental_system_one_verdict.txt +0 -0
  776. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_faithfulness/templates/class.txt +0 -0
  777. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_faithfulness/templates/generate_claims.txt +0 -0
  778. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_faithfulness/templates/generate_final_reason.txt +0 -0
  779. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_faithfulness/templates/generate_reason.txt +0 -0
  780. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_faithfulness/templates/generate_truths.txt +0 -0
  781. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_faithfulness/templates/generate_verdicts.txt +0 -0
  782. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_faithfulness/turn_faithfulness.py +0 -0
  783. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_relevancy/__init__.py +0 -0
  784. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_relevancy/schema.py +0 -0
  785. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_relevancy/templates/_experimental_system_one_questions.txt +0 -0
  786. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_relevancy/templates/_experimental_system_one_verdict.txt +0 -0
  787. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_relevancy/templates/class.txt +0 -0
  788. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_relevancy/templates/generate_reason.txt +0 -0
  789. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_relevancy/templates/generate_verdicts.txt +0 -0
  790. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/turn_relevancy/turn_relevancy.py +0 -0
  791. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/utils/__init__.py +0 -0
  792. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/utils/decision.py +0 -0
  793. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/utils/generation.py +0 -0
  794. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/utils/metrics.py +0 -0
  795. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/utils/models.py +0 -0
  796. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/utils/qag.py +0 -0
  797. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/utils/system_one.py +0 -0
  798. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/utils/system_one_batch.py +0 -0
  799. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/utils/test_case.py +0 -0
  800. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/utils/turns.py +0 -0
  801. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/utils/verbose.py +0 -0
  802. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/voice/__init__.py +0 -0
  803. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/voice/_analysis.py +0 -0
  804. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/voice/_detectors.py +0 -0
  805. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/voice/base_metric.py +0 -0
  806. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/voice/consistency.py +0 -0
  807. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/voice/integrity.py +0 -0
  808. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/voice/intelligibility.py +0 -0
  809. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/voice/naturalness.py +0 -0
  810. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/voice/reliability.py +0 -0
  811. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/voice/responsiveness.py +0 -0
  812. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/metrics/voice/turn_taking.py +0 -0
  813. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/__init__.py +0 -0
  814. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/_summac_model.py +0 -0
  815. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/answer_relevancy_model.py +0 -0
  816. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/detoxify_model.py +0 -0
  817. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/embedding_models/__init__.py +0 -0
  818. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/embedding_models/azure_embedding_model.py +0 -0
  819. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/embedding_models/local_embedding_model.py +0 -0
  820. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/embedding_models/ollama_embedding_model.py +0 -0
  821. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/embedding_models/openai_embedding_model.py +0 -0
  822. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/hallucination_model.py +0 -0
  823. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/llms/__init__.py +0 -0
  824. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/llms/amazon_bedrock_model.py +0 -0
  825. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/llms/anthropic_model.py +0 -0
  826. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/llms/azure_model.py +0 -0
  827. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/llms/constants.py +0 -0
  828. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/llms/deepseek_model.py +0 -0
  829. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/llms/gateway_model.py +0 -0
  830. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/llms/gemini_model.py +0 -0
  831. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/llms/grok_model.py +0 -0
  832. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/llms/kimi_model.py +0 -0
  833. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/llms/litellm_model.py +0 -0
  834. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/llms/local_model.py +0 -0
  835. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/llms/multimodal.py +0 -0
  836. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/llms/ollama_model.py +0 -0
  837. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/llms/openai_model.py +0 -0
  838. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/llms/openrouter_model.py +0 -0
  839. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/llms/portkey_model.py +0 -0
  840. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/llms/utils.py +0 -0
  841. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/retry_policy.py +0 -0
  842. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/speech.py +0 -0
  843. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/speech_selection.py +0 -0
  844. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/stt/__init__.py +0 -0
  845. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/stt/_stream.py +0 -0
  846. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/stt/assemblyai/__init__.py +0 -0
  847. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/stt/assemblyai/assemblyai.py +0 -0
  848. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/stt/assemblyai/schema.py +0 -0
  849. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/stt/cartesia/__init__.py +0 -0
  850. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/stt/cartesia/cartesia.py +0 -0
  851. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/stt/cartesia/schema.py +0 -0
  852. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/stt/deepgram/__init__.py +0 -0
  853. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/stt/deepgram/deepgram.py +0 -0
  854. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/stt/deepgram/schema.py +0 -0
  855. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/stt/elevenlabs/__init__.py +0 -0
  856. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/stt/elevenlabs/elevenlabs.py +0 -0
  857. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/stt/elevenlabs/schema.py +0 -0
  858. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/stt/openai/__init__.py +0 -0
  859. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/stt/openai/openai.py +0 -0
  860. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/summac_model.py +0 -0
  861. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/system_one/__init__.py +0 -0
  862. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/system_one/constants.py +0 -0
  863. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/system_one/limits.py +0 -0
  864. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/system_one/schema.py +0 -0
  865. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/system_one/typesafe_model.py +0 -0
  866. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/tts/__init__.py +0 -0
  867. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/tts/_frames.py +0 -0
  868. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/tts/cartesia/__init__.py +0 -0
  869. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/tts/cartesia/schema.py +0 -0
  870. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/tts/deepgram/__init__.py +0 -0
  871. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/tts/deepgram/schema.py +0 -0
  872. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/tts/elevenlabs/__init__.py +0 -0
  873. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/tts/elevenlabs/schema.py +0 -0
  874. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/tts/openai/__init__.py +0 -0
  875. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/unbias_model.py +0 -0
  876. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/models/utils.py +0 -0
  877. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/__init__.py +0 -0
  878. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/algorithms/__init__.py +0 -0
  879. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/algorithms/base.py +0 -0
  880. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/algorithms/configs.py +0 -0
  881. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/algorithms/copro/__init__.py +0 -0
  882. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/algorithms/copro/copro.py +0 -0
  883. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/algorithms/copro/proposer.py +0 -0
  884. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/algorithms/copro/schema.py +0 -0
  885. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/algorithms/copro/template.py +0 -0
  886. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/algorithms/gepa/__init__.py +0 -0
  887. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/algorithms/gepa/gepa.py +0 -0
  888. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/algorithms/miprov2/__init__.py +0 -0
  889. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/algorithms/miprov2/bootstrapper.py +0 -0
  890. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/algorithms/miprov2/miprov2.py +0 -0
  891. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/algorithms/miprov2/proposer/__init__.py +0 -0
  892. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/algorithms/miprov2/proposer/proposer.py +0 -0
  893. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/algorithms/miprov2/proposer/schema.py +0 -0
  894. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/algorithms/miprov2/proposer/template.py +0 -0
  895. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/algorithms/simba/__init__.py +0 -0
  896. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/algorithms/simba/proposer.py +0 -0
  897. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/algorithms/simba/schema.py +0 -0
  898. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/algorithms/simba/simba.py +0 -0
  899. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/algorithms/simba/template.py +0 -0
  900. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/configs.py +0 -0
  901. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/policies.py +0 -0
  902. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/prompt_optimizer.py +0 -0
  903. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/rewriter/__init__.py +0 -0
  904. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/rewriter/rewriter.py +0 -0
  905. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/rewriter/schema.py +0 -0
  906. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/rewriter/template.py +0 -0
  907. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/scorer/__init__.py +0 -0
  908. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/scorer/base.py +0 -0
  909. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/scorer/schema.py +0 -0
  910. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/scorer/scorer.py +0 -0
  911. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/scorer/template.py +0 -0
  912. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/scorer/utils.py +0 -0
  913. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/types.py +0 -0
  914. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/optimizer/utils.py +0 -0
  915. {deepeval-4.3.3/deepeval/model_integrations → deepeval-4.3.4/deepeval/plugins}/__init__.py +0 -0
  916. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/progress_context.py +0 -0
