judgeval 0.0.24__tar.gz → 0.0.26__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 (157) hide show
  1. {judgeval-0.0.24 → judgeval-0.0.26}/PKG-INFO +1 -1
  2. {judgeval-0.0.24 → judgeval-0.0.26}/Pipfile +1 -0
  3. {judgeval-0.0.24 → judgeval-0.0.26}/Pipfile.lock +1082 -1256
  4. {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/classifier_scorer.mdx +17 -4
  5. {judgeval-0.0.24 → judgeval-0.0.26}/docs/monitoring/introduction.mdx +6 -0
  6. {judgeval-0.0.24 → judgeval-0.0.26}/docs/monitoring/tracing.mdx +3 -3
  7. {judgeval-0.0.24 → judgeval-0.0.26}/pyproject.toml +1 -1
  8. judgeval-0.0.26/src/demo/demo.py +21 -0
  9. judgeval-0.0.26/src/demo/travel_agent.py +245 -0
  10. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/common/tracer.py +55 -8
  11. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/constants.py +3 -2
  12. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/data/datasets/dataset.py +42 -19
  13. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/integrations/langgraph.py +16 -12
  14. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/judgment_client.py +39 -9
  15. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/rules.py +177 -60
  16. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/run_evaluation.py +140 -103
  17. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/score.py +16 -11
  18. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/utils/alerts.py +32 -1
  19. {judgeval-0.0.24 → judgeval-0.0.26}/.github/workflows/ci.yaml +0 -0
  20. {judgeval-0.0.24 → judgeval-0.0.26}/.gitignore +0 -0
  21. {judgeval-0.0.24 → judgeval-0.0.26}/LICENSE.md +0 -0
  22. {judgeval-0.0.24 → judgeval-0.0.26}/README.md +0 -0
  23. {judgeval-0.0.24 → judgeval-0.0.26}/docs/README.md +0 -0
  24. {judgeval-0.0.24 → judgeval-0.0.26}/docs/api_reference/judgment_client.mdx +0 -0
  25. {judgeval-0.0.24 → judgeval-0.0.26}/docs/api_reference/trace.mdx +0 -0
  26. {judgeval-0.0.24 → judgeval-0.0.26}/docs/development.mdx +0 -0
  27. {judgeval-0.0.24 → judgeval-0.0.26}/docs/essentials/code.mdx +0 -0
  28. {judgeval-0.0.24 → judgeval-0.0.26}/docs/essentials/images.mdx +0 -0
  29. {judgeval-0.0.24 → judgeval-0.0.26}/docs/essentials/markdown.mdx +0 -0
  30. {judgeval-0.0.24 → judgeval-0.0.26}/docs/essentials/navigation.mdx +0 -0
  31. {judgeval-0.0.24 → judgeval-0.0.26}/docs/essentials/reusable-snippets.mdx +0 -0
  32. {judgeval-0.0.24 → judgeval-0.0.26}/docs/essentials/settings.mdx +0 -0
  33. {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/data_datasets.mdx +0 -0
  34. {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/data_examples.mdx +0 -0
  35. {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/introduction.mdx +0 -0
  36. {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/judges.mdx +0 -0
  37. {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/answer_correctness.mdx +0 -0
  38. {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/answer_relevancy.mdx +0 -0
  39. {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/comparison.mdx +0 -0
  40. {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/contextual_precision.mdx +0 -0
  41. {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/contextual_recall.mdx +0 -0
  42. {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/contextual_relevancy.mdx +0 -0
  43. {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/custom_scorers.mdx +0 -0
  44. {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/execution_order.mdx +0 -0
  45. {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/faithfulness.mdx +0 -0
  46. {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/groundedness.mdx +0 -0
  47. {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/hallucination.mdx +0 -0
  48. {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/introduction.mdx +0 -0
  49. {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/json_correctness.mdx +0 -0
  50. {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/summarization.mdx +0 -0
  51. {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/unit_testing.mdx +0 -0
  52. {judgeval-0.0.24 → judgeval-0.0.26}/docs/favicon.svg +0 -0
  53. {judgeval-0.0.24 → judgeval-0.0.26}/docs/getting_started.mdx +0 -0
  54. {judgeval-0.0.24 → judgeval-0.0.26}/docs/images/basic_trace_example.png +0 -0
  55. {judgeval-0.0.24 → judgeval-0.0.26}/docs/images/checks-passed.png +0 -0
  56. {judgeval-0.0.24 → judgeval-0.0.26}/docs/images/create_aggressive_scorer.png +0 -0
  57. {judgeval-0.0.24 → judgeval-0.0.26}/docs/images/create_scorer.png +0 -0
  58. {judgeval-0.0.24 → judgeval-0.0.26}/docs/images/evaluation_diagram.png +0 -0
