datachain 0.6.0__tar.gz → 0.6.2__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.

Potentially problematic release.


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

Files changed (262) hide show
  1. {datachain-0.6.0 → datachain-0.6.2}/.pre-commit-config.yaml +1 -1
  2. {datachain-0.6.0/src/datachain.egg-info → datachain-0.6.2}/PKG-INFO +7 -6
  3. {datachain-0.6.0 → datachain-0.6.2}/pyproject.toml +7 -6
  4. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/__init__.py +2 -0
  5. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/catalog/catalog.py +62 -228
  6. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/cli.py +136 -22
  7. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/client/fsspec.py +9 -0
  8. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/client/local.py +11 -32
  9. datachain-0.6.2/src/datachain/config.py +137 -0
  10. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/data_storage/schema.py +66 -33
  11. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/data_storage/sqlite.py +12 -4
  12. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/data_storage/warehouse.py +101 -129
  13. datachain-0.6.2/src/datachain/lib/convert/sql_to_python.py +14 -0
  14. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/lib/dc.py +275 -80
  15. datachain-0.6.2/src/datachain/lib/func/__init__.py +32 -0
  16. datachain-0.6.2/src/datachain/lib/func/aggregate.py +353 -0
  17. datachain-0.6.2/src/datachain/lib/func/func.py +152 -0
  18. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/lib/listing.py +6 -21
  19. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/lib/listing_info.py +4 -0
  20. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/lib/signal_schema.py +17 -8
  21. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/lib/udf.py +3 -3
  22. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/lib/utils.py +5 -0
  23. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/listing.py +22 -48
  24. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/query/__init__.py +1 -2
  25. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/query/batch.py +0 -1
  26. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/query/dataset.py +33 -46
  27. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/query/schema.py +1 -61
  28. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/query/session.py +33 -25
  29. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/remote/studio.py +63 -14
  30. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/sql/functions/__init__.py +1 -1
  31. datachain-0.6.2/src/datachain/sql/functions/aggregate.py +47 -0
  32. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/sql/functions/array.py +0 -8
  33. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/sql/sqlite/base.py +20 -2
  34. datachain-0.6.2/src/datachain/studio.py +129 -0
  35. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/utils.py +58 -0
  36. {datachain-0.6.0 → datachain-0.6.2/src/datachain.egg-info}/PKG-INFO +7 -6
  37. {datachain-0.6.0 → datachain-0.6.2}/src/datachain.egg-info/SOURCES.txt +8 -0
  38. {datachain-0.6.0 → datachain-0.6.2}/src/datachain.egg-info/requires.txt +6 -7
  39. {datachain-0.6.0 → datachain-0.6.2}/tests/conftest.py +39 -15
  40. {datachain-0.6.0 → datachain-0.6.2}/tests/examples/test_wds_e2e.py +1 -2
  41. {datachain-0.6.0 → datachain-0.6.2}/tests/func/test_catalog.py +71 -57
  42. {datachain-0.6.0 → datachain-0.6.2}/tests/func/test_datachain.py +249 -31
  43. {datachain-0.6.0 → datachain-0.6.2}/tests/func/test_dataset_query.py +5 -39
  44. {datachain-0.6.0 → datachain-0.6.2}/tests/func/test_datasets.py +36 -4
  45. {datachain-0.6.0 → datachain-0.6.2}/tests/func/test_listing.py +2 -10
  46. {datachain-0.6.0 → datachain-0.6.2}/tests/func/test_ls.py +47 -72
  47. {datachain-0.6.0 → datachain-0.6.2}/tests/func/test_pull.py +32 -41
  48. datachain-0.6.2/tests/scripts/feature_class_exception.py +34 -0
  49. {datachain-0.6.0 → datachain-0.6.2}/tests/test_atomicity.py +10 -4
  50. {datachain-0.6.0 → datachain-0.6.2}/tests/test_cli_e2e.py +0 -1
  51. datachain-0.6.2/tests/test_cli_studio.py +120 -0
  52. {datachain-0.6.0 → datachain-0.6.2}/tests/test_query_e2e.py +0 -1
