judgeval 0.0.38__tar.gz → 0.0.39__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 (168) hide show
  1. {judgeval-0.0.38 → judgeval-0.0.39}/PKG-INFO +1 -1
  2. {judgeval-0.0.38 → judgeval-0.0.39}/Pipfile +1 -1
  3. {judgeval-0.0.38 → judgeval-0.0.39}/Pipfile.lock +345 -200
  4. {judgeval-0.0.38 → judgeval-0.0.39}/pyproject.toml +1 -1
  5. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/constants.py +1 -0
  6. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/data/example.py +7 -6
  7. judgeval-0.0.39/src/judgeval/data/tool.py +19 -0
  8. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/data/trace.py +2 -1
  9. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/judgment_client.py +6 -4
  10. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/run_evaluation.py +350 -26
  11. {judgeval-0.0.38 → judgeval-0.0.39}/.github/pull_request_template.md +0 -0
  12. {judgeval-0.0.38 → judgeval-0.0.39}/.github/workflows/ci.yaml +0 -0
  13. {judgeval-0.0.38 → judgeval-0.0.39}/.gitignore +0 -0
  14. {judgeval-0.0.38 → judgeval-0.0.39}/LICENSE.md +0 -0
  15. {judgeval-0.0.38 → judgeval-0.0.39}/README.md +0 -0
  16. {judgeval-0.0.38 → judgeval-0.0.39}/assets/Screenshot 2025-05-17 at 8.14.27/342/200/257PM.png" +0 -0
  17. {judgeval-0.0.38 → judgeval-0.0.39}/assets/dataset_clustering_screenshot.png +0 -0
  18. {judgeval-0.0.38 → judgeval-0.0.39}/assets/dataset_clustering_screenshot_dm.png +0 -0
  19. {judgeval-0.0.38 → judgeval-0.0.39}/assets/datasets_preview_screenshot.png +0 -0
  20. {judgeval-0.0.38 → judgeval-0.0.39}/assets/experiments_dashboard_screenshot.png +0 -0
  21. {judgeval-0.0.38 → judgeval-0.0.39}/assets/experiments_page.png +0 -0
  22. {judgeval-0.0.38 → judgeval-0.0.39}/assets/logo-dark.svg +0 -0
  23. {judgeval-0.0.38 → judgeval-0.0.39}/assets/logo-light.svg +0 -0
  24. {judgeval-0.0.38 → judgeval-0.0.39}/assets/monitoring_screenshot.png +0 -0
  25. {judgeval-0.0.38 → judgeval-0.0.39}/assets/trace_screenshot.png +0 -0
  26. {judgeval-0.0.38 → judgeval-0.0.39}/docs/README.md +0 -0
  27. {judgeval-0.0.38 → judgeval-0.0.39}/docs/alerts/notifications.mdx +0 -0
  28. {judgeval-0.0.38 → judgeval-0.0.39}/docs/alerts/platform_notifications.mdx +0 -0
  29. {judgeval-0.0.38 → judgeval-0.0.39}/docs/alerts/rules.mdx +0 -0
  30. {judgeval-0.0.38 → judgeval-0.0.39}/docs/api_reference/judgment_client.mdx +0 -0
  31. {judgeval-0.0.38 → judgeval-0.0.39}/docs/api_reference/trace.mdx +0 -0
  32. {judgeval-0.0.38 → judgeval-0.0.39}/docs/changelog/2025-04-21.mdx +0 -0
  33. {judgeval-0.0.38 → judgeval-0.0.39}/docs/clustering/clustering.mdx +0 -0
  34. {judgeval-0.0.38 → judgeval-0.0.39}/docs/compliance/certifications.mdx +0 -0
  35. {judgeval-0.0.38 → judgeval-0.0.39}/docs/development.mdx +0 -0
  36. {judgeval-0.0.38 → judgeval-0.0.39}/docs/essentials/code.mdx +0 -0
  37. {judgeval-0.0.38 → judgeval-0.0.39}/docs/essentials/images.mdx +0 -0
  38. {judgeval-0.0.38 → judgeval-0.0.39}/docs/essentials/markdown.mdx +0 -0
  39. {judgeval-0.0.38 → judgeval-0.0.39}/docs/essentials/navigation.mdx +0 -0
  40. {judgeval-0.0.38 → judgeval-0.0.39}/docs/essentials/reusable-snippets.mdx +0 -0
  41. {judgeval-0.0.38 → judgeval-0.0.39}/docs/essentials/settings.mdx +0 -0
  42. {judgeval-0.0.38 → judgeval-0.0.39}/docs/evaluation/data_datasets.mdx +0 -0
  43. {judgeval-0.0.38 → judgeval-0.0.39}/docs/evaluation/data_examples.mdx +0 -0
  44. {judgeval-0.0.38 → judgeval-0.0.39}/docs/evaluation/data_sequences.mdx +0 -0
  45. {judgeval-0.0.38 → judgeval-0.0.39}/docs/evaluation/experiment_comparisons.mdx +0 -0
  46. {judgeval-0.0.38 → judgeval-0.0.39}/docs/evaluation/introduction.mdx +0 -0
  47. {judgeval-0.0.38 → judgeval-0.0.39}/docs/evaluation/judges.mdx +0 -0
  48. {judgeval-0.0.38 → judgeval-0.0.39}/docs/evaluation/scorers/agent/derailment.mdx +0 -0