  917. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/prompt/__init__.py +0 -0
  918. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/prompt/api.py +0 -0
  919. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/prompt/prompt.py +0 -0
  920. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/prompt/utils.py +0 -0
  921. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/py.typed +0 -0
  922. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/red_teaming/README.md +0 -0
  923. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/scorer/__init__.py +0 -0
  924. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/scorer/scorer.py +0 -0
  925. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/simulator/__init__.py +0 -0
  926. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/simulator/controller/__init__.py +0 -0
  927. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/simulator/controller/controller.py +0 -0
  928. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/simulator/controller/template.py +0 -0
  929. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/simulator/controller/types.py +0 -0
  930. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/simulator/interrupt_template.py +0 -0
  931. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/simulator/schema.py +0 -0
  932. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/simulator/simulation_graph/__init__.py +0 -0
  933. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/simulator/simulation_graph/default.py +0 -0
  934. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/simulator/simulation_graph/node.py +0 -0
  935. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/simulator/simulation_graph/runner.py +0 -0
  936. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/simulator/simulation_graph/template.py +0 -0
  937. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/simulator/template.py +0 -0
  938. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/simulator/templates/class.txt +0 -0
  939. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/simulator/templates/decide_interrupt.txt +0 -0
  940. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/simulator/templates/interruption_bias_frequent.txt +0 -0
  941. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/simulator/templates/interruption_bias_normal.txt +0 -0
  942. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/simulator/templates/interruption_bias_rare.txt +0 -0
  943. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/simulator/templates/interruption_frustration.txt +0 -0
  944. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/simulator/utils.py +0 -0
  945. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/singleton.py +0 -0
  946. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/sqlite_store/__init__.py +0 -0
  947. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/sqlite_store/store.py +0 -0
  948. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/synthesizer/__init__.py +0 -0
  949. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/synthesizer/base_synthesizer.py +0 -0
  950. {deepeval-4.3.3/deepeval/plugins → deepeval-4.3.4/deepeval/synthesizer/chunking}/__init__.py +0 -0
  951. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/synthesizer/chunking/context_generator.py +0 -0
  952. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/synthesizer/chunking/doc_chunker.py +0 -0
  953. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/synthesizer/config.py +0 -0
  954. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/synthesizer/schema.py +0 -0
  955. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/synthesizer/synthesizer.py +0 -0
  956. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/synthesizer/templates/__init__.py +0 -0
  957. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/synthesizer/templates/template.py +0 -0
  958. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/synthesizer/templates/template_extraction.py +0 -0
  959. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/synthesizer/templates/template_prompt.py +0 -0
  960. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/synthesizer/types.py +0 -0
  961. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/synthesizer/utils.py +0 -0
  962. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/telemetry/__init__.py +0 -0
  963. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/telemetry/api.py +0 -0
  964. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/telemetry/client.py +0 -0
  965. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/telemetry/context.py +0 -0
  966. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/telemetry/events.py +0 -0
  967. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/telemetry/identity.py +0 -0
  968. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/telemetry/judge.py +0 -0
  969. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/telemetry/properties.py +0 -0
  970. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/telemetry/runtime.py +0 -0
  971. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/templates/__init__.py +0 -0
  972. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/templates/classifiers/templates.json +0 -0
  973. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/templates/metrics/fragments/faithfulness_verdicts_example_multimodal.txt +0 -0
  974. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/templates/metrics/fragments/faithfulness_verdicts_format_instruction.txt +0 -0
  975. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/templates/metrics/fragments/faithfulness_verdicts_guidelines_multimodal.txt +0 -0
  976. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/templates/metrics/fragments/faithfulness_verdicts_guidelines_text_only.txt +0 -0
  977. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/templates/metrics/fragments/multimodal_image_generation_eval_context.txt +0 -0
  978. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/templates/metrics/fragments/multimodal_input_rules.txt +0 -0
  979. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/templates/metrics/fragments/multimodal_input_rules_turn_metric.txt +0 -0
  980. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/templates/metrics/templates.json +0 -0
  981. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/templates/resolver.py +0 -0
  982. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/templates/simulator/templates.json +0 -0
  983. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/templates/template_class.py +0 -0
  984. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/test_case/__init__.py +0 -0
  985. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/test_case/arena_test_case.py +0 -0
  986. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/test_case/conversational_test_case.py +0 -0
  987. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/test_case/mcp.py +0 -0
  988. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/test_case/utils.py +0 -0
  989. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/test_run/__init__.py +0 -0
  990. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/test_run/hooks.py +0 -0
  991. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/test_run/hyperparameters.py +0 -0
  992. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/test_run/test_run.py +0 -0
  993. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/tracing/__init__.py +0 -0
  994. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/tracing/integrations.py +0 -0
  995. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/tracing/offline_evals/__init__.py +0 -0
  996. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/tracing/offline_evals/api.py +0 -0
  997. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/tracing/patchers.py +0 -0
  998. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/tracing/perf_epoch_bridge.py +0 -0
  999. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/tracing/trace_test_manager.py +0 -0
  1000. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/utils.py +0 -0
  1001. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/__init__.py +0 -0
  1002. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/background.py +0 -0
  1003. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/config.py +0 -0
  1004. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/__init__.py +0 -0
  1005. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/phone.py +0 -0
  1006. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/providers/__init__.py +0 -0
  1007. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/providers/elevenlabs/README.md +0 -0
  1008. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/providers/elevenlabs/__init__.py +0 -0
  1009. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/providers/elevenlabs/connector.py +0 -0
  1010. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/providers/livekit/README.md +0 -0
  1011. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/providers/livekit/__init__.py +0 -0
  1012. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/providers/livekit/sip.py +0 -0
  1013. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/providers/pipecat/README.md +0 -0
  1014. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/providers/pipecat/__init__.py +0 -0
  1015. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/providers/pipecat/connector.py +0 -0
  1016. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/providers/pipecat/protobuf.py +0 -0
  1017. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/providers/twilio/README.md +0 -0
  1018. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/providers/twilio/__init__.py +0 -0
  1019. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/providers/twilio/connector.py +0 -0
  1020. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/providers/vapi/README.md +0 -0
  1021. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/providers/vapi/__init__.py +0 -0
  1022. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/providers/vapi/connector.py +0 -0
  1023. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/transports/__init__.py +0 -0
  1024. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/transports/base.py +0 -0
  1025. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/transports/callback.py +0 -0
  1026. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/transports/silence.py +0 -0
  1027. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/transports/webrtc.py +0 -0
  1028. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/transports/websocket.py +0 -0
  1029. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/turn_engine.py +0 -0
  1030. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/types.py +0 -0
  1031. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/connectors/utils.py +0 -0
  1032. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/floor_control.py +0 -0
  1033. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/interruption.py +0 -0
  1034. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/output.py +0 -0
  1035. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/protocol.py +0 -0
  1036. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/recording.py +0 -0
  1037. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/streaming.py +0 -0
  1038. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/timeline.py +0 -0
  1039. {deepeval-4.3.3 → deepeval-4.3.4}/deepeval/voice/turn_detection.py +0 -0
@@ -1,15 +1,14 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: deepeval
3
- Version: 4.3.3
3
+ Version: 4.3.4
4
4
  Summary: The LLM Evaluation Framework
5
5
  License: Apache-2.0
6
6
  License-File: LICENSE.md
7
7
  Author: Jeffrey Ip
8
8
  Author-email: jeffreyip@confident-ai.com
9
- Requires-Python: >=3.9,<4.0
9
+ Requires-Python: >=3.10,<4.0
10
10
  Classifier: License :: OSI Approved :: Apache Software License
11
11
  Classifier: Programming Language :: Python :: 3
12
- Classifier: Programming Language :: Python :: 3.9
13
12
  Classifier: Programming Language :: Python :: 3.10
14
13
  Classifier: Programming Language :: Python :: 3.11
15
14
  Classifier: Programming Language :: Python :: 3.12
@@ -18,6 +17,7 @@ Classifier: Programming Language :: Python :: 3.14
18
17
  Provides-Extra: inspect
19
18
  Requires-Dist: aiohttp
20
19
  Requires-Dist: click (>=8.0.0,<8.4.0)
20
+ Requires-Dist: confident-trace (>=0.1.14,<0.2.0)
21
21
  Requires-Dist: grpcio (>=1.67.1,<2.0.0)
22
22
  Requires-Dist: jinja2
23
23
  Requires-Dist: nest_asyncio
@@ -285,7 +285,7 @@ Let's pretend your LLM application is a customer support AI agent; here's how De
285
285
 
