datachain 0.1.12__tar.gz → 0.2.0__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.

Potentially problematic release.


This version of datachain might be problematic. Click here for more details.

Files changed (263) hide show
  1. {datachain-0.1.12 → datachain-0.2.0}/.cruft.json +1 -1
  2. datachain-0.2.0/.github/workflows/docs.yml +34 -0
  3. {datachain-0.1.12 → datachain-0.2.0}/.github/workflows/tests.yml +3 -0
  4. {datachain-0.1.12 → datachain-0.2.0}/.pre-commit-config.yaml +1 -1
  5. {datachain-0.1.12 → datachain-0.2.0}/CONTRIBUTING.rst +20 -0
  6. {datachain-0.1.12/src/datachain.egg-info → datachain-0.2.0}/PKG-INFO +10 -3
  7. datachain-0.2.0/docs/assets/datachain.png +0 -0
  8. datachain-0.2.0/docs/index.md +3 -0
  9. datachain-0.2.0/docs/references/catalog.md +3 -0
  10. datachain-0.2.0/docs/references/datachain.md +3 -0
  11. datachain-0.2.0/examples/computer_vision/fashion_product_images/.gitignore +4 -0
  12. datachain-0.2.0/examples/computer_vision/fashion_product_images/1-quick-start.ipynb +1853 -0
  13. datachain-0.2.0/examples/computer_vision/fashion_product_images/2-working-with-image-datachains.ipynb +3158 -0
  14. datachain-0.2.0/examples/computer_vision/fashion_product_images/README.md +60 -0
  15. datachain-0.2.0/examples/computer_vision/fashion_product_images/requirements.txt +6 -0
  16. datachain-0.2.0/examples/computer_vision/fashion_product_images/scripts/1-quick-start.py +91 -0
  17. datachain-0.2.0/examples/computer_vision/fashion_product_images/scripts/2-basic-operations.py +51 -0
  18. datachain-0.2.0/examples/computer_vision/fashion_product_images/scripts/2-embeddings.py +44 -0
  19. datachain-0.2.0/examples/computer_vision/fashion_product_images/scripts/3-split-train-test.py +46 -0
  20. datachain-0.2.0/examples/computer_vision/fashion_product_images/src/clustering.py +41 -0
  21. datachain-0.2.0/examples/computer_vision/fashion_product_images/static/images/basic-operations.png +0 -0
  22. datachain-0.2.0/examples/computer_vision/fashion_product_images/static/images/core-concepts.png +0 -0
  23. datachain-0.2.0/examples/computer_vision/fashion_product_images/static/images/datachain-logo.png +0 -0
  24. datachain-0.2.0/examples/computer_vision/fashion_product_images/static/images/datachain-overview.png +0 -0
  25. datachain-0.2.0/examples/computer_vision/fashion_product_images/static/images/dataset-1.png +0 -0
  26. datachain-0.2.0/examples/computer_vision/fashion_product_images/static/images/dataset-2.png +0 -0
  27. datachain-0.2.0/examples/computer_vision/fashion_product_images/static/images/dataset-3.png +0 -0
  28. datachain-0.2.0/examples/computer_vision/fashion_product_images/static/images/studio.png +0 -0
  29. {datachain-0.1.12 → datachain-0.2.0}/examples/json-csv-reader.py +40 -8
  30. {datachain-0.1.12 → datachain-0.2.0}/examples/llm-claude-simple-query.py +1 -0
  31. {datachain-0.1.12 → datachain-0.2.0}/examples/udfs/stateful.py +1 -1
  32. {datachain-0.1.12 → datachain-0.2.0}/examples/udfs/stateful_similarity.py +9 -3
  33. {datachain-0.1.12 → datachain-0.2.0}/examples/unstructured-text.py +1 -1
  34. {datachain-0.1.12 → datachain-0.2.0}/examples/wds.py +6 -5
  35. datachain-0.2.0/mkdocs.yml +134 -0
  36. {datachain-0.1.12 → datachain-0.2.0}/noxfile.py +6 -0
  37. {datachain-0.1.12 → datachain-0.2.0}/pyproject.toml +25 -7
  38. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/_version.py +2 -2
  39. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/asyn.py +3 -3
  40. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/catalog/catalog.py +6 -6
  41. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/catalog/loader.py +3 -3
  42. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/cli.py +2 -1
  43. datachain-0.2.0/src/datachain/client/azure.py +66 -0
  44. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/client/fsspec.py +1 -1
  45. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/client/local.py +1 -1
  46. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/data_storage/metastore.py +11 -3
  47. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/data_storage/schema.py +2 -3
  48. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/data_storage/warehouse.py +31 -30
  49. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/dataset.py +1 -3
  50. datachain-0.2.0/src/datachain/lib/arrow.py +85 -0
  51. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/lib/dc.py +377 -178
  52. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/lib/feature.py +41 -90
  53. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/lib/feature_registry.py +3 -1
  54. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/lib/feature_utils.py +2 -2
  55. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/lib/file.py +20 -20
