judgeval 0.0.1__tar.gz → 0.0.2__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 (130) hide show
  1. {judgeval-0.0.1 → judgeval-0.0.2}/PKG-INFO +2 -8
  2. judgeval-0.0.2/README.md +3 -0
  3. {judgeval-0.0.1 → judgeval-0.0.2}/pyproject.toml +1 -1
  4. judgeval-0.0.1/README.md +0 -9
  5. {judgeval-0.0.1 → judgeval-0.0.2}/.github/workflows/ci.yaml +0 -0
  6. {judgeval-0.0.1 → judgeval-0.0.2}/.gitignore +0 -0
  7. {judgeval-0.0.1 → judgeval-0.0.2}/LICENSE.md +0 -0
  8. {judgeval-0.0.1 → judgeval-0.0.2}/Pipfile +0 -0
  9. {judgeval-0.0.1 → judgeval-0.0.2}/docs/README.md +0 -0
  10. {judgeval-0.0.1 → judgeval-0.0.2}/docs/development.mdx +0 -0
  11. {judgeval-0.0.1 → judgeval-0.0.2}/docs/essentials/code.mdx +0 -0
  12. {judgeval-0.0.1 → judgeval-0.0.2}/docs/essentials/images.mdx +0 -0
  13. {judgeval-0.0.1 → judgeval-0.0.2}/docs/essentials/markdown.mdx +0 -0
  14. {judgeval-0.0.1 → judgeval-0.0.2}/docs/essentials/navigation.mdx +0 -0
  15. {judgeval-0.0.1 → judgeval-0.0.2}/docs/essentials/reusable-snippets.mdx +0 -0
  16. {judgeval-0.0.1 → judgeval-0.0.2}/docs/essentials/settings.mdx +0 -0
  17. {judgeval-0.0.1 → judgeval-0.0.2}/docs/evaluation/data_datasets.mdx +0 -0
  18. {judgeval-0.0.1 → judgeval-0.0.2}/docs/evaluation/data_examples.mdx +0 -0
  19. {judgeval-0.0.1 → judgeval-0.0.2}/docs/evaluation/introduction.mdx +0 -0
  20. {judgeval-0.0.1 → judgeval-0.0.2}/docs/evaluation/judges.mdx +0 -0
  21. {judgeval-0.0.1 → judgeval-0.0.2}/docs/evaluation/scorers/answer_relevancy.mdx +0 -0
  22. {judgeval-0.0.1 → judgeval-0.0.2}/docs/evaluation/scorers/classifier_scorer.mdx +0 -0
  23. {judgeval-0.0.1 → judgeval-0.0.2}/docs/evaluation/scorers/contextual_precision.mdx +0 -0
  24. {judgeval-0.0.1 → judgeval-0.0.2}/docs/evaluation/scorers/contextual_recall.mdx +0 -0
  25. {judgeval-0.0.1 → judgeval-0.0.2}/docs/evaluation/scorers/contextual_relevancy.mdx +0 -0
  26. {judgeval-0.0.1 → judgeval-0.0.2}/docs/evaluation/scorers/custom_scorers.mdx +0 -0
  27. {judgeval-0.0.1 → judgeval-0.0.2}/docs/evaluation/scorers/faithfulness.mdx +0 -0
  28. {judgeval-0.0.1 → judgeval-0.0.2}/docs/evaluation/scorers/hallucination.mdx +0 -0
  29. {judgeval-0.0.1 → judgeval-0.0.2}/docs/evaluation/scorers/introduction.mdx +0 -0
  30. {judgeval-0.0.1 → judgeval-0.0.2}/docs/evaluation/scorers/json_correctness.mdx +0 -0
  31. {judgeval-0.0.1 → judgeval-0.0.2}/docs/evaluation/scorers/summarization.mdx +0 -0
  32. {judgeval-0.0.1 → judgeval-0.0.2}/docs/evaluation/scorers/tool_correctness.mdx +0 -0
  33. {judgeval-0.0.1 → judgeval-0.0.2}/docs/favicon.svg +0 -0
  34. {judgeval-0.0.1 → judgeval-0.0.2}/docs/getting_started.mdx +0 -0
  35. {judgeval-0.0.1 → judgeval-0.0.2}/docs/images/checks-passed.png +0 -0
  36. {judgeval-0.0.1 → judgeval-0.0.2}/docs/images/create_aggressive_scorer.png +0 -0
  37. {judgeval-0.0.1 → judgeval-0.0.2}/docs/images/create_scorer.png +0 -0
  38. {judgeval-0.0.1 → judgeval-0.0.2}/docs/images/evaluation_diagram.png +0 -0
  39. {judgeval-0.0.1 → judgeval-0.0.2}/docs/images/hero-dark.svg +0 -0
  40. {judgeval-0.0.1 → judgeval-0.0.2}/docs/images/hero-light.svg +0 -0
  41. {judgeval-0.0.1 → judgeval-0.0.2}/docs/introduction.mdx +0 -0
  42. {judgeval-0.0.1 → judgeval-0.0.2}/docs/judgment/introduction.mdx +0 -0