  49. {judgeval-0.0.38 → judgeval-0.0.39}/docs/evaluation/scorers/classifier_scorer.mdx +0 -0
  50. {judgeval-0.0.38 → judgeval-0.0.39}/docs/evaluation/scorers/custom_scorers.mdx +0 -0
  51. {judgeval-0.0.38 → judgeval-0.0.39}/docs/evaluation/scorers/default/answer_correctness.mdx +0 -0
  52. {judgeval-0.0.38 → judgeval-0.0.39}/docs/evaluation/scorers/default/answer_relevancy.mdx +0 -0
  53. {judgeval-0.0.38 → judgeval-0.0.39}/docs/evaluation/scorers/default/comparison.mdx +0 -0
  54. {judgeval-0.0.38 → judgeval-0.0.39}/docs/evaluation/scorers/default/contextual_precision.mdx +0 -0
  55. {judgeval-0.0.38 → judgeval-0.0.39}/docs/evaluation/scorers/default/contextual_recall.mdx +0 -0
  56. {judgeval-0.0.38 → judgeval-0.0.39}/docs/evaluation/scorers/default/contextual_relevancy.mdx +0 -0
  57. {judgeval-0.0.38 → judgeval-0.0.39}/docs/evaluation/scorers/default/execution_order.mdx +0 -0
  58. {judgeval-0.0.38 → judgeval-0.0.39}/docs/evaluation/scorers/default/faithfulness.mdx +0 -0
  59. {judgeval-0.0.38 → judgeval-0.0.39}/docs/evaluation/scorers/default/groundedness.mdx +0 -0
  60. {judgeval-0.0.38 → judgeval-0.0.39}/docs/evaluation/scorers/default/json_correctness.mdx +0 -0
  61. {judgeval-0.0.38 → judgeval-0.0.39}/docs/evaluation/scorers/default/summarization.mdx +0 -0
  62. {judgeval-0.0.38 → judgeval-0.0.39}/docs/evaluation/scorers/introduction.mdx +0 -0
  63. {judgeval-0.0.38 → judgeval-0.0.39}/docs/evaluation/unit_testing.mdx +0 -0
  64. {judgeval-0.0.38 → judgeval-0.0.39}/docs/favicon.svg +0 -0
  65. {judgeval-0.0.38 → judgeval-0.0.39}/docs/getting_started.mdx +0 -0
  66. {judgeval-0.0.38 → judgeval-0.0.39}/docs/images/annotation_queue_ui.png +0 -0
  67. {judgeval-0.0.38 → judgeval-0.0.39}/docs/images/basic_trace_example.png +0 -0
  68. {judgeval-0.0.38 → judgeval-0.0.39}/docs/images/checks-passed.png +0 -0
  69. {judgeval-0.0.38 → judgeval-0.0.39}/docs/images/cluster.png +0 -0
  70. {judgeval-0.0.38 → judgeval-0.0.39}/docs/images/cluster_button.png +0 -0
  71. {judgeval-0.0.38 → judgeval-0.0.39}/docs/images/create_aggressive_scorer.png +0 -0
  72. {judgeval-0.0.38 → judgeval-0.0.39}/docs/images/create_scorer.png +0 -0
  73. {judgeval-0.0.38 → judgeval-0.0.39}/docs/images/dashboard_annotation_queue_button.png +0 -0
  74. {judgeval-0.0.38 → judgeval-0.0.39}/docs/images/evaluation_diagram.png +0 -0
  75. {judgeval-0.0.38 → judgeval-0.0.39}/docs/images/experiment-comparison-page-2.png +0 -0
  76. {judgeval-0.0.38 → judgeval-0.0.39}/docs/images/experiment-page-comparison.png +0 -0
  77. {judgeval-0.0.38 → judgeval-0.0.39}/docs/images/experiment-popout-comparison.png +0 -0
  78. {judgeval-0.0.38 → judgeval-0.0.39}/docs/images/experiments-page-comparison-2.png +0 -0
  79. {judgeval-0.0.38 → judgeval-0.0.39}/docs/images/experiments-page-comparison.png +0 -0
  80. {judgeval-0.0.38 → judgeval-0.0.39}/docs/images/export-dataset.png +0 -0
  81. {judgeval-0.0.38 → judgeval-0.0.39}/docs/images/hero-dark.svg +0 -0
  82. {judgeval-0.0.38 → judgeval-0.0.39}/docs/images/hero-light.svg +0 -0
  83. {judgeval-0.0.38 → judgeval-0.0.39}/docs/images/notifications_page.png +0 -0
  84. {judgeval-0.0.38 → judgeval-0.0.39}/docs/images/online_eval_fault.png +0 -0
  85. {judgeval-0.0.38 → judgeval-0.0.39}/docs/images/reports_modal.png +0 -0
  86. {judgeval-0.0.38 → judgeval-0.0.39}/docs/images/synth_data_button.png +0 -0
  87. {judgeval-0.0.38 → judgeval-0.0.39}/docs/images/synth_data_window.png +0 -0
  88. {judgeval-0.0.38 → judgeval-0.0.39}/docs/images/trace_ss.png +0 -0
  89. {judgeval-0.0.38 → judgeval-0.0.39}/docs/integration/langgraph.mdx +0 -0
  90. {judgeval-0.0.38 → judgeval-0.0.39}/docs/introduction.mdx +0 -0
  91. {judgeval-0.0.38 → judgeval-0.0.39}/docs/judgment_cli/installation.mdx +0 -0
  92. {judgeval-0.0.38 → judgeval-0.0.39}/docs/judgment_cli/self-hosting.mdx +0 -0