  56. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/lib/image.py +9 -2
  57. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/lib/meta_formats.py +66 -34
  58. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/lib/settings.py +5 -5
  59. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/lib/signal_schema.py +103 -105
  60. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/lib/udf.py +3 -12
  61. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/lib/udf_signature.py +11 -6
  62. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/lib/webdataset_laion.py +5 -22
  63. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/listing.py +8 -8
  64. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/progress.py +1 -1
  65. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/query/builtins.py +1 -1
  66. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/query/dataset.py +39 -110
  67. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/query/dispatch.py +1 -1
  68. datachain-0.2.0/src/datachain/query/metrics.py +19 -0
  69. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/query/schema.py +13 -3
  70. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/utils.py +1 -122
  71. {datachain-0.1.12 → datachain-0.2.0/src/datachain.egg-info}/PKG-INFO +10 -3
  72. {datachain-0.1.12 → datachain-0.2.0}/src/datachain.egg-info/SOURCES.txt +31 -5
  73. {datachain-0.1.12 → datachain-0.2.0}/src/datachain.egg-info/requires.txt +10 -2
  74. {datachain-0.1.12 → datachain-0.2.0}/tests/conftest.py +25 -27
  75. {datachain-0.1.12 → datachain-0.2.0}/tests/func/test_catalog.py +24 -19
  76. {datachain-0.1.12 → datachain-0.2.0}/tests/func/test_client.py +1 -1
  77. datachain-0.2.0/tests/func/test_datachain.py +13 -0
  78. {datachain-0.1.12 → datachain-0.2.0}/tests/func/test_dataset_query.py +15 -107
  79. {datachain-0.1.12 → datachain-0.2.0}/tests/func/test_datasets.py +4 -12
  80. {datachain-0.1.12 → datachain-0.2.0}/tests/func/test_pytorch.py +3 -8
  81. {datachain-0.1.12 → datachain-0.2.0}/tests/func/test_query.py +66 -34
  82. {datachain-0.1.12 → datachain-0.2.0}/tests/scripts/feature_class_parallel.py +7 -1
  83. {datachain-0.1.12 → datachain-0.2.0}/tests/test_cli_e2e.py +2 -2
  84. {datachain-0.1.12 → datachain-0.2.0}/tests/test_query_e2e.py +2 -2
  85. datachain-0.2.0/tests/unit/lib/test_arrow.py +110 -0
  86. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/lib/test_datachain.py +190 -21
  87. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/lib/test_datachain_merge.py +1 -1
  88. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/lib/test_feature.py +15 -313
  89. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/lib/test_feature_utils.py +13 -2
  90. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/lib/test_file.py +20 -0
  91. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/lib/test_signal_schema.py +73 -24
  92. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/lib/test_udf_signature.py +0 -4
  93. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/test_client_s3.py +4 -4
  94. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/test_id_generator.py +2 -2
  95. datachain-0.2.0/tests/unit/test_query_metrics.py +29 -0
  96. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/test_storage.py +2 -2
  97. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/test_utils.py +0 -57
  98. {datachain-0.1.12 → datachain-0.2.0}/tests/utils.py +1 -16
  99. datachain-0.1.12/examples/dir_expansion.py +0 -69
  100. datachain-0.1.12/src/datachain/client/azure.py +0 -30
  101. datachain-0.1.12/src/datachain/lib/parquet.py +0 -32
  102. datachain-0.1.12/tests/unit/lib/test_parquet.py +0 -33
  103. {datachain-0.1.12 → datachain-0.2.0}/.gitattributes +0 -0
  104. {datachain-0.1.12 → datachain-0.2.0}/.github/ISSUE_TEMPLATE/bug_report.yml +0 -0
  105. {datachain-0.1.12 → datachain-0.2.0}/.github/ISSUE_TEMPLATE/empty_issue.md +0 -0
  106. {datachain-0.1.12 → datachain-0.2.0}/.github/ISSUE_TEMPLATE/feature_request.yml +0 -0
  107. {datachain-0.1.12 → datachain-0.2.0}/.github/codecov.yaml +0 -0
  108. {datachain-0.1.12 → datachain-0.2.0}/.github/dependabot.yml +0 -0
  109. {datachain-0.1.12 → datachain-0.2.0}/.github/workflows/benchmarks.yml +0 -0
  110. {datachain-0.1.12 → datachain-0.2.0}/.github/workflows/release.yml +0 -0
  111. {datachain-0.1.12 → datachain-0.2.0}/.github/workflows/update-template.yaml +0 -0
  112. {datachain-0.1.12 → datachain-0.2.0}/.gitignore +0 -0
  113. {datachain-0.1.12 → datachain-0.2.0}/.reuse/dep5 +0 -0
  114. {datachain-0.1.12 → datachain-0.2.0}/CODE_OF_CONDUCT.rst +0 -0
  115. {datachain-0.1.12 → datachain-0.2.0}/LICENSE +0 -0
  116. {datachain-0.1.12 → datachain-0.2.0}/LICENSES/Apache-2.0.txt +0 -0
