.gitignore
.pre-commit-config.yaml
README.md
environment-dev.yml
mkdocs.yml
pyproject.toml
.github/workflows/build_docs.yml
.github/workflows/publish_docs.yml
.github/workflows/release_pypi.yaml
.github/workflows/tests.yml
docs/index.md
docs/installation.md
docs/quickstart.md
docs/welcome.md
docs/api/cli.md
docs/api/core.md
docs/api/datasets.md
docs/api/evaluators.md
docs/api/index.md
docs/api/interactive.md
docs/api/metrics.md
docs/api/model-providers.md
docs/api/models.md
docs/api/plugin.md
docs/api/providers.md
docs/api/runners.md
docs/api/sessions.md
docs/api/storage.md
docs/assets/images/dotevals-logo-dark.svg
docs/assets/images/dotevals-logo-light.svg
docs/assets/images/dotevals.svg
docs/assets/images/dottxt-dark.svg
docs/assets/images/dottxt-light.svg
docs/assets/images/use_philosophy.png
docs/concepts/core-terminology.md
docs/explanation/control-plane-architecture.md
docs/explanation/design-principles.md
docs/explanation/index.md
docs/explanation/plugin-architecture.md
docs/how-to/batch-inference-local-models.md
docs/how-to/index.md
docs/how-to/model-provider-pattern.md
docs/how-to/plugins/create-dataset-plugin.md
docs/how-to/plugins/create-evaluator-plugin.md
docs/how-to/plugins/create-metrics-plugin.md
docs/how-to/plugins/create-model-provider-plugin.md
docs/how-to/plugins/create-storage-plugin.md
docs/reference/batch.md
docs/reference/cli.md
docs/reference/concurrency.md
docs/reference/datasets.md
docs/reference/evaluators.md
docs/reference/experiments.md
docs/reference/foreach.md
docs/reference/index.md
docs/reference/interactive.md
docs/reference/metrics.md
docs/reference/plugin-entry-points.md
docs/reference/plugins.md
docs/reference/pytest-mode.md
docs/reference/pytest.md
docs/reference/storage.md
docs/stylesheets/extra.css
docs/tutorials/01-your-first-evaluation.md
docs/tutorials/02-using-real-models.md
docs/tutorials/03-working-with-real-datasets.md
docs/tutorials/04-building-custom-evaluators.md
docs/tutorials/05-scale-with-async-evaluation.md
docs/tutorials/06-pytest-fixtures-and-resource-pooling.md
docs/tutorials/07-comparing-multiple-models.md
docs/tutorials/08-build-production-evaluation-pipeline.md
docs/tutorials/index.md
examples/bfcl.py
examples/gpqa.py
examples/gsm8k.py
examples/sroie.py
src/dotevals/__init__.py
src/dotevals/_version.py
src/dotevals/cli.py
src/dotevals/decorators.py
src/dotevals/exceptions.py
src/dotevals/fixtures.py
src/dotevals/interactive.py
src/dotevals/models.py
src/dotevals/plugin.py
src/dotevals/progress.py
src/dotevals/providers.py
src/dotevals/retry.py
src/dotevals/runners.py
src/dotevals/sessions.py
src/dotevals/utils.py
src/dotevals.egg-info/PKG-INFO
src/dotevals.egg-info/SOURCES.txt
src/dotevals.egg-info/dependency_links.txt
src/dotevals.egg-info/entry_points.txt
src/dotevals.egg-info/requires.txt
src/dotevals.egg-info/top_level.txt
src/dotevals/concurrency/__init__.py
src/dotevals/concurrency/adaptive.py
src/dotevals/concurrency/async_sequential.py
src/dotevals/concurrency/sequential.py
src/dotevals/concurrency/sliding_window.py
src/dotevals/datasets/__init__.py
src/dotevals/datasets/base.py
src/dotevals/evaluators/__init__.py
src/dotevals/evaluators/ast_evaluation.py
src/dotevals/evaluators/base.py
src/dotevals/evaluators/registry.py
src/dotevals/executors/__init__.py
src/dotevals/executors/base.py
src/dotevals/executors/batch.py
src/dotevals/executors/executor.py
src/dotevals/executors/foreach.py
src/dotevals/executors/registry.py
src/dotevals/metrics/__init__.py
src/dotevals/metrics/base.py
src/dotevals/metrics/registry.py
src/dotevals/storage/__init__.py
src/dotevals/storage/base.py
src/dotevals/storage/json.py
tests/__init__.py
tests/test_async_plugin.py
tests/test_cli.py
tests/test_datasets.py
tests/test_decorators.py
tests/test_error_handling.py
tests/test_error_metrics.py
tests/test_evaluation_resumption.py
tests/test_exceptions.py
tests/test_experiment_manager.py
tests/test_fixtures.py
tests/test_fixtures_integration.py
tests/test_foreach_registry.py
tests/test_foreach_strategies.py
tests/test_integration.py
tests/test_interactive.py
tests/test_json_storage.py
tests/test_models.py
tests/test_plugin.py
tests/test_plugin_internals.py
tests/test_providers.py
tests/test_retry.py
tests/test_retry_logic.py
tests/test_runners.py
tests/test_sessions.py
tests/test_storage.py
tests/test_utils.py
tests/utils.py
tests/concurrency/__init__.py
tests/concurrency/test_adaptive.py
tests/concurrency/test_async_sequential.py
tests/concurrency/test_sequential.py
tests/concurrency/test_sliding_window.py
tests/evaluators/__init__.py
tests/evaluators/test_evaluator_plugins.py
tests/evaluators/test_evaluators.py
tests/executors/test_batch.py
tests/executors/test_foreach.py
tests/metrics/__init__.py
tests/metrics/test_metrics.py
tests/metrics/test_metrics_init.py
tests/metrics/test_metrics_registry.py