286
286
  ## Installation
287
287
 
288
- Deepeval works with **Python>=3.9+**.
288
+ Deepeval works with **Python>=3.10+**.
289
289
 
290
290
  ```
291
291
  pip install -U deepeval
@@ -232,7 +232,7 @@ Let's pretend your LLM application is a customer support AI agent; here's how De
232
232
 
233
233
  ## Installation
234
234
 
235
- Deepeval works with **Python>=3.9+**.
235
+ Deepeval works with **Python>=3.10+**.
236
236
 
237
237
  ```
238
238
  pip install -U deepeval
@@ -55,20 +55,16 @@ def _expose_public_api() -> None:
55
55
  telemetry = _telemetry
56
56
 
57
57
  def instrument(*args, **kwargs):
58
- """Set up Confident AI's OTel backend.
58
+ """Trace whatever OpenInference instrumentors run for deepeval.
59
59
 
60
- Configures a TracerProvider, attaches deepeval's OpenInference span
61
- interceptor, and routes spans through the context-aware processor
62
- (REST when a deepeval trace context is active or an evaluation is
63
- running, OTLP otherwise). Pair with any community OpenInference
64
- instrumentor (e.g. ``GoogleADKInstrumentor``, ``OpenAIInstrumentor``)
65
- to capture framework-specific telemetry.
60
+ Starts confident-trace, whose tracer provider any community
61
+ OpenInference instrumentor (e.g. ``OpenAIInstrumentor``) traces on.
62
+ deepeval evaluates the spans it collects, and confident-trace sends
63
+ the rest to Confident AI.
66
64
 
