judgeval 0.3.1__tar.gz → 0.3.2__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 (116) hide show
  1. {judgeval-0.3.1 → judgeval-0.3.2}/PKG-INFO +1 -1
  2. {judgeval-0.3.1 → judgeval-0.3.2}/pyproject.toml +1 -1
  3. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/common/tracer/core.py +2 -0
  4. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/common/tracer/trace_manager.py +5 -1
  5. {judgeval-0.3.1 → judgeval-0.3.2}/.github/ISSUE_TEMPLATE/bug_report.md +0 -0
  6. {judgeval-0.3.1 → judgeval-0.3.2}/.github/ISSUE_TEMPLATE/config.yml +0 -0
  7. {judgeval-0.3.1 → judgeval-0.3.2}/.github/ISSUE_TEMPLATE/feature_request.md +0 -0
  8. {judgeval-0.3.1 → judgeval-0.3.2}/.github/pull_request_template.md +0 -0
  9. {judgeval-0.3.1 → judgeval-0.3.2}/.github/workflows/blocked-pr.yaml +0 -0
  10. {judgeval-0.3.1 → judgeval-0.3.2}/.github/workflows/ci.yaml +0 -0
  11. {judgeval-0.3.1 → judgeval-0.3.2}/.github/workflows/lint.yaml +0 -0
  12. {judgeval-0.3.1 → judgeval-0.3.2}/.github/workflows/merge-branch-check.yaml +0 -0
  13. {judgeval-0.3.1 → judgeval-0.3.2}/.github/workflows/mypy.yaml +0 -0
  14. {judgeval-0.3.1 → judgeval-0.3.2}/.github/workflows/pre-commit-autoupdate.yaml +0 -0
  15. {judgeval-0.3.1 → judgeval-0.3.2}/.github/workflows/release.yaml +0 -0
  16. {judgeval-0.3.1 → judgeval-0.3.2}/.github/workflows/validate-branch.yaml +0 -0
  17. {judgeval-0.3.1 → judgeval-0.3.2}/.gitignore +0 -0
  18. {judgeval-0.3.1 → judgeval-0.3.2}/.pre-commit-config.yaml +0 -0
  19. {judgeval-0.3.1 → judgeval-0.3.2}/LICENSE.md +0 -0
  20. {judgeval-0.3.1 → judgeval-0.3.2}/README.md +0 -0
  21. {judgeval-0.3.1 → judgeval-0.3.2}/assets/Screenshot 2025-05-17 at 8.14.27/342/200/257PM.png" +0 -0
  22. {judgeval-0.3.1 → judgeval-0.3.2}/assets/agent.gif +0 -0
  23. {judgeval-0.3.1 → judgeval-0.3.2}/assets/agent_trace_example.png +0 -0
  24. {judgeval-0.3.1 → judgeval-0.3.2}/assets/data.gif +0 -0
  25. {judgeval-0.3.1 → judgeval-0.3.2}/assets/dataset_clustering_screenshot.png +0 -0
  26. {judgeval-0.3.1 → judgeval-0.3.2}/assets/dataset_clustering_screenshot_dm.png +0 -0
  27. {judgeval-0.3.1 → judgeval-0.3.2}/assets/datasets_preview_screenshot.png +0 -0
  28. {judgeval-0.3.1 → judgeval-0.3.2}/assets/document.gif +0 -0
  29. {judgeval-0.3.1 → judgeval-0.3.2}/assets/error_analysis_dashboard.png +0 -0
  30. {judgeval-0.3.1 → judgeval-0.3.2}/assets/errors.png +0 -0
  31. {judgeval-0.3.1 → judgeval-0.3.2}/assets/experiments_dashboard_screenshot.png +0 -0
  32. {judgeval-0.3.1 → judgeval-0.3.2}/assets/experiments_page.png +0 -0
  33. {judgeval-0.3.1 → judgeval-0.3.2}/assets/experiments_pagev2.png +0 -0
  34. {judgeval-0.3.1 → judgeval-0.3.2}/assets/logo-dark.svg +0 -0
  35. {judgeval-0.3.1 → judgeval-0.3.2}/assets/logo-light.svg +0 -0
  36. {judgeval-0.3.1 → judgeval-0.3.2}/assets/monitoring_screenshot.png +0 -0
  37. {judgeval-0.3.1 → judgeval-0.3.2}/assets/new_darkmode.svg +0 -0
  38. {judgeval-0.3.1 → judgeval-0.3.2}/assets/new_lightmode.svg +0 -0
  39. {judgeval-0.3.1 → judgeval-0.3.2}/assets/online_eval.png +0 -0
  40. {judgeval-0.3.1 → judgeval-0.3.2}/assets/product_shot.png +0 -0
  41. {judgeval-0.3.1 → judgeval-0.3.2}/assets/test.png +0 -0
  42. {judgeval-0.3.1 → judgeval-0.3.2}/assets/tests.png +0 -0
  43. {judgeval-0.3.1 → judgeval-0.3.2}/assets/trace.gif +0 -0
  44. {judgeval-0.3.1 → judgeval-0.3.2}/assets/trace_demo.png +0 -0
  45. {judgeval-0.3.1 → judgeval-0.3.2}/assets/trace_screenshot.png +0 -0
  46. {judgeval-0.3.1 → judgeval-0.3.2}/assets/trace_screenshot_old.png +0 -0
  47. {judgeval-0.3.1 → judgeval-0.3.2}/pytest.ini +0 -0
  48. {judgeval-0.3.1 → judgeval-0.3.2}/src/.coveragerc +0 -0
  49. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/__init__.py +0 -0
  50. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/clients.py +0 -0
  51. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/common/__init__.py +0 -0
