.env.example
LICENSE
MANIFEST.in
README.md
USAGE.md
pyproject.toml
src/data_sampler/__init__.py
src/data_sampler/caching.py
src/data_sampler/config.py
src/data_sampler/env.py
src/data_sampler/kb.py
src/data_sampler/manifest.py
src/data_sampler/pipeline.py
src/data_sampler/py.typed
src/data_sampler/cli/__init__.py
src/data_sampler/cli/build_techqa.py
src/data_sampler/cli/curate.py
src/data_sampler/cli/generate.py
src/data_sampler/cli/run.py
src/data_sampler/cli/score.py
src/data_sampler/cli/split.py
src/data_sampler/core/__init__.py
src/data_sampler/core/paths.py
src/data_sampler/core/data/__init__.py
src/data_sampler/core/data/cleaning.py
src/data_sampler/core/data/config.py
src/data_sampler/core/data/kb_splitter.py
src/data_sampler/core/data/local_kb.py
src/data_sampler/core/data/prompts.py
src/data_sampler/core/data/split.py
src/data_sampler/core/evaluation/__init__.py
src/data_sampler/core/evaluation/silver_cache.py
src/data_sampler/core/evaluation/quality/__init__.py
src/data_sampler/core/evaluation/quality/evaluator.py
src/data_sampler/core/evaluation/quality/metrics.py
src/data_sampler/core/evaluation/quality/reporter.py
src/data_sampler/core/utils/__init__.py
src/data_sampler/core/utils/cost_tracker.py
src/data_sampler/core/utils/formatting.py
src/data_sampler/core/utils/idk.py
src/data_sampler/core/utils/io.py
src/data_sampler/core/utils/llm_clients.py
src/data_sampler/core/utils/local_rag.py
src/data_sampler/core/utils/logging.py
src/data_sampler/curation/__init__.py
src/data_sampler/curation/filtering.py
src/data_sampler/curation/prompts.py
src/data_sampler/curation/quality.py
src/data_sampler/curation/splitting.py
src/data_sampler/generation/__init__.py
src/data_sampler/generation/augment.py
src/data_sampler/generation/fetch.py
src/data_sampler/generation/pipeline.py
src/data_sampler/generation/prompts.py
src/winnow_sampler.egg-info/PKG-INFO
src/winnow_sampler.egg-info/SOURCES.txt
src/winnow_sampler.egg-info/dependency_links.txt
src/winnow_sampler.egg-info/entry_points.txt
src/winnow_sampler.egg-info/requires.txt
src/winnow_sampler.egg-info/top_level.txt
tests/__init__.py
tests/conftest.py
tests/test_cache_invalidation.py
tests/test_caching.py
tests/test_config.py
tests/test_curate_cli.py
tests/test_curation_quality.py
tests/test_dedup.py
tests/test_end_to_end.py
tests/test_env_loading.py
tests/test_failure_reporting.py
tests/test_filtering.py
tests/test_generation_augment.py
tests/test_generation_fetch.py
tests/test_generation_pipeline.py
tests/test_manifest.py
tests/test_pipeline.py
tests/test_schema_preservation.py
tests/test_split_cli.py
tests/test_split_dpo.py
tests/test_splitting.py
tests/fixtures/__init__.py
tests/fixtures/mini_kb.py