67
65
  Accepts the same trace-level kwargs as
68
66
  ``deepeval.integrations.openinference.instrument_openinference``:
69
- ``api_key``, ``name``, ``thread_id``, ``user_id``, ``metadata``,
70
- ``tags``, ``environment``, ``metric_collection``, ``test_case_id``,
71
- ``turn_id``. Span-level config goes on ``with next_*_span(...)``
67
+ ``name``, ``thread_id``, ``metadata``, ``tags``, ``environment``. Span-level config goes on ``with next_*_span(...)``
72
68
  / ``update_current_span(...)``.
73
69
  """
74
70
  from deepeval.integrations.openinference import (
@@ -0,0 +1 @@
1
+ __version__: str = "4.3.4"
@@ -12,9 +12,9 @@ except ImportError:
12
12
  AsyncAnthropic = None # type: ignore
13
13
 
14
14
  if Anthropic or AsyncAnthropic:
15
- from deepeval.anthropic.patch import patch_anthropic_classes
16
15
  from deepeval.telemetry import capture_tracing_integration
17
16
  from deepeval.tracing.integrations import Integration
17
+ from deepeval.tracing.otel.setup import ensure_confident_trace
18
18
 
19
19
  with capture_tracing_integration(Integration.ANTHROPIC):
20
- patch_anthropic_classes()
20
+ ensure_confident_trace(("anthropic",))
@@ -990,6 +990,14 @@ class Settings(BaseSettings):
990
990
  None,
991
991
  description="Enable detailed internal tracing of metric and model methods inside @observe spans.",
992
992
  )
993
+ DEEPEVAL_AUTO_TRACE: Optional[bool] = Field(
994
+ True,
995
+ description="Trace every installed library confident-trace supports while evals_iterator or deepeval test run runs. Set to false to trace only @observe code and the integrations you set up.",
996
+ )
997
+ DEEPEVAL_GLOBAL_TRACER_PROVIDER: Optional[bool] = Field(
998
+ False,
999
+ description="Install deepeval's tracer provider as the global OpenTelemetry provider when none is set, so other OpenTelemetry spans in your app are traced too. Off by default, which leaves the global provider to your own OpenTelemetry setup.",
1000
+ )
993
1001
 
994
1002
  CONFIDENT_OTEL_URL: Optional[AnyUrl] = Field(
995
1003
  "https://otel.confident-ai.com",
@@ -1181,7 +1189,9 @@ class Settings(BaseSettings):
1181
1189
  "DEEPEVAL_DISABLE_TIMEOUTS",
1182
1190
  "DEEPEVAL_VERBOSE_MODE",
1183
1191
  "DEEPEVAL_GRPC_LOGGING",
1192
+ "DEEPEVAL_AUTO_TRACE",
1184
1193
  "DEEPEVAL_DISABLE_DOTENV",
1194
+ "DEEPEVAL_GLOBAL_TRACER_PROVIDER",
1185
1195
  "DEEPEVAL_TELEMETRY_OPT_OUT",
1186
1196
  "DEEPEVAL_TELEMETRY_ENABLED",
1187
1197
  "DEEPEVAL_MODEL_THINKING",
@@ -12,7 +12,6 @@ LOGIN_PROMPT = "\n✨👀 Looking for a place for your LLM test data to live
12
12
 
13
13
 
14
14
  CONFIDENT_TRACE_VERBOSE = "CONFIDENT_TRACE_VERBOSE"
15
- CONFIDENT_TRACE_FLUSH = "CONFIDENT_TRACE_FLUSH"
16
15
  CONFIDENT_TRACE_SAMPLE_RATE = "CONFIDENT_TRACE_SAMPLE_RATE"
17
16
  CONFIDENT_TRACE_ENVIRONMENT = "CONFIDENT_TRACE_ENVIRONMENT"
18
17
  CONFIDENT_TRACING_ENABLED = "CONFIDENT_TRACING_ENABLED"
@@ -67,8 +67,7 @@ class NoMetricsError(DeepEvalError):
67
67
  Raised by the ``evals_iterator`` executor when, after iteration completes,
68
68
  we can prove that no metrics were declared via:
69
69
  - ``evals_iterator(metrics=[...])`` (top-level / trace-level metrics)
70
- - ``@observe(metrics=[...])`` or ``@observe(metric_collection=...)``
71
- on any span (span-level metrics)
70
+ - ``@observe(metrics=[...])`` on any span (span-level metrics)
72
71
  - ``update_current_trace(metrics=[...])`` inside the traced function
73
72
  (trace-level metrics, set at runtime)
74
73
 
@@ -15,7 +15,6 @@ from deepeval.tracing.tracing import (
15
15
  trace_manager,
16
16
  Trace,
17
17
  BaseSpan,
18
- LlmSpan,
19
18
  )
20
19
  from deepeval.errors import MissingTestCaseParamsError
21
20
  from deepeval.utils import (
@@ -35,19 +34,9 @@ from deepeval.test_case import (
35
34
  LLMTestCase,
36
35
  ConversationalTestCase,
37
36
  )
38
- from deepeval.test_run import (
39
- global_test_run_manager,
40
- TestRunManager,
41
- )
42
37
  from deepeval.evaluate.types import TestResult
43
38
  from deepeval.tracing.types import TraceSpanStatus
44
39
  from deepeval.config.settings import get_settings
45
- from deepeval.test_run import TEMP_FILE_PATH
46
- from deepeval.confident.api import is_confident
47
- from deepeval.test_run.hyperparameters import (
48
- process_hyperparameters,
49
- process_prompts,
50
- )
51
40
 