  117. {datachain-0.1.12 → datachain-0.2.0}/LICENSES/BSD-3-Clause.txt +0 -0
  118. {datachain-0.1.12 → datachain-0.2.0}/LICENSES/Python-2.0.txt +0 -0
  119. {datachain-0.1.12 → datachain-0.2.0}/README.rst +0 -0
  120. {datachain-0.1.12/docs → datachain-0.2.0/docs/tutorials}/cv_intro.md +0 -0
  121. {datachain-0.1.12/docs → datachain-0.2.0/docs/tutorials}/udfs.md +0 -0
  122. {datachain-0.1.12 → datachain-0.2.0}/examples/blip2_image_desc_lib.py +0 -0
  123. {datachain-0.1.12 → datachain-0.2.0}/examples/clip.py +0 -0
  124. {datachain-0.1.12 → datachain-0.2.0}/examples/common_sql_functions.py +0 -0
  125. {datachain-0.1.12 → datachain-0.2.0}/examples/hf_pipeline.py +0 -0
  126. {datachain-0.1.12 → datachain-0.2.0}/examples/iptc_exif_xmp_lib.py +0 -0
  127. {datachain-0.1.12 → datachain-0.2.0}/examples/llava2_image_desc_lib.py +0 -0
  128. {datachain-0.1.12 → datachain-0.2.0}/examples/llm-claude-aggregate-query.py +0 -0
  129. {datachain-0.1.12 → datachain-0.2.0}/examples/llm-claude.py +0 -0
  130. {datachain-0.1.12 → datachain-0.2.0}/examples/loader.py +0 -0
  131. {datachain-0.1.12 → datachain-0.2.0}/examples/neurips/README +0 -0
  132. {datachain-0.1.12 → datachain-0.2.0}/examples/neurips/distance_to_query.py +0 -0
  133. {datachain-0.1.12 → datachain-0.2.0}/examples/neurips/llm_chat.py +0 -0
  134. {datachain-0.1.12 → datachain-0.2.0}/examples/neurips/requirements.txt +0 -0
  135. {datachain-0.1.12 → datachain-0.2.0}/examples/neurips/single_query.py +0 -0
  136. {datachain-0.1.12 → datachain-0.2.0}/examples/neurips/text_loaders.py +0 -0
  137. {datachain-0.1.12 → datachain-0.2.0}/examples/notebooks/clip_fine_tuning.ipynb +0 -0
  138. {datachain-0.1.12 → datachain-0.2.0}/examples/openai_image_desc_lib.py +0 -0
  139. {datachain-0.1.12 → datachain-0.2.0}/examples/openimage-detect.py +0 -0
  140. {datachain-0.1.12 → datachain-0.2.0}/examples/pose_detection.py +0 -0
  141. {datachain-0.1.12 → datachain-0.2.0}/examples/torch-loader.py +0 -0
  142. {datachain-0.1.12 → datachain-0.2.0}/examples/udfs/batching.py +0 -0
  143. {datachain-0.1.12 → datachain-0.2.0}/examples/udfs/image_transformation.py +0 -0
  144. {datachain-0.1.12 → datachain-0.2.0}/examples/udfs/parallel.py +0 -0
  145. {datachain-0.1.12 → datachain-0.2.0}/examples/udfs/simple.py +0 -0
  146. {datachain-0.1.12 → datachain-0.2.0}/examples/wds_filtered.py +0 -0
  147. {datachain-0.1.12 → datachain-0.2.0}/examples/zalando/zalando_clip.py +0 -0
  148. {datachain-0.1.12 → datachain-0.2.0}/examples/zalando/zalando_dir_as_class.py +0 -0
  149. {datachain-0.1.12 → datachain-0.2.0}/examples/zalando/zalando_splits_and_classes_ds.py +0 -0
  150. {datachain-0.1.12 → datachain-0.2.0}/examples/zalando/zalando_splits_and_classes_output.py +0 -0
  151. {datachain-0.1.12 → datachain-0.2.0}/setup.cfg +0 -0
  152. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/__init__.py +0 -0
  153. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/__main__.py +0 -0
  154. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/cache.py +0 -0
  155. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/catalog/__init__.py +3 -3
  156. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/catalog/datasource.py +0 -0
  157. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/catalog/subclass.py +0 -0
  158. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/cli_utils.py +0 -0
  159. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/client/__init__.py +0 -0
  160. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/client/fileslice.py +0 -0
  161. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/client/gcs.py +0 -0
  162. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/client/s3.py +0 -0
  163. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/config.py +0 -0
  164. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/data_storage/__init__.py +1 -1
  165. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/data_storage/db_engine.py +0 -0
  166. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/data_storage/id_generator.py +0 -0
  167. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/data_storage/job.py +0 -0
  168. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/data_storage/serializer.py +0 -0
  169. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/data_storage/sqlite.py +0 -0
  170. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/error.py +0 -0
  171. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/lib/__init__.py +0 -0
  172. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/lib/cached_stream.py +0 -0
  173. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/lib/claude.py +0 -0
  174. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/lib/gpt4_vision.py +0 -0
  175. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/lib/hf_image_to_text.py +0 -0