  53. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/lib/test_datachain.py +636 -28
  54. datachain-0.6.2/tests/unit/lib/test_listing_info.py +34 -0
  55. datachain-0.6.2/tests/unit/lib/test_sql_to_python.py +25 -0
  56. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/test_cli_parsing.py +1 -2
  57. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/test_client.py +16 -34
  58. datachain-0.6.2/tests/unit/test_config.py +174 -0
  59. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/test_data_storage.py +30 -40
  60. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/test_listing.py +22 -42
  61. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/test_utils.py +47 -0
  62. {datachain-0.6.0 → datachain-0.6.2}/tests/utils.py +20 -15
  63. datachain-0.6.0/src/datachain/config.py +0 -62
  64. datachain-0.6.0/src/datachain/lib/convert/sql_to_python.py +0 -18
  65. datachain-0.6.0/tests/scripts/feature_class_exception.py +0 -11
  66. datachain-0.6.0/tests/unit/lib/test_sql_to_python.py +0 -28
  67. {datachain-0.6.0 → datachain-0.6.2}/.cruft.json +0 -0
  68. {datachain-0.6.0 → datachain-0.6.2}/.gitattributes +0 -0
  69. {datachain-0.6.0 → datachain-0.6.2}/.github/ISSUE_TEMPLATE/bug_report.yml +0 -0
  70. {datachain-0.6.0 → datachain-0.6.2}/.github/ISSUE_TEMPLATE/empty_issue.md +0 -0
  71. {datachain-0.6.0 → datachain-0.6.2}/.github/ISSUE_TEMPLATE/feature_request.yml +0 -0
  72. {datachain-0.6.0 → datachain-0.6.2}/.github/codecov.yaml +0 -0
  73. {datachain-0.6.0 → datachain-0.6.2}/.github/dependabot.yml +0 -0
  74. {datachain-0.6.0 → datachain-0.6.2}/.github/workflows/benchmarks.yml +0 -0
  75. {datachain-0.6.0 → datachain-0.6.2}/.github/workflows/release.yml +0 -0
  76. {datachain-0.6.0 → datachain-0.6.2}/.github/workflows/tests-studio.yml +0 -0
  77. {datachain-0.6.0 → datachain-0.6.2}/.github/workflows/tests.yml +0 -0
  78. {datachain-0.6.0 → datachain-0.6.2}/.github/workflows/update-template.yaml +0 -0
  79. {datachain-0.6.0 → datachain-0.6.2}/.gitignore +0 -0
  80. {datachain-0.6.0 → datachain-0.6.2}/CODE_OF_CONDUCT.rst +0 -0
  81. {datachain-0.6.0 → datachain-0.6.2}/CONTRIBUTING.rst +0 -0
  82. {datachain-0.6.0 → datachain-0.6.2}/LICENSE +0 -0
  83. {datachain-0.6.0 → datachain-0.6.2}/README.rst +0 -0
  84. {datachain-0.6.0 → datachain-0.6.2}/docs/assets/captioned_cartoons.png +0 -0
  85. {datachain-0.6.0 → datachain-0.6.2}/docs/assets/datachain-white.svg +0 -0
  86. {datachain-0.6.0 → datachain-0.6.2}/docs/assets/datachain.svg +0 -0
  87. {datachain-0.6.0 → datachain-0.6.2}/docs/assets/flowchart.png +0 -0
  88. {datachain-0.6.0 → datachain-0.6.2}/docs/index.md +0 -0
  89. {datachain-0.6.0 → datachain-0.6.2}/docs/references/datachain.md +0 -0
  90. {datachain-0.6.0 → datachain-0.6.2}/docs/references/datatype.md +0 -0
  91. {datachain-0.6.0 → datachain-0.6.2}/docs/references/file.md +0 -0
  92. {datachain-0.6.0 → datachain-0.6.2}/docs/references/index.md +0 -0
  93. {datachain-0.6.0 → datachain-0.6.2}/docs/references/sql.md +0 -0
  94. {datachain-0.6.0 → datachain-0.6.2}/docs/references/torch.md +0 -0
  95. {datachain-0.6.0 → datachain-0.6.2}/docs/references/udf.md +0 -0
  96. {datachain-0.6.0 → datachain-0.6.2}/examples/computer_vision/iptc_exif_xmp_lib.py +0 -0
  97. {datachain-0.6.0 → datachain-0.6.2}/examples/computer_vision/llava2_image_desc_lib.py +0 -0
  98. {datachain-0.6.0 → datachain-0.6.2}/examples/computer_vision/openimage-detect.py +0 -0
  99. {datachain-0.6.0 → datachain-0.6.2}/examples/get_started/common_sql_functions.py +0 -0
  100. {datachain-0.6.0 → datachain-0.6.2}/examples/get_started/json-csv-reader.py +0 -0
  101. {datachain-0.6.0 → datachain-0.6.2}/examples/get_started/torch-loader.py +0 -0
  102. {datachain-0.6.0 → datachain-0.6.2}/examples/get_started/udfs/parallel.py +0 -0
  103. {datachain-0.6.0 → datachain-0.6.2}/examples/get_started/udfs/simple.py +0 -0
  104. {datachain-0.6.0 → datachain-0.6.2}/examples/get_started/udfs/stateful.py +0 -0
  105. {datachain-0.6.0 → datachain-0.6.2}/examples/llm_and_nlp/claude-query.py +0 -0
  106. {datachain-0.6.0 → datachain-0.6.2}/examples/llm_and_nlp/unstructured-embeddings-gen.py +0 -0
  107. {datachain-0.6.0 → datachain-0.6.2}/examples/llm_and_nlp/unstructured-summary-map.py +0 -0
