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.
- {judgeval-0.0.24 → judgeval-0.0.26}/PKG-INFO +1 -1
- {judgeval-0.0.24 → judgeval-0.0.26}/Pipfile +1 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/Pipfile.lock +1082 -1256
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/classifier_scorer.mdx +17 -4
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/monitoring/introduction.mdx +6 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/monitoring/tracing.mdx +3 -3
- {judgeval-0.0.24 → judgeval-0.0.26}/pyproject.toml +1 -1
- judgeval-0.0.26/src/demo/demo.py +21 -0
- judgeval-0.0.26/src/demo/travel_agent.py +245 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/common/tracer.py +55 -8
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/constants.py +3 -2
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/data/datasets/dataset.py +42 -19
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/integrations/langgraph.py +16 -12
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/judgment_client.py +39 -9
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/rules.py +177 -60
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/run_evaluation.py +140 -103
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/score.py +16 -11
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/utils/alerts.py +32 -1
- {judgeval-0.0.24 → judgeval-0.0.26}/.github/workflows/ci.yaml +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/.gitignore +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/LICENSE.md +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/README.md +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/README.md +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/api_reference/judgment_client.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/api_reference/trace.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/development.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/essentials/code.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/essentials/images.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/essentials/markdown.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/essentials/navigation.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/essentials/reusable-snippets.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/essentials/settings.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/data_datasets.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/data_examples.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/introduction.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/judges.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/answer_correctness.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/answer_relevancy.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/comparison.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/contextual_precision.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/contextual_recall.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/contextual_relevancy.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/custom_scorers.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/execution_order.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/faithfulness.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/groundedness.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/hallucination.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/introduction.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/json_correctness.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/scorers/summarization.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/evaluation/unit_testing.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/favicon.svg +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/getting_started.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/images/basic_trace_example.png +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/images/checks-passed.png +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/images/create_aggressive_scorer.png +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/images/create_scorer.png +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/images/evaluation_diagram.png +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/images/hero-dark.svg +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/images/hero-light.svg +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/images/online_eval_fault.png +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/images/trace_ss.png +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/integration/langgraph.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/introduction.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/judgment/introduction.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/logo/dark.svg +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/logo/light.svg +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/mint.json +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/monitoring/production_insights.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/notebooks/create_dataset.ipynb +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/notebooks/create_scorer.ipynb +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/notebooks/demo.ipynb +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/notebooks/prompt_scorer.ipynb +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/notebooks/quickstart.ipynb +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/quickstart.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/docs/snippets/snippet-intro.mdx +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/pytest.ini +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/__init__.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/clients.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/common/__init__.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/common/exceptions.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/common/logger.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/common/utils.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/data/__init__.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/data/api_example.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/data/datasets/__init__.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/data/datasets/eval_dataset_client.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/data/example.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/data/result.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/data/scorer_data.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/evaluation_run.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/judges/__init__.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/judges/base_judge.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/judges/litellm_judge.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/judges/mixture_of_judges.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/judges/together_judge.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/judges/utils.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/__init__.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/api_scorer.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/base_scorer.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/exceptions.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorer.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/__init__.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/api_scorers/__init__.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/api_scorers/answer_correctness.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/api_scorers/answer_relevancy.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/api_scorers/comparison.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/api_scorers/contextual_precision.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/api_scorers/contextual_recall.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/api_scorers/contextual_relevancy.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/api_scorers/execution_order.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/api_scorers/faithfulness.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/api_scorers/groundedness.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/api_scorers/hallucination.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/api_scorers/instruction_adherence.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/api_scorers/json_correctness.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/api_scorers/summarization.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/classifiers/__init__.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/classifiers/text2sql/__init__.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/classifiers/text2sql/text2sql_scorer.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/__init__.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/answer_correctness/__init__.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/answer_correctness/answer_correctness_scorer.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/answer_correctness/prompts.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/answer_relevancy/__init__.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/answer_relevancy/answer_relevancy_scorer.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/answer_relevancy/prompts.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/comparison/__init__.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/comparison/comparison_scorer.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/comparison/prompts.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/contextual_precision/__init__.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/contextual_precision/contextual_precision_scorer.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/contextual_precision/prompts.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/contextual_recall/__init__.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/contextual_recall/contextual_recall_scorer.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/contextual_recall/prompts.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/contextual_relevancy/__init__.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/contextual_relevancy/contextual_relevancy_scorer.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/contextual_relevancy/prompts.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/execution_order/__init__.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/execution_order/execution_order.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/faithfulness/__init__.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/faithfulness/faithfulness_scorer.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/faithfulness/prompts.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/hallucination/__init__.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/hallucination/hallucination_scorer.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/hallucination/prompts.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/instruction_adherence/instruction_adherence.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/instruction_adherence/prompt.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/json_correctness/__init__.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/json_correctness/json_correctness_scorer.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/summarization/__init__.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/summarization/prompts.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/judgeval_scorers/local_implementations/summarization/summarization_scorer.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/prompt_scorer.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/scorers/utils.py +0 -0
- {judgeval-0.0.24 → judgeval-0.0.26}/src/judgeval/tracer/__init__.py +0 -0