  59. {judgeval-0.0.24 → judgeval-0.0.26}/docs/images/hero-dark.svg +0 -0
  60. {judgeval-0.0.24 → judgeval-0.0.26}/docs/images/hero-light.svg +0 -0
  61. {judgeval-0.0.24 → judgeval-0.0.26}/docs/images/online_eval_fault.png +0 -0
  62. {judgeval-0.0.24 → judgeval-0.0.26}/docs/images/trace_ss.png +0 -0
  63. {judgeval-0.0.24 → judgeval-0.0.26}/docs/integration/langgraph.mdx +0 -0
  64. {judgeval-0.0.24 → judgeval-0.0.26}/docs/introduction.mdx +0 -0
  65. {judgeval-0.0.24 → judgeval-0.0.26}/docs/judgment/introduction.mdx +0 -0
  66. {judgeval-0.0.24 → judgeval-0.0.26}/docs/logo/dark.svg +0 -0
  67. {judgeval-0.0.24 → judgeval-0.0.26}/docs/logo/light.svg +0 -0
  68. {judgeval-0.0.24 → judgeval-0.0.26}/docs/mint.json +0 -0
  69. {judgeval-0.0.24 → judgeval-0.0.26}/docs/monitoring/production_insights.mdx +0 -0
  70. {judgeval-0.0.24 → judgeval-0.0.26}/docs/notebooks/create_dataset.ipynb +0 -0
  71. {judgeval-0.0.24 → judgeval-0.0.26}/docs/notebooks/create_scorer.ipynb +0 -0
  72. {judgeval-0.0.24 → judgeval-0.0.26}/docs/notebooks/demo.ipynb +0 -0
  73. {judgeval-0.0.24 → judgeval-0.0.26}/docs/notebooks/prompt_scorer.ipynb +0 -0
  74. {judgeval-0.0.24 → judgeval-0.0.26}/docs/notebooks/quickstart.ipynb +0 -0
  75. {judgeval-0.0.24 → judgeval-0.0.26}/docs/quickstart.mdx +0 -0
  76. {judgeval-0.0.24 → judgeval-0.0.26}/docs/snippets/snippet-intro.mdx +0 -0
  77. {judgeval-0.0.24 → judgeval-0.0.26}/pytest.ini +0 -0
  78. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/__init__.py +0 -0
  79. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/clients.py +0 -0
  80. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/common/__init__.py +0 -0
  81. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/common/exceptions.py +0 -0
  82. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/common/logger.py +0 -0
  83. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/common/utils.py +0 -0
  84. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/data/__init__.py +0 -0
  85. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/data/api_example.py +0 -0
  86. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/data/datasets/__init__.py +0 -0
  87. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/data/datasets/eval_dataset_client.py +0 -0
  88. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/data/example.py +0 -0
  89. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/data/result.py +0 -0
  90. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/data/scorer_data.py +0 -0
  91. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/evaluation_run.py +0 -0
  92. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/judges/__init__.py +0 -0
  93. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/judges/base_judge.py +0 -0
  94. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/judges/litellm_judge.py +0 -0
  95. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/judges/mixture_of_judges.py +0 -0
  96. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/judges/together_judge.py +0 -0
  97. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/judges/utils.py +0 -0
  98. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/__init__.py +0 -0
  99. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/api_scorer.py +0 -0
  100. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/base_scorer.py +0 -0
  101. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/exceptions.py +0 -0
  102. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorer.py +0 -0
  103. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/__init__.py +0 -0
  104. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/api_scorers/__init__.py +0 -0
  105. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/api_scorers/answer_correctness.py +0 -0
  106. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/api_scorers/answer_relevancy.py +0 -0
  107. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/api_scorers/comparison.py +0 -0
  108. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/api_scorers/contextual_precision.py +0 -0
  109. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/api_scorers/contextual_recall.py +0 -0
  110. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/api_scorers/contextual_relevancy.py +0 -0
  111. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/api_scorers/execution_order.py +0 -0
  112. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/api_scorers/faithfulness.py +0 -0
  113. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/api_scorers/groundedness.py +0 -0