  176. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/lib/hf_pipeline.py +0 -0
  177. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/lib/image_transform.py +0 -0
  178. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/lib/iptc_exif_xmp.py +0 -0
  179. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/lib/pytorch.py +0 -0
  180. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/lib/reader.py +0 -0
  181. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/lib/text.py +0 -0
  182. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/lib/unstructured.py +0 -0
  183. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/lib/utils.py +0 -0
  184. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/lib/vfile.py +0 -0
  185. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/lib/webdataset.py +0 -0
  186. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/node.py +1 -1
  187. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/nodes_fetcher.py +0 -0
  188. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/nodes_thread_pool.py +0 -0
  189. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/py.typed +0 -0
  190. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/query/__init__.py +0 -0
  191. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/query/batch.py +0 -0
  192. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/query/params.py +0 -0
  193. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/query/session.py +0 -0
  194. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/query/udf.py +0 -0
  195. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/remote/__init__.py +0 -0
  196. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/remote/studio.py +0 -0
  197. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/sql/__init__.py +1 -1
  198. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/sql/default/__init__.py +0 -0
  199. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/sql/default/base.py +0 -0
  200. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/sql/functions/__init__.py +0 -0
  201. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/sql/functions/array.py +0 -0
  202. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/sql/functions/conditional.py +0 -0
  203. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/sql/functions/path.py +0 -0
  204. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/sql/functions/random.py +0 -0
  205. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/sql/functions/string.py +0 -0
  206. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/sql/selectable.py +0 -0
  207. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/sql/sqlite/__init__.py +0 -0
  208. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/sql/sqlite/base.py +0 -0
  209. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/sql/sqlite/types.py +0 -0
  210. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/sql/sqlite/vector.py +0 -0
  211. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/sql/types.py +0 -0
  212. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/sql/utils.py +0 -0
  213. {datachain-0.1.12 → datachain-0.2.0}/src/datachain/storage.py +0 -0
  214. {datachain-0.1.12 → datachain-0.2.0}/src/datachain.egg-info/dependency_links.txt +0 -0
  215. {datachain-0.1.12 → datachain-0.2.0}/src/datachain.egg-info/entry_points.txt +0 -0
  216. {datachain-0.1.12 → datachain-0.2.0}/src/datachain.egg-info/top_level.txt +0 -0
  217. {datachain-0.1.12 → datachain-0.2.0}/tests/__init__.py +0 -0
  218. {datachain-0.1.12 → datachain-0.2.0}/tests/benchmarks/__init__.py +0 -0
  219. {datachain-0.1.12 → datachain-0.2.0}/tests/benchmarks/conftest.py +0 -0
  220. {datachain-0.1.12 → datachain-0.2.0}/tests/benchmarks/test_ls.py +0 -0
  221. {datachain-0.1.12 → datachain-0.2.0}/tests/benchmarks/test_version.py +0 -0
  222. {datachain-0.1.12 → datachain-0.2.0}/tests/data.py +0 -0
  223. {datachain-0.1.12 → datachain-0.2.0}/tests/func/__init__.py +0 -0
  224. {datachain-0.1.12 → datachain-0.2.0}/tests/func/test_ls.py +0 -0
  225. {datachain-0.1.12 → datachain-0.2.0}/tests/func/test_pull.py +0 -0
  226. {datachain-0.1.12 → datachain-0.2.0}/tests/scripts/feature_class.py +0 -0
  227. {datachain-0.1.12 → datachain-0.2.0}/tests/scripts/name_len_normal.py +0 -0
  228. {datachain-0.1.12 → datachain-0.2.0}/tests/scripts/name_len_slow.py +0 -0
  229. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/__init__.py +0 -0
  230. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/lib/__init__.py +0 -0
  231. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/lib/test_cached_stream.py +0 -0
  232. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/lib/test_image.py +0 -0