  108. {datachain-0.6.0 → datachain-0.6.2}/examples/multimodal/clip_inference.py +0 -0
  109. {datachain-0.6.0 → datachain-0.6.2}/examples/multimodal/hf_pipeline.py +0 -0
  110. {datachain-0.6.0 → datachain-0.6.2}/examples/multimodal/openai_image_desc_lib.py +0 -0
  111. {datachain-0.6.0 → datachain-0.6.2}/examples/multimodal/wds.py +0 -0
  112. {datachain-0.6.0 → datachain-0.6.2}/examples/multimodal/wds_filtered.py +0 -0
  113. {datachain-0.6.0 → datachain-0.6.2}/mkdocs.yml +0 -0
  114. {datachain-0.6.0 → datachain-0.6.2}/noxfile.py +0 -0
  115. {datachain-0.6.0 → datachain-0.6.2}/overrides/main.html +0 -0
  116. {datachain-0.6.0 → datachain-0.6.2}/setup.cfg +0 -0
  117. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/__main__.py +0 -0
  118. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/asyn.py +0 -0
  119. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/cache.py +0 -0
  120. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/catalog/__init__.py +0 -0
  121. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/catalog/datasource.py +0 -0
  122. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/catalog/loader.py +0 -0
  123. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/cli_utils.py +0 -0
  124. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/client/__init__.py +0 -0
  125. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/client/azure.py +0 -0
  126. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/client/fileslice.py +0 -0
  127. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/client/gcs.py +0 -0
  128. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/client/hf.py +0 -0
  129. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/client/s3.py +0 -0
  130. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/data_storage/__init__.py +0 -0
  131. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/data_storage/db_engine.py +0 -0
  132. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/data_storage/id_generator.py +0 -0
  133. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/data_storage/job.py +0 -0
  134. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/data_storage/metastore.py +0 -0
  135. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/data_storage/serializer.py +0 -0
  136. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/dataset.py +0 -0
  137. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/error.py +0 -0
  138. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/job.py +0 -0
  139. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/lib/__init__.py +0 -0
  140. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/lib/arrow.py +0 -0
  141. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/lib/clip.py +0 -0
  142. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/lib/convert/__init__.py +0 -0
  143. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/lib/convert/flatten.py +0 -0
  144. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/lib/convert/python_to_sql.py +0 -0
  145. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/lib/convert/unflatten.py +0 -0
  146. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/lib/convert/values_to_tuples.py +0 -0
  147. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/lib/data_model.py +0 -0
  148. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/lib/dataset_info.py +0 -0
  149. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/lib/file.py +0 -0
  150. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/lib/hf.py +0 -0
  151. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/lib/image.py +0 -0
  152. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/lib/meta_formats.py +0 -0
  153. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/lib/model_store.py +0 -0
  154. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/lib/pytorch.py +0 -0
  155. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/lib/settings.py +0 -0
  156. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/lib/tar.py +0 -0
  157. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/lib/text.py +0 -0
  158. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/lib/udf_signature.py +0 -0
  159. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/lib/vfile.py +0 -0