52
41
  logger = logging.getLogger(__name__)
53
42
 
@@ -116,6 +105,15 @@ def _skip_metrics_for_error(
116
105
  return False
117
106
 
118
107
 
108
+ def _attach_span_tree(
109
+ test_case: LLMTestCase, trace: Trace, span: Optional[BaseSpan]
110
+ ) -> None:
111
+ """Let metrics that look past their own span (e.g. ArgumentCorrectness)
112
+ reach the rest of the trace. `span` is None for a trace-level test case."""
113
+ test_case._trace_root_spans = trace.root_spans
114
+ test_case._trace_span = span
115
+
116
+
119
117
  def _trace_error(current_trace: Trace) -> Optional[str]:
120
118
  def _first_err(s: BaseSpan) -> Optional[str]:
121
119
  if s.status == TraceSpanStatus.ERRORED and s.error:
@@ -317,36 +315,3 @@ def _execute_classifier(
317
315
  classifier.label = None
318
316
  else:
319
317
  raise
320
-
321
-
322
- def log_prompt(
323
- llm_span: LlmSpan,
324
- test_run_manager: TestRunManager,
325
- ):
326
- prompt = llm_span.prompt
327
- if prompt is None:
328
- return
329
-
330
- span_hyperparameters = {}
331
- prompt_hash = prompt.hash if is_confident() else None
332
- key = f"{prompt.alias}_{prompt_hash}"
333
- span_hyperparameters[key] = prompt
334
-
335
- test_run = test_run_manager.get_test_run()
336
- if test_run.prompts is None:
337
- test_run.prompts = []
338
- if test_run.hyperparameters is None:
339
- test_run.hyperparameters = {}
340
-
341
- if key not in test_run.hyperparameters:
342
- test_run.hyperparameters.update(
343
- process_hyperparameters(span_hyperparameters, False)
344
- )
345
- existing_prompt_keys = {f"{p.alias}_{p.hash}" for p in test_run.prompts}
346
- new_prompts = process_prompts(span_hyperparameters)
347
- for new_prompt in new_prompts:
348
- new_prompt_key = f"{new_prompt.alias}_{new_prompt.hash}"
349
- if new_prompt_key not in existing_prompt_keys:
350
- test_run.prompts.append(new_prompt)
351
-
352
- global_test_run_manager.save_test_run(TEMP_FILE_PATH)
@@ -65,10 +65,10 @@ logger = logging.getLogger(__name__)
65
65
 
66
66
 
67
67
  from deepeval.evaluate.execute._common import (
68
+ _attach_span_tree,
68
69
  _skip_metrics_for_error,
69
70
  _trace_error,
70
71
  filter_duplicate_results,
71
- log_prompt,
72
72
  )
73
73
 
74
74
 
@@ -354,7 +354,6 @@ async def _a_execute_span_test_case(
354
354
  trace_api.agent_spans.append(api_span)
355
355
  elif isinstance(span, LlmSpan):
356
356
  trace_api.llm_spans.append(api_span)
357
- log_prompt(span, test_run_manager)
358
357
  elif isinstance(span, RetrieverSpan):
359
358
  trace_api.retriever_spans.append(api_span)
360
359
  elif isinstance(span, ToolSpan):
@@ -416,6 +415,7 @@ async def _a_execute_span_test_case(
416
415
  if test_case is None:
417
416
  test_case = LLMTestCase(input="None")
418
417
  test_case._trace_dict = trace_manager.create_nested_spans_dict(span)
418
+ _attach_span_tree(test_case, current_trace, span)
419
419
 
420
420
  for metric in metrics:
421
421
  metric.skipped = False
@@ -524,6 +524,7 @@ async def _a_execute_trace_test_case(
524
524
  test_case._trace_dict = trace_manager.create_nested_spans_dict(
525
525
  trace.root_spans[0]
526
526
  )
527
+ _attach_span_tree(test_case, trace, None)
527
528
 
528
529
  for metric in metrics:
529
530
  metric.skipped = False
@@ -35,6 +35,7 @@ from deepeval.tracing.tracing import (
35
35
  ToolSpan,
36
36
  )
37
37
  from deepeval.tracing.context import current_trace_context
38
+ from deepeval.tracing.otel.setup import start_automatic_tracing
38
39
  from deepeval.tracing.api import (
39
40
  BaseApiSpan,
40
41
  )
@@ -85,6 +86,7 @@ logger = logging.getLogger(__name__)
85
86
 
86
87
 
87
88
  from deepeval.evaluate.execute._common import (
89
+ _attach_span_tree,
88
90
  _await_with_outer_deadline,
89
91
  _execute_metric,
90
92
  _log_gather_timeout,
@@ -94,7 +96,6 @@ from deepeval.evaluate.execute._common import (
94
96
  _snapshot_tasks,
95
97
  _trace_error,
96
98
  filter_duplicate_results,
97
- log_prompt,
98
99
  )
99
100
  from deepeval.evaluate.execute.agentic import (
100
101
  _a_execute_agentic_test_case,
@@ -251,7 +252,6 @@ def execute_agentic_test_cases_from_loop(
251
252
  trace_api.agent_spans.append(api_span)
252
253
  elif isinstance(span, LlmSpan):
253
254
  trace_api.llm_spans.append(api_span)
254
- log_prompt(span, test_run_manager)
255
255
  elif isinstance(span, RetrieverSpan):
256
256
  trace_api.retriever_spans.append(api_span)
257
257
  elif isinstance(span, ToolSpan):
@@ -319,6 +319,7 @@ def execute_agentic_test_cases_from_loop(
319
319
  advance=count_metrics_in_span_subtree(span),
320
320
  )
321
321
  return
322
+ _attach_span_tree(llm_test_case, current_trace, span)
322
323
 
323
324
  # Preparing metric calculation
324
325
  api_span.metrics_data = []
@@ -411,6 +412,7 @@ def execute_agentic_test_cases_from_loop(
411
412
  current_trace.root_spans[0]
412
413
  )
413
414
  )
415
+ _attach_span_tree(llm_test_case, current_trace, None)
414
416
 
415
417
  if not skip_metrics_for_this_golden:
416
418
  for metric in current_trace.metrics:
@@ -476,6 +478,7 @@ def execute_agentic_test_cases_from_loop(
476
478
  ):
477
479
  _raise_no_metrics_error()
478
480
 