  233. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/lib/test_reader.py +0 -0
  234. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/lib/test_text.py +0 -0
  235. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/lib/test_utils.py +0 -0
  236. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/lib/test_webdataset.py +0 -0
  237. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/sql/__init__.py +0 -0
  238. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/sql/sqlite/__init__.py +0 -0
  239. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/sql/sqlite/test_utils.py +0 -0
  240. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/sql/test_array.py +0 -0
  241. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/sql/test_conditional.py +0 -0
  242. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/sql/test_path.py +0 -0
  243. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/sql/test_random.py +0 -0
  244. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/sql/test_selectable.py +0 -0
  245. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/sql/test_string.py +0 -0
  246. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/test_asyn.py +0 -0
  247. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/test_cache.py +0 -0
  248. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/test_catalog.py +0 -0
  249. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/test_catalog_loader.py +0 -0
  250. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/test_cli_parsing.py +0 -0
  251. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/test_client.py +0 -0
  252. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/test_data_storage.py +0 -0
  253. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/test_database_engine.py +0 -0
  254. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/test_dataset.py +1 -1
  255. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/test_dispatch.py +0 -0
  256. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/test_fileslice.py +0 -0
  257. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/test_listing.py +0 -0
  258. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/test_metastore.py +0 -0
  259. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/test_query_params.py +0 -0
  260. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/test_serializer.py +0 -0
  261. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/test_session.py +0 -0
  262. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/test_udf.py +0 -0
  263. {datachain-0.1.12 → datachain-0.2.0}/tests/unit/test_warehouse.py +0 -0
@@ -13,7 +13,7 @@
13
13
  "version": "0.0.0",
14
14
  "copyright_year": "2022",
15
15
  "license": "Apache-2.0",
16
- "docs": "False",
16
+ "docs": true,
17
17
  "short_description": "Wrangle unstructured AI data at scale",
18
18
  "development_status": "Development Status :: 2 - Pre-Alpha",
19
19
  "_template": "https://github.com/iterative/py-template"
@@ -0,0 +1,34 @@
1
+ name: Documentation
2
+
3
+ on:
4
+ push:
5
+ branches: [main]
6
+ workflow_dispatch:
7
+
8
+ jobs:
9
+ docs:
10
+ runs-on: ubuntu-latest
11
+ steps:
12
+ - name: Check out the repository
13
+ uses: actions/checkout@v4
14
+ with:
15
+ fetch-depth: 0
16
+
17
+ - name: Set up Python
18
+ uses: actions/setup-python@v5
19
+ with:
20
+ python-version: '3.12'
21
+ cache: 'pip'
22
+
23
+ - name: Install uv
24
+ run: python -m pip install --upgrade uv
25
+
26
+ - name: Configure git
27
+ run: |
28
+ git config user.name 'github-actions[bot]'
29
+ git config user.email 'github-actions[bot]@users.noreply.github.com'
30
+
31
+ - name: Publish docs
32
+ run: |
33
+ uv pip install '.[docs]' --system
34
+ mkdocs gh-deploy
@@ -122,3 +122,6 @@ jobs:
122
122
 
123
123
  - name: Build package
124
124
  run: nox -s build
125
+
126
+ - name: Build docs
127
+ run: nox -s docs
@@ -21,7 +21,7 @@ repos:
21
21
  - id: trailing-whitespace
22
22
  exclude: '^LICENSES/'
23
23
  - repo: https://github.com/astral-sh/ruff-pre-commit
24
- rev: 'v0.4.9'
24
+ rev: 'v0.5.0'
25
25
  hooks:
26
26
  - id: ruff
27
27
  args: [--fix, --exit-non-zero-on-fix]
@@ -8,11 +8,13 @@ welcomes contributions in the form of bug reports, feature requests, and pull re
8
8
  Here is a list of important resources for contributors:
9
9
 
10
10
  - `Source Code`_
11
+ - `Documentation`_
11
12
  - `Issue Tracker`_
12
13
  - `Code of Conduct`_
13
14
 
14
15
  .. _Apache 2.0 license: https://opensource.org/licenses/Apache-2.0
15
16
  .. _Source Code: https://github.com/iterative/dvcx
17
+ .. _Documentation: https://docs.dvc.ai/datachain
16
18
  .. _Issue Tracker: https://github.com/iterative/dvcx/issues
17
19
 
18
20
  How to report a bug
@@ -82,6 +84,24 @@ and are written using the pytest_ testing framework.