  43. {judgeval-0.0.1 → judgeval-0.0.2}/docs/logo/dark.svg +0 -0
  44. {judgeval-0.0.1 → judgeval-0.0.2}/docs/logo/light.svg +0 -0
  45. {judgeval-0.0.1 → judgeval-0.0.2}/docs/mint.json +0 -0
  46. {judgeval-0.0.1 → judgeval-0.0.2}/docs/notebooks/create_dataset.ipynb +0 -0
  47. {judgeval-0.0.1 → judgeval-0.0.2}/docs/notebooks/create_scorer.ipynb +0 -0
  48. {judgeval-0.0.1 → judgeval-0.0.2}/docs/notebooks/demo.ipynb +0 -0
  49. {judgeval-0.0.1 → judgeval-0.0.2}/docs/notebooks/prompt_scorer.ipynb +0 -0
  50. {judgeval-0.0.1 → judgeval-0.0.2}/docs/notebooks/quickstart.ipynb +0 -0
  51. {judgeval-0.0.1 → judgeval-0.0.2}/docs/quickstart.mdx +0 -0
  52. {judgeval-0.0.1 → judgeval-0.0.2}/docs/snippets/snippet-intro.mdx +0 -0
  53. {judgeval-0.0.1 → judgeval-0.0.2}/e2etests/judgment_client_test.py +0 -0
  54. {judgeval-0.0.1 → judgeval-0.0.2}/e2etests/playground.py +0 -0
  55. {judgeval-0.0.1 → judgeval-0.0.2}/e2etests/test_prompt_scoring.py +0 -0
  56. {judgeval-0.0.1 → judgeval-0.0.2}/e2etests/test_tracer.py +0 -0
  57. {judgeval-0.0.1 → judgeval-0.0.2}/pytest.ini +0 -0
  58. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/__init__.py +0 -0
  59. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/clients.py +0 -0
  60. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/common/__init__.py +0 -0
  61. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/common/exceptions.py +0 -0
  62. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/common/logger.py +0 -0
  63. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/common/tracer.py +0 -0
  64. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/common/utils.py +0 -0
  65. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/constants.py +0 -0
  66. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/data/__init__.py +0 -0
  67. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/data/api_example.py +0 -0
  68. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/data/datasets/__init__.py +0 -0
  69. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/data/datasets/dataset.py +0 -0
  70. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/data/datasets/ground_truth.py +0 -0
  71. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/data/datasets/utils.py +0 -0
  72. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/data/example.py +0 -0
  73. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/data/result.py +0 -0
  74. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/data/scorer_data.py +0 -0
  75. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/evaluation_run.py +0 -0
  76. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/judges/__init__.py +0 -0
  77. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/judges/base_judge.py +0 -0
  78. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/judges/litellm_judge.py +0 -0
  79. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/judges/mixture_of_judges.py +0 -0
  80. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/judges/together_judge.py +0 -0
  81. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/judges/utils.py +0 -0
  82. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/judgment_client.py +0 -0
  83. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/run_evaluation.py +0 -0