481
+ stop_automatic_tracing = start_automatic_tracing()
479
482
  try:
480
483
  if display_config.show_indicator and _use_bar_indicator:
481
484
  progress = Progress(
@@ -499,6 +502,7 @@ def execute_agentic_test_cases_from_loop(
499
502
  except Exception:
500
503
  raise
501
504
  finally:
505
+ stop_automatic_tracing()
502
506
  # Atomic exit cleanup: replacing the session resets mode + every
503
507
  # per-run collection in a single assignment, so state can't leak
504
508
  # into the next run.
@@ -913,6 +917,7 @@ def a_execute_agentic_test_cases_from_loop(
913
917
  )
914
918
  )
915
919
 
920
+ stop_automatic_tracing = start_automatic_tracing()
916
921
  try:
917
922
  if display_config.show_indicator and _use_bar_indicator:
918
923
  progress = Progress(
@@ -943,6 +948,7 @@ def a_execute_agentic_test_cases_from_loop(
943
948
  except Exception:
944
949
  raise
945
950
  finally:
951
+ stop_automatic_tracing()
946
952
  # Atomic exit cleanup: replacing the session resets mode + every
947
953
  # per-run collection in a single assignment.
948
954
  local_trace_manager.eval_session = EvalSession()
@@ -53,10 +53,10 @@ logger = logging.getLogger(__name__)
53
53
 
54
54
 
55
55
  from deepeval.evaluate.execute._common import (
56
+ _attach_span_tree,
56
57
  _execute_metric,
57
58
  _skip_metrics_for_error,
58
59
  _trace_error,
59
- log_prompt,
60
60
  )
61
61
 
62
62
 
@@ -132,6 +132,8 @@ def _assert_test_from_current_trace(
132
132
  is_promoted_root = True
133
133
  else:
134
134
  root_for_dfs = root
135
+ # A root still parked under the open wrapper points at it too.
136
+ is_promoted_root = root.parent_uuid is not None
135
137
 
136
138
  effective_trace_output = (
137
139
  current_trace.output
@@ -187,7 +189,6 @@ def _assert_test_from_current_trace(
187
189
  trace_api.agent_spans.append(api_span)
188
190
  elif isinstance(span, LlmSpan):
189
191
  trace_api.llm_spans.append(api_span)
190
- log_prompt(span, test_run_manager)
191
192
  elif isinstance(span, RetrieverSpan):
192
193
  trace_api.retriever_spans.append(api_span)
193
194
  elif isinstance(span, ToolSpan):
@@ -239,6 +240,7 @@ def _assert_test_from_current_trace(
239
240
  )
240
241
  )
241
242
  return
243
+ _attach_span_tree(llm_test_case, current_trace, span)
242
244
 
243
245
  api_span.metrics_data = []
244
246
  for metric in metrics:
@@ -301,6 +303,7 @@ def _assert_test_from_current_trace(
301
303
  llm_test_case_for_trace._trace_dict = (
302
304
  trace_manager.create_nested_spans_dict(root_for_dfs)
303
305
  )
306
+ _attach_span_tree(llm_test_case_for_trace, current_trace, None)
304
307
 