82
84
  .. _pytest: https://pytest.readthedocs.io/
83
85
 
84
86
 
87
+ Build documentation
88
+ -------------------
89
+
90
+ If you've made any changes to the documentation (including changes to function signatures,
91
+ class definitions, or docstrings that will appear in the API documentation),
92
+ make sure it builds successfully.
93
+
94
+ .. code:: console
95
+
96
+ $ nox -s docs
97
+
98
+ In order to run this locally with hot reload on changes:
99
+
100
+ .. code:: console
101
+
102
+ $ mkdocs serve
103
+
104
+
85
105
  How to submit changes
86
106
  ---------------------
87
107
 
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: datachain
3
- Version: 0.1.12
3
+ Version: 0.2.0
4
4
  Summary: Wrangle unstructured AI data at scale
5
5
  Author-email: Dmitry Petrov <support@dvc.org>
6
6
  License: Apache-2.0
@@ -38,6 +38,13 @@ Requires-Dist: ujson>=5.9.0
38
38
  Requires-Dist: pydantic<3,>=2
39
39
  Requires-Dist: jmespath>=1.0
40
40
  Requires-Dist: datamodel-code-generator>=0.25
41
+ Provides-Extra: docs
42
+ Requires-Dist: mkdocs>=1.5.2; extra == "docs"
43
+ Requires-Dist: mkdocs-gen-files>=0.5.0; extra == "docs"
44
+ Requires-Dist: mkdocs-material>=9.3.1; extra == "docs"
45
+ Requires-Dist: mkdocs-section-index>=0.3.6; extra == "docs"
46
+ Requires-Dist: mkdocstrings-python>=1.6.3; extra == "docs"
47
+ Requires-Dist: mkdocs-literate-nav>=0.6.1; extra == "docs"
41
48
  Provides-Extra: cv
42
49
  Requires-Dist: Pillow<11,>=10.0.0; extra == "cv"
43
50
  Requires-Dist: torch>=2.1.0; extra == "cv"
@@ -67,8 +74,8 @@ Requires-Dist: open_clip_torch; extra == "tests"
67
74
  Requires-Dist: aiotools>=1.7.0; extra == "tests"
68
75
  Requires-Dist: requests-mock; extra == "tests"
69
76
  Provides-Extra: dev
70
- Requires-Dist: datachain[tests]; extra == "dev"
71
- Requires-Dist: mypy==1.10.0; extra == "dev"
77
+ Requires-Dist: datachain[docs,tests]; extra == "dev"
78
+ Requires-Dist: mypy==1.10.1; extra == "dev"
72
79
  Requires-Dist: types-python-dateutil; extra == "dev"
73
80
  Requires-Dist: types-PyYAML; extra == "dev"
74
81
  Requires-Dist: types-requests; extra == "dev"
@@ -0,0 +1,3 @@
1
+ # Welcome to DataChain
2
+
3
+ - [API Reference](./references/datachain.md)
@@ -0,0 +1,3 @@
1
+ # `Catalog`
2
+
3
+ ::: datachain.catalog.Catalog
@@ -0,0 +1,3 @@
1
+ # `DataChain`
2
+
3
+ ::: datachain.lib.dc.DataChain
@@ -0,0 +1,4 @@
1
+ .datachain
2
+ data
3
+ dev
4
+ test-notebooks.sh