  160. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/lib/webdataset.py +0 -0
  161. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/lib/webdataset_laion.py +0 -0
  162. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/node.py +0 -0
  163. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/nodes_fetcher.py +0 -0
  164. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/nodes_thread_pool.py +0 -0
  165. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/progress.py +0 -0
  166. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/py.typed +0 -0
  167. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/query/dispatch.py +0 -0
  168. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/query/metrics.py +0 -0
  169. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/query/params.py +0 -0
  170. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/query/queue.py +0 -0
  171. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/remote/__init__.py +0 -0
  172. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/sql/__init__.py +0 -0
  173. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/sql/default/__init__.py +0 -0
  174. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/sql/default/base.py +0 -0
  175. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/sql/functions/conditional.py +0 -0
  176. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/sql/functions/path.py +0 -0
  177. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/sql/functions/random.py +0 -0
  178. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/sql/functions/string.py +0 -0
  179. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/sql/selectable.py +0 -0
  180. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/sql/sqlite/__init__.py +0 -0
  181. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/sql/sqlite/types.py +0 -0
  182. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/sql/sqlite/vector.py +0 -0
  183. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/sql/types.py +0 -0
  184. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/sql/utils.py +0 -0
  185. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/storage.py +0 -0
  186. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/telemetry.py +0 -0
  187. {datachain-0.6.0 → datachain-0.6.2}/src/datachain/torch/__init__.py +0 -0
  188. {datachain-0.6.0 → datachain-0.6.2}/src/datachain.egg-info/dependency_links.txt +0 -0
  189. {datachain-0.6.0 → datachain-0.6.2}/src/datachain.egg-info/entry_points.txt +0 -0
  190. {datachain-0.6.0 → datachain-0.6.2}/src/datachain.egg-info/top_level.txt +0 -0
  191. {datachain-0.6.0 → datachain-0.6.2}/tests/__init__.py +0 -0
  192. {datachain-0.6.0 → datachain-0.6.2}/tests/benchmarks/__init__.py +0 -0
  193. {datachain-0.6.0 → datachain-0.6.2}/tests/benchmarks/conftest.py +0 -0
  194. {datachain-0.6.0 → datachain-0.6.2}/tests/benchmarks/datasets/.dvc/.gitignore +0 -0
  195. {datachain-0.6.0 → datachain-0.6.2}/tests/benchmarks/datasets/.dvc/config +0 -0
  196. {datachain-0.6.0 → datachain-0.6.2}/tests/benchmarks/datasets/.gitignore +0 -0
  197. {datachain-0.6.0 → datachain-0.6.2}/tests/benchmarks/datasets/laion-tiny.npz.dvc +0 -0
  198. {datachain-0.6.0 → datachain-0.6.2}/tests/benchmarks/test_datachain.py +0 -0
  199. {datachain-0.6.0 → datachain-0.6.2}/tests/benchmarks/test_ls.py +0 -0
  200. {datachain-0.6.0 → datachain-0.6.2}/tests/benchmarks/test_version.py +0 -0
  201. {datachain-0.6.0 → datachain-0.6.2}/tests/data.py +0 -0
  202. {datachain-0.6.0 → datachain-0.6.2}/tests/examples/__init__.py +0 -0
  203. {datachain-0.6.0 → datachain-0.6.2}/tests/examples/test_examples.py +0 -0
  204. {datachain-0.6.0 → datachain-0.6.2}/tests/examples/wds_data.py +0 -0
  205. {datachain-0.6.0 → datachain-0.6.2}/tests/func/__init__.py +0 -0
  206. {datachain-0.6.0 → datachain-0.6.2}/tests/func/test_client.py +0 -0
  207. {datachain-0.6.0 → datachain-0.6.2}/tests/func/test_feature_pickling.py +0 -0
  208. {datachain-0.6.0 → datachain-0.6.2}/tests/func/test_meta_formats.py +0 -0
  209. {datachain-0.6.0 → datachain-0.6.2}/tests/func/test_metrics.py +0 -0
  210. {datachain-0.6.0 → datachain-0.6.2}/tests/func/test_pytorch.py +0 -0
  211. {datachain-0.6.0 → datachain-0.6.2}/tests/func/test_query.py +0 -0