305
308
  trace_api.metrics_data = []
306
309
  for metric in current_trace.metrics:
@@ -292,8 +292,8 @@ def create_api_trace(trace: Trace, golden: Golden) -> TraceApi:
292
292
  # doing it twice (here + walker) would either double-emit or require
293
293
  # the walker to dedupe.
294
294
  #
295
- # Trace-level fields (``name``, ``tags``, ``thread_id``, ``user_id``,
296
- # ``metadata``, ``environment``) are forwarded from the trace so that
295
+ # Trace-level fields (``name``, ``tags``, ``thread_id``, ``metadata``,
296
+ # ``environment``) are forwarded from the trace so that
297
297
  # OTel-based integrations whose users configured them via instrumentation
298
298
  # settings or ``update_current_trace(...)`` see them on the dashboard.
299
299
  # The non-eval REST path (``trace_manager.create_trace_api``) already
@@ -345,7 +345,6 @@ def create_api_trace(trace: Trace, golden: Golden) -> TraceApi:
345
345
  name=trace.name,
346
346
  tags=trace.tags,
347
347
  threadId=trace.thread_id,
348
- userId=trace.user_id,
349
348
  environment=trace.environment,
350
349
  status=(
351
350
  TraceSpanApiStatus.SUCCESS
@@ -0,0 +1,49 @@
1
+ # `deepeval.integrations`
2
+
3
+ Contributor reference for the framework integrations.
4
+
5
+ > Note: `deepeval.openai`, `deepeval.anthropic`, and `deepeval.openai_agents` live at the top level of the `deepeval` package, not under this folder. They're listed here so the matrix is complete.
6
+
7
+ ## How an integration traces
8
+
9
+ Every integration runs on confident-trace. Its entry point calls `ensure_confident_trace(...)` (`deepeval/tracing/otel/setup.py`) with the confident-trace instrumentations it needs. Those instrumentations, or the framework's own OpenTelemetry telemetry that they switch on, produce the spans.
10
+
11
+ A framework's own telemetry goes to the global tracer provider, which deepeval otherwise leaves to the application. An entry point that relies on it passes `global_provider=True`: confident-trace's provider becomes the global one when none is set, or deepeval's processors join the application's. Only an integration the user sets up does this; automatic tracing never does.
12
+
13
+ `@observe` runs on confident-trace too: each observed function is a confident-trace span.
14
+
15
+ `DeepEvalSpanBridge` (`deepeval/tracing/otel/bridge.py`) collects the spans of every trace deepeval consumes: one inside `@observe` / `with trace(...)`, in `evals_iterator` or `evaluate`, or under a trace-shape test. It converts them into deepeval spans (`converter.py`), so metrics, `update_current_span(...)`, `update_current_trace(...)` and `next_*_span(...)` work the same as with `@observe`. confident-trace exports every trace to Confident AI, except one an evaluation or a trace-shape test consumes locally.
16
+
17
+ | Integration | Entry point | confident-trace instrumentations | Adapter |
18
+ | ------------- | ------------------------------------------------- | ------------------------------------------------------------ | --------------- |
19
+ | OpenAI | `from deepeval.openai import OpenAI` | `openai` | — |
20
+ | Anthropic | `from deepeval.anthropic import Anthropic` | `anthropic` | — |
21
+ | LangChain | `CallbackHandler()` | `langchain`, `langgraph` | — |
22
+ | LangGraph | `CallbackHandler()` | `langchain`, `langgraph` | — |
23
+ | LlamaIndex | `instrument_llama_index()` | `llamaindex` and the model providers | `llamaindex` |
24
+ | CrewAI | `instrument_crewai()` | `crewai` and the model providers | — |
25
+ | OpenAI Agents | `add_trace_processor(DeepEvalTracingProcessor())` | `openai_agents` (OpenInference), `openai` | `openinference` |
26
+ | Pydantic AI | `DeepEvalInstrumentationSettings(...)` | `pydantic_ai` (Pydantic AI's own telemetry) | `pydantic_ai` |
27
+ | Strands | `instrument_strands()` | `strands` (Strands' own telemetry) | `strands` |
28
+ | AgentCore | `instrument_agentcore()` | `agentcore`, `strands` | `strands` |
29
+ | Google ADK | `instrument_google_adk()` | `google_adk` (ADK's own telemetry) | `google_adk` |
30
+ | OpenInference | `instrument_openinference()` / `deepeval.instrument()` | none: pair it with any `openinference-instrumentation-*` | `openinference` |
31
+
32
+ ## What an integration adds
33
+
34
+ confident-trace records what a framework does. An integration adds only what deepeval knows and the framework doesn't:
35
+
36
+ - **Trace settings** such as `name`, `thread_id` and `tags`. An integration that sees a run start stages them with `stage_next_trace(...)` (the LangChain handler). One that only configures instrumentation stamps them on its instrumentation scope's spans with `set_trace_defaults(...)` (Strands, ADK, OpenInference), or on one agent's tracer (Pydantic AI).
37
+ - **Span settings** such as metrics. For a span the user can't reach from inside, stage them before it opens with `stage_next_span(...)` / `staged_next_span(...)`, which a user's `next_*_span(...)` overrides (CrewAI's `Crew` / `Agent` / `LLM`, OpenAI Agents' `Agent`). Inside a span's body, such as a tool's, call `update_current_span(...)`.
38
+ - **Span type**, for a span only the integration can classify: `stage_next_span_type(...)` (LangChain types the invoked run as the agent).
39
+
40
+ ## Writing an adapter
41
+
42
+ Most spans convert by the GenAI semantic conventions and `confident.*` attributes alone. When a framework records content elsewhere, add an `Adapter` (`deepeval/tracing/otel/adapters/base.py`) and register it in `ADAPTERS`, framework adapters ahead of the generic `openinference` one.
43
+
44
+ - `detect(span)` claims the framework's spans, usually by instrumentation scope.
45
+ - `start_span_type(span)` / `span_type(span)` classify spans the conventions don't. A declared `confident.span.type` still wins, and an adapter wins over the GenAI operation name.
46
+ - `span_fields(...)` and `trace_fields(...)` only fill fields the span didn't set.
47
+ - `self_providers` lists names a framework reports as the provider in place of the model's vendor.
48
+
49
+ Map fields the way the Confident AI backend does for the same framework, so a trace looks the same locally and on the platform. The deliberate difference is content that evaluation reads: model and agent output becomes its answer text, and agent input the latest user message.
@@ -0,0 +1,3 @@
1
+ from .otel import instrument_agentcore
2
+
3
+ __all__ = ["instrument_agentcore"]
@@ -0,0 +1,42 @@
1
+ """deepeval's AWS Bedrock AgentCore integration, built on confident-trace.
2
+
3
+ confident-trace traces each AgentCore invocation once deepeval starts it with
4
+ the ``agentcore`` instrumentation, and the Strands agent serving it with the
5
+ ``strands`` one.
6
+ """
7
+
8
+ from typing import List, Optional
9
+
10
+ from deepeval.telemetry import capture_tracing_integration
11
+ from deepeval.tracing.integrations import Integration