  93. {judgeval-0.0.38 → judgeval-0.0.39}/docs/judgment_cli/supabase-org-id.png +0 -0
  94. {judgeval-0.0.38 → judgeval-0.0.39}/docs/logo/dark.svg +0 -0
  95. {judgeval-0.0.38 → judgeval-0.0.39}/docs/logo/light.svg +0 -0
  96. {judgeval-0.0.38 → judgeval-0.0.39}/docs/mint.json +0 -0
  97. {judgeval-0.0.38 → judgeval-0.0.39}/docs/monitoring/annotations.mdx +0 -0
  98. {judgeval-0.0.38 → judgeval-0.0.39}/docs/monitoring/introduction.mdx +0 -0
  99. {judgeval-0.0.38 → judgeval-0.0.39}/docs/monitoring/production_insights.mdx +0 -0
  100. {judgeval-0.0.38 → judgeval-0.0.39}/docs/monitoring/tracing.mdx +0 -0
  101. {judgeval-0.0.38 → judgeval-0.0.39}/docs/monitoring/tracing_s3.mdx +0 -0
  102. {judgeval-0.0.38 → judgeval-0.0.39}/docs/notebooks/create_dataset.ipynb +0 -0
  103. {judgeval-0.0.38 → judgeval-0.0.39}/docs/notebooks/create_scorer.ipynb +0 -0
  104. {judgeval-0.0.38 → judgeval-0.0.39}/docs/notebooks/demo.ipynb +0 -0
  105. {judgeval-0.0.38 → judgeval-0.0.39}/docs/notebooks/prompt_scorer.ipynb +0 -0
  106. {judgeval-0.0.38 → judgeval-0.0.39}/docs/notebooks/quickstart.ipynb +0 -0
  107. {judgeval-0.0.38 → judgeval-0.0.39}/docs/optimization/osiris_agent.mdx +0 -0
  108. {judgeval-0.0.38 → judgeval-0.0.39}/docs/quickstart.mdx +0 -0
  109. {judgeval-0.0.38 → judgeval-0.0.39}/docs/self_hosting/get_started.mdx +0 -0
  110. {judgeval-0.0.38 → judgeval-0.0.39}/docs/snippets/snippet-intro.mdx +0 -0
  111. {judgeval-0.0.38 → judgeval-0.0.39}/docs/synthetic_data/synthetic_data.mdx +0 -0
  112. {judgeval-0.0.38 → judgeval-0.0.39}/pytest.ini +0 -0
  113. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/__init__.py +0 -0
  114. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/clients.py +0 -0
  115. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/common/__init__.py +0 -0
  116. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/common/exceptions.py +0 -0
  117. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/common/logger.py +0 -0
  118. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/common/s3_storage.py +0 -0
  119. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/common/tracer.py +0 -0
  120. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/common/utils.py +0 -0
  121. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/data/__init__.py +0 -0
  122. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/data/custom_example.py +0 -0
  123. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/data/datasets/__init__.py +0 -0
  124. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/data/datasets/dataset.py +0 -0
  125. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/data/datasets/eval_dataset_client.py +0 -0
  126. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/data/result.py +0 -0
  127. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/data/scorer_data.py +0 -0
  128. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/data/trace_run.py +0 -0
  129. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/evaluation_run.py +0 -0
  130. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/integrations/langgraph.py +0 -0
  131. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/judges/__init__.py +0 -0
  132. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/judges/base_judge.py +0 -0
  133. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/judges/litellm_judge.py +0 -0
  134. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/judges/mixture_of_judges.py +0 -0
  135. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/judges/together_judge.py +0 -0
  136. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/judges/utils.py +0 -0
  137. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/rules.py +0 -0
  138. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/scorers/__init__.py +0 -0