  84. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/scorers/__init__.py +0 -0
  85. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/scorers/base_scorer.py +0 -0
  86. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/scorers/custom_scorer.py +0 -0
  87. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/scorers/judgeval_scorers/__init__.py +0 -0
  88. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/scorers/judgeval_scorers/answer_relevancy.py +0 -0
  89. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/scorers/judgeval_scorers/contextual_precision.py +0 -0
  90. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/scorers/judgeval_scorers/contextual_recall.py +0 -0
  91. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/scorers/judgeval_scorers/contextual_relevancy.py +0 -0
  92. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/scorers/judgeval_scorers/faithfulness.py +0 -0
  93. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/scorers/judgeval_scorers/hallucination.py +0 -0
  94. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/scorers/judgeval_scorers/json_correctness.py +0 -0
  95. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/scorers/judgeval_scorers/summarization.py +0 -0
  96. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/scorers/judgeval_scorers/tool_correctness.py +0 -0
  97. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/scorers/prompt_scorer.py +0 -0
  98. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/scorers/score.py +0 -0
  99. {judgeval-0.0.1 → judgeval-0.0.2}/src/judgeval/scorers/utils.py +0 -0
  100. {judgeval-0.0.1 → judgeval-0.0.2}/tests/common/test_exceptions.py +0 -0
  101. {judgeval-0.0.1 → judgeval-0.0.2}/tests/common/test_logger.py +0 -0
  102. {judgeval-0.0.1 → judgeval-0.0.2}/tests/common/test_tracer.py +0 -0
  103. {judgeval-0.0.1 → judgeval-0.0.2}/tests/common/test_utils.py +0 -0
  104. {judgeval-0.0.1 → judgeval-0.0.2}/tests/data/datasets/sample_data/dataset.csv +0 -0
  105. {judgeval-0.0.1 → judgeval-0.0.2}/tests/data/datasets/sample_data/dataset.json +0 -0
  106. {judgeval-0.0.1 → judgeval-0.0.2}/tests/data/datasets/test_dataset.py +0 -0
  107. {judgeval-0.0.1 → judgeval-0.0.2}/tests/data/datasets/test_dataset_utils.py +0 -0
  108. {judgeval-0.0.1 → judgeval-0.0.2}/tests/data/datasets/test_ground_truth.py +0 -0
  109. {judgeval-0.0.1 → judgeval-0.0.2}/tests/data/test_api_example.py +0 -0
  110. {judgeval-0.0.1 → judgeval-0.0.2}/tests/data/test_example.py +0 -0
  111. {judgeval-0.0.1 → judgeval-0.0.2}/tests/data/test_result.py +0 -0
  112. {judgeval-0.0.1 → judgeval-0.0.2}/tests/data/test_scorer_data.py +0 -0
  113. {judgeval-0.0.1 → judgeval-0.0.2}/tests/judges/test_judge_utils.py +0 -0
  114. {judgeval-0.0.1 → judgeval-0.0.2}/tests/judges/test_litellm_judge.py +0 -0
  115. {judgeval-0.0.1 → judgeval-0.0.2}/tests/judges/test_mixture_of_judges.py +0 -0
  116. {judgeval-0.0.1 → judgeval-0.0.2}/tests/judges/test_together_judge.py +0 -0
  117. {judgeval-0.0.1 → judgeval-0.0.2}/tests/scorers/judgeval_scorers/test_answer_relevancy.py +0 -0
  118. {judgeval-0.0.1 → judgeval-0.0.2}/tests/scorers/judgeval_scorers/test_contextual_precision.py +0 -0
  119. {judgeval-0.0.1 → judgeval-0.0.2}/tests/scorers/judgeval_scorers/test_contextual_recall.py +0 -0