  212. {datachain-0.6.0 → datachain-0.6.2}/tests/scripts/feature_class.py +0 -0
  213. {datachain-0.6.0 → datachain-0.6.2}/tests/scripts/feature_class_parallel.py +0 -0
  214. {datachain-0.6.0 → datachain-0.6.2}/tests/scripts/feature_class_parallel_data_model.py +0 -0
  215. {datachain-0.6.0 → datachain-0.6.2}/tests/scripts/name_len_slow.py +0 -0
  216. {datachain-0.6.0 → datachain-0.6.2}/tests/test_telemetry.py +0 -0
  217. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/__init__.py +0 -0
  218. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/lib/__init__.py +0 -0
  219. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/lib/conftest.py +0 -0
  220. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/lib/test_arrow.py +0 -0
  221. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/lib/test_clip.py +0 -0
  222. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/lib/test_datachain_bootstrap.py +0 -0
  223. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/lib/test_datachain_merge.py +0 -0
  224. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/lib/test_feature.py +0 -0
  225. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/lib/test_feature_utils.py +0 -0
  226. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/lib/test_file.py +0 -0
  227. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/lib/test_hf.py +0 -0
  228. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/lib/test_image.py +0 -0
  229. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/lib/test_schema.py +0 -0
  230. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/lib/test_signal_schema.py +0 -0
  231. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/lib/test_text.py +0 -0
  232. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/lib/test_udf_signature.py +0 -0
  233. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/lib/test_utils.py +0 -0
  234. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/lib/test_webdataset.py +0 -0
  235. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/sql/__init__.py +0 -0
  236. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/sql/sqlite/__init__.py +0 -0
  237. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/sql/sqlite/test_utils.py +0 -0
  238. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/sql/test_array.py +0 -0
  239. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/sql/test_conditional.py +0 -0
  240. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/sql/test_path.py +0 -0
  241. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/sql/test_random.py +0 -0
  242. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/sql/test_selectable.py +0 -0
  243. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/sql/test_string.py +0 -0
  244. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/test_asyn.py +0 -0
  245. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/test_cache.py +0 -0
  246. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/test_catalog.py +0 -0
  247. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/test_catalog_loader.py +0 -0
  248. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/test_client_s3.py +0 -0
  249. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/test_database_engine.py +0 -0
  250. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/test_dataset.py +0 -0
  251. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/test_dispatch.py +0 -0
  252. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/test_fileslice.py +0 -0
  253. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/test_id_generator.py +0 -0
  254. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/test_metastore.py +0 -0
  255. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/test_module_exports.py +0 -0
  256. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/test_query.py +0 -0
  257. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/test_query_metrics.py +0 -0
  258. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/test_query_params.py +0 -0
  259. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/test_serializer.py +0 -0
  260. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/test_session.py +0 -0
  261. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/test_storage.py +0 -0