  139. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/scorers/api_scorer.py +0 -0
  140. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/scorers/exceptions.py +0 -0
  141. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/scorers/judgeval_scorer.py +0 -0
  142. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/scorers/judgeval_scorers/__init__.py +0 -0
  143. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/scorers/judgeval_scorers/api_scorers/__init__.py +0 -0
  144. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/scorers/judgeval_scorers/api_scorers/answer_correctness.py +0 -0
  145. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/scorers/judgeval_scorers/api_scorers/answer_relevancy.py +0 -0
  146. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/scorers/judgeval_scorers/api_scorers/comparison.py +0 -0
  147. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/scorers/judgeval_scorers/api_scorers/contextual_precision.py +0 -0
  148. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/scorers/judgeval_scorers/api_scorers/contextual_recall.py +0 -0
  149. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/scorers/judgeval_scorers/api_scorers/contextual_relevancy.py +0 -0
  150. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/scorers/judgeval_scorers/api_scorers/derailment_scorer.py +0 -0
  151. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/scorers/judgeval_scorers/api_scorers/execution_order.py +0 -0
  152. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/scorers/judgeval_scorers/api_scorers/faithfulness.py +0 -0
  153. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/scorers/judgeval_scorers/api_scorers/groundedness.py +0 -0
  154. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/scorers/judgeval_scorers/api_scorers/hallucination.py +0 -0
  155. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/scorers/judgeval_scorers/api_scorers/instruction_adherence.py +0 -0
  156. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/scorers/judgeval_scorers/api_scorers/json_correctness.py +0 -0
  157. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/scorers/judgeval_scorers/api_scorers/summarization.py +0 -0
  158. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/scorers/judgeval_scorers/api_scorers/tool_order.py +0 -0
  159. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/scorers/judgeval_scorers/classifiers/__init__.py +0 -0
  160. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/scorers/judgeval_scorers/classifiers/text2sql/__init__.py +0 -0
  161. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/scorers/judgeval_scorers/classifiers/text2sql/text2sql_scorer.py +0 -0
  162. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/scorers/prompt_scorer.py +0 -0
  163. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/scorers/score.py +0 -0
  164. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/scorers/utils.py +0 -0
  165. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/tracer/__init__.py +0 -0
  166. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/utils/alerts.py +0 -0
  167. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/utils/data_utils.py +0 -0
  168. {judgeval-0.0.38 → judgeval-0.0.39}/src/judgeval/version_check.py +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: judgeval
3
- Version: 0.0.38
3
+ Version: 0.0.39
4
4
  Summary: Judgeval Package
5
5
  Project-URL: Homepage, https://github.com/JudgmentLabs/judgeval
6
6
  Project-URL: Issues, https://github.com/JudgmentLabs/judgeval/issues
@@ -4,7 +4,7 @@ verify_ssl = true
4
4
  name = "pypi"
5
5
 
6
6
  [packages]
7
- litellm = "==1.38.12"
7
+ litellm = "==1.61.15"
8
8
  python-dotenv = "==1.0.1"
9
9
  requests = "*"
10
10
  pandas = "*"