  120. {judgeval-0.0.1 → judgeval-0.0.2}/tests/scorers/judgeval_scorers/test_contextual_relevancy.py +0 -0
  121. {judgeval-0.0.1 → judgeval-0.0.2}/tests/scorers/judgeval_scorers/test_faithfulness.py +0 -0
  122. {judgeval-0.0.1 → judgeval-0.0.2}/tests/scorers/judgeval_scorers/test_hallucination.py +0 -0
  123. {judgeval-0.0.1 → judgeval-0.0.2}/tests/scorers/judgeval_scorers/test_json_correctness.py +0 -0
  124. {judgeval-0.0.1 → judgeval-0.0.2}/tests/scorers/judgeval_scorers/test_summarization.py +0 -0
  125. {judgeval-0.0.1 → judgeval-0.0.2}/tests/scorers/judgeval_scorers/test_tool_correctness.py +0 -0
  126. {judgeval-0.0.1 → judgeval-0.0.2}/tests/scorers/test_base_scorer.py +0 -0
  127. {judgeval-0.0.1 → judgeval-0.0.2}/tests/scorers/test_custom_scorer.py +0 -0
  128. {judgeval-0.0.1 → judgeval-0.0.2}/tests/scorers/test_prompt_scorer.py +0 -0
  129. {judgeval-0.0.1 → judgeval-0.0.2}/tests/scorers/test_score.py +0 -0
  130. {judgeval-0.0.1 → judgeval-0.0.2}/tests/scorers/test_scorer_utils.py +0 -0
{judgeval-0.0.1 → judgeval-0.0.2}/PKG-INFO RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: judgeval
3
- Version: 0.0.1
3
+ Version: 0.0.2
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
@@ -31,10 +31,4 @@ Description-Content-Type: text/markdown
31
31
 
32
32
  # judgeval
33
33
 
34
-
35
- TODOS
36
-
37
- 1. public interface for Example and Measurement objects
38
- 2. call to backend
39
- 3. datasets and logging
40
- 4. exporting to platform
34
+ Judgeval is a open-source evaluation framework for multi-agent LLM workflows, for both real-time and offline evaluations.
judgeval-0.0.2/README.md ADDED
@@ -0,0 +1,3 @@
1
+ # judgeval
2
+
3
+ Judgeval is a open-source evaluation framework for multi-agent LLM workflows, for both real-time and offline evaluations.
{judgeval-0.0.1 → judgeval-0.0.2}/pyproject.toml RENAMED
@@ -1,6 +1,6 @@
1
1
  [project]
2
2
  name = "judgeval"
3
- version = "0.0.1"
3
+ version = "0.0.2"
4
4
  authors = [
5
5
  { name="Andrew Li", email="andrew@judgmentlabs.ai" },
6
6
  { name="Alex Shan", email="alex@judgmentlabs.ai" },
judgeval-0.0.1/README.md DELETED
@@ -1,9 +0,0 @@
1
- # judgeval
2
-
3
-
4
- TODOS
5
-
6
- 1. public interface for Example and Measurement objects
7
- 2. call to backend
8
- 3. datasets and logging
9
- 4. exporting to platform
{judgeval-0.0.1 → judgeval-0.0.2}/.gitignore RENAMED
File without changes
{judgeval-0.0.1 → judgeval-0.0.2}/LICENSE.md RENAMED
File without changes
{judgeval-0.0.1 → judgeval-0.0.2}/Pipfile RENAMED
File without changes
{judgeval-0.0.1 → judgeval-0.0.2}/docs/README.md RENAMED
File without changes
{judgeval-0.0.1 → judgeval-0.0.2}/docs/development.mdx RENAMED
File without changes
{judgeval-0.0.1 → judgeval-0.0.2}/docs/favicon.svg RENAMED
File without changes
{judgeval-0.0.1 → judgeval-0.0.2}/docs/introduction.mdx RENAMED
File without changes
{judgeval-0.0.1 → judgeval-0.0.2}/docs/logo/dark.svg RENAMED
File without changes
{judgeval-0.0.1 → judgeval-0.0.2}/docs/logo/light.svg RENAMED
File without changes
{judgeval-0.0.1 → judgeval-0.0.2}/docs/mint.json RENAMED
File without changes
{judgeval-0.0.1 → judgeval-0.0.2}/docs/quickstart.mdx RENAMED
File without changes
{judgeval-0.0.1 → judgeval-0.0.2}/pytest.ini RENAMED
File without changes