  52. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/common/api/__init__.py +0 -0
  53. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/common/api/api.py +0 -0
  54. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/common/api/constants.py +0 -0
  55. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/common/exceptions.py +0 -0
  56. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/common/logger.py +0 -0
  57. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/common/storage/__init__.py +0 -0
  58. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/common/storage/s3_storage.py +0 -0
  59. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/common/tracer/__init__.py +0 -0
  60. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/common/tracer/constants.py +0 -0
  61. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/common/tracer/otel_exporter.py +0 -0
  62. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/common/tracer/otel_span_processor.py +0 -0
  63. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/common/tracer/span_processor.py +0 -0
  64. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/common/tracer/span_transformer.py +0 -0
  65. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/common/utils.py +0 -0
  66. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/constants.py +0 -0
  67. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/data/__init__.py +0 -0
  68. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/data/example.py +0 -0
  69. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/data/judgment_types.py +0 -0
  70. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/data/result.py +0 -0
  71. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/data/scorer_data.py +0 -0
  72. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/data/scripts/fix_default_factory.py +0 -0
  73. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/data/scripts/openapi_transform.py +0 -0
  74. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/data/tool.py +0 -0
  75. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/data/trace.py +0 -0
  76. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/data/trace_run.py +0 -0
  77. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/dataset.py +0 -0
  78. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/evaluation_run.py +0 -0
  79. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/integrations/langgraph.py +0 -0
  80. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/judges/__init__.py +0 -0
  81. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/judges/base_judge.py +0 -0
  82. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/judges/litellm_judge.py +0 -0
  83. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/judges/mixture_of_judges.py +0 -0
  84. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/judges/together_judge.py +0 -0
  85. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/judges/utils.py +0 -0
  86. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/judgment_client.py +0 -0
  87. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/rules.py +0 -0
  88. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/run_evaluation.py +0 -0
  89. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/scorers/__init__.py +0 -0
  90. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/scorers/agent_scorer.py +0 -0
  91. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/scorers/api_scorer.py +0 -0
  92. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/scorers/base_scorer.py +0 -0
  93. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/scorers/example_scorer.py +0 -0
  94. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/scorers/exceptions.py +0 -0
  95. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/scorers/judgeval_scorers/__init__.py +0 -0