  262. {datachain-0.6.0 → datachain-0.6.2}/tests/unit/test_warehouse.py +0 -0
@@ -24,7 +24,7 @@ repos:
24
24
  - id: trailing-whitespace
25
25
  exclude: '^LICENSES/'
26
26
  - repo: https://github.com/astral-sh/ruff-pre-commit
27
- rev: 'v0.6.9'
27
+ rev: 'v0.7.0'
28
28
  hooks:
29
29
  - id: ruff
30
30
  args: [--fix, --exit-non-zero-on-fix]
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: datachain
3
- Version: 0.6.0
3
+ Version: 0.6.2
4
4
  Summary: Wrangle unstructured AI data at scale
5
5
  Author-email: Dmitry Petrov <support@dvc.org>
6
6
  License: Apache-2.0
@@ -19,8 +19,7 @@ License-File: LICENSE
19
19
  Requires-Dist: pyyaml
20
20
  Requires-Dist: tomlkit
21
21
  Requires-Dist: tqdm
22
- Requires-Dist: numpy
23
- Requires-Dist: numpy<2,>=1; sys_platform == "win32"
22
+ Requires-Dist: numpy<3,>=1
24
23
  Requires-Dist: pandas>=2.0.0
25
24
  Requires-Dist: pyarrow
26
25
  Requires-Dist: typing-extensions
@@ -39,11 +38,13 @@ Requires-Dist: orjson>=3.10.5
39
38
  Requires-Dist: pydantic<3,>=2
40
39
  Requires-Dist: jmespath>=1.0
41
40
  Requires-Dist: datamodel-code-generator>=0.25
42
- Requires-Dist: Pillow<11,>=10.0.0
41
+ Requires-Dist: Pillow<12,>=10.0.0
43
42
  Requires-Dist: msgpack<2,>=1.0.4
44
43
  Requires-Dist: psutil
45
44
  Requires-Dist: huggingface_hub
46
45
  Requires-Dist: iterative-telemetry>=0.0.9
46
+ Requires-Dist: platformdirs
47
+ Requires-Dist: dvc-studio-client<1,>=0.21
47
48
  Provides-Extra: docs
48
49
  Requires-Dist: mkdocs>=1.5.2; extra == "docs"
49
50
  Requires-Dist: mkdocs-gen-files>=0.5.0; extra == "docs"
@@ -81,7 +82,7 @@ Requires-Dist: requests-mock; extra == "tests"
81
82
  Requires-Dist: scipy; extra == "tests"
82
83
  Provides-Extra: dev
83
84
  Requires-Dist: datachain[docs,tests]; extra == "dev"
84
- Requires-Dist: mypy==1.11.2; extra == "dev"
85
+ Requires-Dist: mypy==1.12.1; extra == "dev"
85
86
  Requires-Dist: types-python-dateutil; extra == "dev"
86
87
  Requires-Dist: types-pytz; extra == "dev"
87
88
  Requires-Dist: types-PyYAML; extra == "dev"
@@ -91,7 +92,7 @@ Requires-Dist: datachain[tests]; extra == "examples"
91
92
  Requires-Dist: numpy<2,>=1; extra == "examples"
92
93
  Requires-Dist: defusedxml; extra == "examples"
93
94
  Requires-Dist: accelerate; extra == "examples"
94
- Requires-Dist: unstructured[embed-huggingface,pdf]; extra == "examples"
95
+ Requires-Dist: unstructured[embed-huggingface,pdf]<0.16.0; extra == "examples"
95
96
  Requires-Dist: pdfplumber==0.11.4; extra == "examples"
96
97
  Requires-Dist: huggingface_hub[hf_transfer]; extra == "examples"
97
98
  Requires-Dist: onnx==1.16.1; extra == "examples"
@@ -22,8 +22,7 @@ dependencies = [
22
22
  "pyyaml",
23
23
  "tomlkit",
24
24
  "tqdm",
25
- "numpy",
26
- 'numpy>=1,<2; sys_platform == "win32"',
25
+ "numpy>=1,<3",
27
26
  "pandas>=2.0.0",
28
27
  "pyarrow",
29
28
  "typing-extensions",
@@ -42,11 +41,13 @@ dependencies = [
42
41
  "pydantic>=2,<3",
43
42
  "jmespath>=1.0",
44
43
  "datamodel-code-generator>=0.25",
45
- "Pillow>=10.0.0,<11",
44
+ "Pillow>=10.0.0,<12",
46
45
  "msgpack>=1.0.4,<2",
47
46
  "psutil",
48
47
  "huggingface_hub",
49
- "iterative-telemetry>=0.0.9"
48
+ "iterative-telemetry>=0.0.9",
49
+ "platformdirs",
50
+ "dvc-studio-client>=0.21,<1"
50
51
  ]
51
52
 
52
53
  [project.optional-dependencies]
@@ -93,7 +94,7 @@ tests = [
93
94
  ]
94
95
  dev = [
95
96
  "datachain[docs,tests]",
96
- "mypy==1.11.2",
97
+ "mypy==1.12.1",
97
98
  "types-python-dateutil",
98
99
  "types-pytz",
99
100
  "types-PyYAML",
@@ -104,7 +105,7 @@ examples = [
104
105
  "numpy>=1,<2",
105
106
  "defusedxml",
106
107
  "accelerate",
107
- "unstructured[pdf, embed-huggingface]",
108
+ "unstructured[pdf,embed-huggingface]<0.16.0",
108
109
  "pdfplumber==0.11.4",
109
110
  "huggingface_hub[hf_transfer]",
110
111
  "onnx==1.16.1"
@@ -1,3 +1,4 @@
1
+ from datachain.lib import func
1
2
  from datachain.lib.data_model import DataModel, DataType, is_chain_type
2
3
  from datachain.lib.dc import C, Column, DataChain, Sys
3
4
  from datachain.lib.file import (
@@ -34,6 +35,7 @@ __all__ = [
34
35
  "Sys",
35
36
  "TarVFile",
36
37
  "TextFile",
38
+ "func",
37
39
  "is_chain_type",
38
40
  "metrics",
39
41
  "param",