12
+ from deepeval.tracing.otel.adapters.strands import SCOPE
13
+ from deepeval.tracing.otel.setup import (
14
+ ensure_confident_trace,
15
+ set_trace_defaults,
16
+ )
17
+
18
+
19
+ def instrument_agentcore(
20
+ # Deprecated, ignored: a Confident AI platform setting. Don't build on it.
21
+ api_key: Optional[str] = None,
22
+ name: Optional[str] = None,
23
+ thread_id: Optional[str] = None,
24
+ # Deprecated, ignored: a Confident AI platform setting. Don't build on it.
25
+ user_id: Optional[str] = None,
26
+ metadata: Optional[dict] = None,
27
+ tags: Optional[List[str]] = None,
28
+ environment: Optional[str] = None,
29
+ # Deprecated, ignored: Confident AI platform settings. Don't build on them.
30
+ metric_collection: Optional[str] = None,
31
+ test_case_id: Optional[str] = None,
32
+ turn_id: Optional[str] = None,
33
+ ) -> None:
34
+ """Trace AWS Bedrock AgentCore and its Strands agents for deepeval.
35
+
36
+ The kwargs are defaults for every trace; ``update_current_trace(...)``
37
+ overrides them at runtime. Span fields are set at the call site with
38
+ ``update_current_span(...)`` or ``next_*_span(...)``.
39
+ """
40
+ with capture_tracing_integration(Integration.AGENTCORE):
41
+ ensure_confident_trace(("agentcore", "strands"), global_provider=True)
42
+ set_trace_defaults(SCOPE, dict(locals()))
@@ -0,0 +1,167 @@
1
+ """deepeval's CrewAI integration, built on confident-trace.
2
+
3
+ confident-trace traces crews, tasks, agents and tools once deepeval starts it
4
+ with the ``crewai`` instrumentation, and their model calls with the provider
5
+ ones. deepeval adds a span for each knowledge retrieval; its ``Crew``,
6
+ ``Agent``, ``LLM`` and ``tool`` add the metrics they are given.
7
+ """
8
+
9
+ import functools
10
+ import inspect
11
+ from typing import Any, Callable, Optional
12
+
13
+ from deepeval.telemetry import capture_tracing_integration
14
+ from deepeval.tracing.context import update_current_span
15
+ from deepeval.tracing.integrations import Integration
16
+ from deepeval.tracing.otel.setup import ensure_confident_trace
17
+
18
+ try:
19
+ import crewai # noqa: F401
20
+
21
+ crewai_installed = True
22
+ except ImportError:
23
+ crewai_installed = False
24
+
25
+ # CrewAI's model calls are traced through their provider's SDK.
26
+ INSTRUMENTATIONS = (
27
+ "crewai",
28
+ "openai",
29
+ "anthropic",
30
+ "google_genai",
31
+ "bedrock",
32
+ "litellm",
33
+ )
34
+ _RETRIEVALS = ("handle_knowledge_retrieval", "ahandle_knowledge_retrieval")
35
+ _FOR_EACH = ("kickoff_for_each", "kickoff_for_each_async", "akickoff_for_each")
36
+
37
+
38
+ def is_crewai_installed():
39
+ if not crewai_installed:
40
+ raise ImportError(
41
+ "CrewAI is not installed. Please install it with `pip install crewai`."
42
+ )
43
+
44
+
45
+ def instrument_crewai(
46
+ # Deprecated, ignored: a Confident AI platform setting. Don't build on it.
47
+ api_key: Optional[str] = None,
48
+ ):
49
+ is_crewai_installed()
50
+ with capture_tracing_integration(Integration.CREW_AI):
51
+ ensure_confident_trace(INSTRUMENTATIONS)
52
+ _trace_knowledge_retrieval()
53
+ _trace_kickoff_for_each()
54
+
55
+
56
+ def reset_crewai_instrumentation():
57
+ """Kept for compatibility: deepeval keeps no CrewAI state of its own."""
58
+
59
+
60
+ def _trace_knowledge_retrieval() -> None:
61
+ import crewai.agent.core as core
62
+
63
+ for name in _RETRIEVALS:
64
+ retrieve = getattr(core, name, None)
65
+ if retrieve is not None and not getattr(
66
+ retrieve, "_deepeval_patched", False
67
+ ):
68
+ setattr(core, name, _with_retrieval_span(retrieve))
69
+
70
+
71
+ def _with_retrieval_span(retrieve: Callable[..., Any]) -> Callable[..., Any]:
72
+ """``retrieve``, recorded as a retriever span when the agent has knowledge.
73
+
74
+ It returns the task prompt with what it retrieved appended.
75
+ """
76
+ import confident_trace
77
+
78
+ if inspect.iscoroutinefunction(retrieve):
79
+
80
+ @functools.wraps(retrieve)
81
+ async def traced(agent, task, task_prompt, *args, **kwargs):
82
+ if not _uses_knowledge(agent):
83
+ return await retrieve(agent, task, task_prompt, *args, **kwargs)
84
+ with confident_trace.span(
85
+ name="knowledge_retrieval", type="retriever"
86
+ ):
87
+ prompt = await retrieve(
88
+ agent, task, task_prompt, *args, **kwargs
89
+ )
90
+ _record_retrieval(agent, task_prompt, prompt)
91
+ return prompt
92
+
93
+ else:
94
+
95
+ @functools.wraps(retrieve)
96
+ def traced(agent, task, task_prompt, *args, **kwargs):
97
+ if not _uses_knowledge(agent):
98
+ return retrieve(agent, task, task_prompt, *args, **kwargs)
99
+ with confident_trace.span(
100
+ name="knowledge_retrieval", type="retriever"
101
+ ):
102
+ prompt = retrieve(agent, task, task_prompt, *args, **kwargs)
103
+ _record_retrieval(agent, task_prompt, prompt)
104
+ return prompt
105
+
106
+ traced._deepeval_patched = True
107
+ return traced
108
+
109
+
110
+ def _trace_kickoff_for_each() -> None:
111
+ """Run each ``kickoff_for_each`` under one span, carrying the crew's
112
+ metrics: CrewAI kicks off a copy of the crew per input."""
113
+ from crewai import Crew
114
+
115
+ from deepeval.integrations.crewai.subs import with_staged_metrics
116
+
117
+ for name in _FOR_EACH:
118
+ kickoff = getattr(Crew, name, None)
119
+ if kickoff is not None and not getattr(
120
+ kickoff, "_deepeval_patched", False
121
+ ):
122
+ spanned = _with_span(kickoff, name)
123
+ traced = with_staged_metrics(lambda spanned=spanned: spanned, None)
124
+ traced._deepeval_patched = True
125
+ setattr(Crew, name, traced)
126
+
127
+
128
+ def _with_span(method: Callable[..., Any], name: str) -> Callable[..., Any]:
129
+ """``method``, run inside a span called ``name``."""
130
+ import confident_trace
131
+
132
+ if inspect.iscoroutinefunction(method):
133
+
134
+ @functools.wraps(method)
135
+ async def traced(*args, **kwargs):
136
+ with confident_trace.span(name=name):
137
+ return await method(*args, **kwargs)
138
+
139
+ else:
140
+
141
+ @functools.wraps(method)
142
+ def traced(*args, **kwargs):
143
+ with confident_trace.span(name=name):
144
+ return method(*args, **kwargs)
145
+
146
+ return traced
147
+
148
+
149
+ def _uses_knowledge(agent: Any) -> bool:
150
+ # CrewAI's own test for whether it retrieves anything.
151
+ crew = agent.crew if not isinstance(agent.crew, str) else None
152
+ return bool(agent.knowledge or (crew and crew.knowledge))
153
+
154
+
155
+ def _record_retrieval(agent: Any, task_prompt: Any, prompt: Any) -> None:
156
+ retrieved = (
157
+ prompt[len(task_prompt) :]
158
+ if isinstance(prompt, str)
159
+ and isinstance(task_prompt, str)
160
+ and prompt.startswith(task_prompt)
161
+ else None
162
+ )
163
+ update_current_span(
164
+ input=getattr(agent, "knowledge_search_query", None),
165
+ output=retrieved or None,
166
+ retrieval_context=[retrieved] if retrieved else None,
167
+ )