  114. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/api_scorers/hallucination.py +0 -0
  115. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/api_scorers/instruction_adherence.py +0 -0
  116. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/api_scorers/json_correctness.py +0 -0
  117. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/api_scorers/summarization.py +0 -0
  118. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/classifiers/__init__.py +0 -0
  119. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/classifiers/text2sql/__init__.py +0 -0
  120. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/classifiers/text2sql/text2sql_scorer.py +0 -0
  121. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/__init__.py +0 -0
  122. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/answer_correctness/__init__.py +0 -0
  123. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/answer_correctness/answer_correctness_scorer.py +0 -0
  124. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/answer_correctness/prompts.py +0 -0
  125. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/answer_relevancy/__init__.py +0 -0
  126. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/answer_relevancy/answer_relevancy_scorer.py +0 -0
  127. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/answer_relevancy/prompts.py +0 -0
  128. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/comparison/__init__.py +0 -0
  129. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/comparison/comparison_scorer.py +0 -0
  130. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/comparison/prompts.py +0 -0
  131. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/contextual_precision/__init__.py +0 -0
  132. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/contextual_precision/contextual_precision_scorer.py +0 -0
  133. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/contextual_precision/prompts.py +0 -0
  134. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/contextual_recall/__init__.py +0 -0
  135. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/contextual_recall/contextual_recall_scorer.py +0 -0
  136. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/contextual_recall/prompts.py +0 -0
  137. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/contextual_relevancy/__init__.py +0 -0
  138. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/contextual_relevancy/contextual_relevancy_scorer.py +0 -0
  139. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/contextual_relevancy/prompts.py +0 -0
  140. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/execution_order/__init__.py +0 -0
  141. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/execution_order/execution_order.py +0 -0
  142. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/faithfulness/__init__.py +0 -0
  143. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/faithfulness/faithfulness_scorer.py +0 -0
  144. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/faithfulness/prompts.py +0 -0
  145. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/hallucination/__init__.py +0 -0
  146. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/hallucination/hallucination_scorer.py +0 -0
  147. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/hallucination/prompts.py +0 -0
  148. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/instruction_adherence/instruction_adherence.py +0 -0
  149. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/instruction_adherence/prompt.py +0 -0
  150. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/json_correctness/__init__.py +0 -0
  151. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/json_correctness/json_correctness_scorer.py +0 -0
  152. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/summarization/__init__.py +0 -0
  153. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/summarization/prompts.py +0 -0
  154. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/summarization/summarization_scorer.py +0 -0
  155. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/prompt_scorer.py +0 -0
  156. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/utils.py +0 -0
  157. {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/tracer/__init__.py +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: judgeval
3
- Version: 0.0.24
3
+ Version: 0.0.26
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
@@ -23,6 +23,7 @@ langchain-huggingface = "*"
23
23
  langchain-openai = "*"
24
24
  langchain-anthropic = "*"
25
25
  langchain-core = "*"
26
+ langchain-community = "*"
26
27
 
27
28
  [dev-packages]
28
29
  pytest = "*"