  96. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/scorers/judgeval_scorers/api_scorers/__init__.py +0 -0
  97. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/scorers/judgeval_scorers/api_scorers/answer_correctness.py +0 -0
  98. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/scorers/judgeval_scorers/api_scorers/answer_relevancy.py +0 -0
  99. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/scorers/judgeval_scorers/api_scorers/derailment_scorer.py +0 -0
  100. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/scorers/judgeval_scorers/api_scorers/execution_order.py +0 -0
  101. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/scorers/judgeval_scorers/api_scorers/faithfulness.py +0 -0
  102. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/scorers/judgeval_scorers/api_scorers/hallucination.py +0 -0
  103. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/scorers/judgeval_scorers/api_scorers/instruction_adherence.py +0 -0
  104. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/scorers/judgeval_scorers/api_scorers/prompt_scorer.py +0 -0
  105. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/scorers/judgeval_scorers/api_scorers/tool_dependency.py +0 -0
  106. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/scorers/judgeval_scorers/api_scorers/tool_order.py +0 -0
  107. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/scorers/score.py +0 -0
  108. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/scorers/utils.py +0 -0
  109. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/tracer/__init__.py +0 -0
  110. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/utils/alerts.py +0 -0
  111. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/utils/file_utils.py +0 -0
  112. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/utils/requests.py +0 -0
  113. {judgeval-0.3.1 → judgeval-0.3.2}/src/judgeval/version_check.py +0 -0
  114. {judgeval-0.3.1 → judgeval-0.3.2}/src/update_types.sh +0 -0
  115. {judgeval-0.3.1 → judgeval-0.3.2}/update_version.py +0 -0
  116. {judgeval-0.3.1 → judgeval-0.3.2}/uv.lock +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: judgeval
3
- Version: 0.3.1
3
+ Version: 0.3.2
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
@@ -1,6 +1,6 @@
1
1
  [project]
2
2
  name = "judgeval"
3
- version = "0.3.1"
3
+ version = "0.3.2"
4
4
  authors = [
5
5
  { name="Andrew Li", email="andrew@judgmentlabs.ai" },
6
6
  { name="Alex Shan", email="alex@judgmentlabs.ai" },
@@ -418,6 +418,8 @@ class TraceClient:
418
418
  self.start_time or time.time(), timezone.utc
419
419
  ).isoformat(),
420
420
  "duration": total_duration,
421
+ "trace_spans": [span.model_dump() for span in self.trace_spans],
422
+ "evaluation_runs": [run.model_dump() for run in self.evaluation_runs],
421
423
  "offline_mode": self.tracer.offline_mode,
422
424
  "parent_trace_id": self.parent_trace_id,
423
425
  "parent_name": self.parent_name,
@@ -54,7 +54,6 @@ class TraceManagerClient:
54
54
  Returns:
55
55
  dict: Server response containing UI URL and other metadata
56
56
  """
57
- server_response = self.api_client.upsert_trace(trace_data)
58
57
 
59
58
  if self.tracer and self.tracer.use_s3 and final_save:
60
59
  try:
@@ -67,6 +66,11 @@ class TraceManagerClient:
67
66
  except Exception as e:
68
67
  judgeval_logger.warning(f"Failed to save trace to S3: {str(e)}")
69
68
 
69
+ trace_data.pop("trace_spans", None)
70
+ trace_data.pop("evaluation_runs", None)
71
+
72
+ server_response = self.api_client.upsert_trace(trace_data)
73
+
70
74
  if not offline_mode and show_link and "ui_results_url" in server_response:
71
75
  pretty_str = f"\n🔍 You can view your trace data here: [rgb(106,0,255)][link={server_response['ui_results_url']}]View Trace[/link]\n"
72
76
  rprint(pretty_str)
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes