nucliadb 2.46.1.post382__py3-none-any.whl → 6.2.1.post2777__py3-none-any.whl

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.
Files changed (431) hide show
  1. migrations/0002_rollover_shards.py +1 -2
  2. migrations/0003_allfields_key.py +2 -37
  3. migrations/0004_rollover_shards.py +1 -2
  4. migrations/0005_rollover_shards.py +1 -2
  5. migrations/0006_rollover_shards.py +2 -4
  6. migrations/0008_cleanup_leftover_rollover_metadata.py +1 -2
  7. migrations/0009_upgrade_relations_and_texts_to_v2.py +5 -4
  8. migrations/0010_fix_corrupt_indexes.py +11 -12
  9. migrations/0011_materialize_labelset_ids.py +2 -18
  10. migrations/0012_rollover_shards.py +6 -12
  11. migrations/0013_rollover_shards.py +2 -4
  12. migrations/0014_rollover_shards.py +5 -7
  13. migrations/0015_targeted_rollover.py +6 -12
  14. migrations/0016_upgrade_to_paragraphs_v2.py +27 -32
  15. migrations/0017_multiple_writable_shards.py +3 -6
  16. migrations/0018_purge_orphan_kbslugs.py +59 -0
  17. migrations/0019_upgrade_to_paragraphs_v3.py +66 -0
  18. migrations/0020_drain_nodes_from_cluster.py +83 -0
  19. nucliadb/standalone/tests/unit/test_run.py → migrations/0021_overwrite_vectorsets_key.py +17 -18
  20. nucliadb/tests/unit/test_openapi.py → migrations/0022_fix_paragraph_deletion_bug.py +16 -11
  21. migrations/0023_backfill_pg_catalog.py +80 -0
  22. migrations/0025_assign_models_to_kbs_v2.py +113 -0
  23. migrations/0026_fix_high_cardinality_content_types.py +61 -0
  24. migrations/0027_rollover_texts3.py +73 -0
  25. nucliadb/ingest/fields/date.py → migrations/pg/0001_bootstrap.py +10 -12
  26. migrations/pg/0002_catalog.py +42 -0
  27. nucliadb/ingest/tests/unit/test_settings.py → migrations/pg/0003_catalog_kbid_index.py +5 -3
  28. nucliadb/common/cluster/base.py +41 -24
  29. nucliadb/common/cluster/discovery/base.py +6 -14
  30. nucliadb/common/cluster/discovery/k8s.py +9 -19
  31. nucliadb/common/cluster/discovery/manual.py +1 -3
  32. nucliadb/common/cluster/discovery/single.py +1 -2
  33. nucliadb/common/cluster/discovery/utils.py +1 -3
  34. nucliadb/common/cluster/grpc_node_dummy.py +11 -16
  35. nucliadb/common/cluster/index_node.py +10 -19
  36. nucliadb/common/cluster/manager.py +223 -102
  37. nucliadb/common/cluster/rebalance.py +42 -37
  38. nucliadb/common/cluster/rollover.py +377 -204
  39. nucliadb/common/cluster/settings.py +16 -9
  40. nucliadb/common/cluster/standalone/grpc_node_binding.py +24 -76
  41. nucliadb/common/cluster/standalone/index_node.py +4 -11
  42. nucliadb/common/cluster/standalone/service.py +2 -6
  43. nucliadb/common/cluster/standalone/utils.py +9 -6
  44. nucliadb/common/cluster/utils.py +43 -29
  45. nucliadb/common/constants.py +20 -0
  46. nucliadb/common/context/__init__.py +6 -4
  47. nucliadb/common/context/fastapi.py +8 -5
  48. nucliadb/{tests/knowledgeboxes/__init__.py → common/counters.py} +8 -2
  49. nucliadb/common/datamanagers/__init__.py +24 -5
  50. nucliadb/common/datamanagers/atomic.py +102 -0
  51. nucliadb/common/datamanagers/cluster.py +5 -5
  52. nucliadb/common/datamanagers/entities.py +6 -16
  53. nucliadb/common/datamanagers/fields.py +84 -0
  54. nucliadb/common/datamanagers/kb.py +101 -24
  55. nucliadb/common/datamanagers/labels.py +26 -56
  56. nucliadb/common/datamanagers/processing.py +2 -6
  57. nucliadb/common/datamanagers/resources.py +214 -117
  58. nucliadb/common/datamanagers/rollover.py +77 -16
  59. nucliadb/{ingest/orm → common/datamanagers}/synonyms.py +16 -28
  60. nucliadb/common/datamanagers/utils.py +19 -11
  61. nucliadb/common/datamanagers/vectorsets.py +110 -0
  62. nucliadb/common/external_index_providers/base.py +257 -0
  63. nucliadb/{ingest/tests/unit/test_cache.py → common/external_index_providers/exceptions.py} +9 -8
  64. nucliadb/common/external_index_providers/manager.py +101 -0
  65. nucliadb/common/external_index_providers/pinecone.py +933 -0
  66. nucliadb/common/external_index_providers/settings.py +52 -0
  67. nucliadb/common/http_clients/auth.py +3 -6
  68. nucliadb/common/http_clients/processing.py +6 -11
  69. nucliadb/common/http_clients/utils.py +1 -3
  70. nucliadb/common/ids.py +240 -0
  71. nucliadb/common/locking.py +43 -13
  72. nucliadb/common/maindb/driver.py +11 -35
  73. nucliadb/common/maindb/exceptions.py +6 -6
  74. nucliadb/common/maindb/local.py +22 -9
  75. nucliadb/common/maindb/pg.py +206 -111
  76. nucliadb/common/maindb/utils.py +13 -44
  77. nucliadb/common/models_utils/from_proto.py +479 -0
  78. nucliadb/common/models_utils/to_proto.py +60 -0
  79. nucliadb/common/nidx.py +260 -0
  80. nucliadb/export_import/datamanager.py +25 -19
  81. nucliadb/export_import/exceptions.py +8 -0
  82. nucliadb/export_import/exporter.py +20 -7
  83. nucliadb/export_import/importer.py +6 -11
  84. nucliadb/export_import/models.py +5 -5
  85. nucliadb/export_import/tasks.py +4 -4
  86. nucliadb/export_import/utils.py +94 -54
  87. nucliadb/health.py +1 -3
  88. nucliadb/ingest/app.py +15 -11
  89. nucliadb/ingest/consumer/auditing.py +30 -147
  90. nucliadb/ingest/consumer/consumer.py +96 -52
  91. nucliadb/ingest/consumer/materializer.py +10 -12
  92. nucliadb/ingest/consumer/pull.py +12 -27
  93. nucliadb/ingest/consumer/service.py +20 -19
  94. nucliadb/ingest/consumer/shard_creator.py +7 -14
  95. nucliadb/ingest/consumer/utils.py +1 -3
  96. nucliadb/ingest/fields/base.py +139 -188
  97. nucliadb/ingest/fields/conversation.py +18 -5
  98. nucliadb/ingest/fields/exceptions.py +1 -4
  99. nucliadb/ingest/fields/file.py +7 -25
  100. nucliadb/ingest/fields/link.py +11 -16
  101. nucliadb/ingest/fields/text.py +9 -4
  102. nucliadb/ingest/orm/brain.py +255 -262
  103. nucliadb/ingest/orm/broker_message.py +181 -0
  104. nucliadb/ingest/orm/entities.py +36 -51
  105. nucliadb/ingest/orm/exceptions.py +12 -0
  106. nucliadb/ingest/orm/knowledgebox.py +334 -278
  107. nucliadb/ingest/orm/processor/__init__.py +2 -697
  108. nucliadb/ingest/orm/processor/auditing.py +117 -0
  109. nucliadb/ingest/orm/processor/data_augmentation.py +164 -0
  110. nucliadb/ingest/orm/processor/pgcatalog.py +84 -0
  111. nucliadb/ingest/orm/processor/processor.py +752 -0
  112. nucliadb/ingest/orm/processor/sequence_manager.py +1 -1
  113. nucliadb/ingest/orm/resource.py +280 -520
  114. nucliadb/ingest/orm/utils.py +25 -31
  115. nucliadb/ingest/partitions.py +3 -9
  116. nucliadb/ingest/processing.py +76 -81
  117. nucliadb/ingest/py.typed +0 -0
  118. nucliadb/ingest/serialize.py +37 -173
  119. nucliadb/ingest/service/__init__.py +1 -3
  120. nucliadb/ingest/service/writer.py +186 -577
  121. nucliadb/ingest/settings.py +13 -22
  122. nucliadb/ingest/utils.py +3 -6
  123. nucliadb/learning_proxy.py +264 -51
  124. nucliadb/metrics_exporter.py +30 -19
  125. nucliadb/middleware/__init__.py +1 -3
  126. nucliadb/migrator/command.py +1 -3
  127. nucliadb/migrator/datamanager.py +13 -13
  128. nucliadb/migrator/migrator.py +57 -37
  129. nucliadb/migrator/settings.py +2 -1
  130. nucliadb/migrator/utils.py +18 -10
  131. nucliadb/purge/__init__.py +139 -33
  132. nucliadb/purge/orphan_shards.py +7 -13
  133. nucliadb/reader/__init__.py +1 -3
  134. nucliadb/reader/api/models.py +3 -14
  135. nucliadb/reader/api/v1/__init__.py +0 -1
  136. nucliadb/reader/api/v1/download.py +27 -94
  137. nucliadb/reader/api/v1/export_import.py +4 -4
  138. nucliadb/reader/api/v1/knowledgebox.py +13 -13
  139. nucliadb/reader/api/v1/learning_config.py +8 -12
  140. nucliadb/reader/api/v1/resource.py +67 -93
  141. nucliadb/reader/api/v1/services.py +70 -125
  142. nucliadb/reader/app.py +16 -46
  143. nucliadb/reader/lifecycle.py +18 -4
  144. nucliadb/reader/py.typed +0 -0
  145. nucliadb/reader/reader/notifications.py +10 -31
  146. nucliadb/search/__init__.py +1 -3
  147. nucliadb/search/api/v1/__init__.py +2 -2
  148. nucliadb/search/api/v1/ask.py +112 -0
  149. nucliadb/search/api/v1/catalog.py +184 -0
  150. nucliadb/search/api/v1/feedback.py +17 -25
  151. nucliadb/search/api/v1/find.py +41 -41
  152. nucliadb/search/api/v1/knowledgebox.py +90 -62
  153. nucliadb/search/api/v1/predict_proxy.py +2 -2
  154. nucliadb/search/api/v1/resource/ask.py +66 -117
  155. nucliadb/search/api/v1/resource/search.py +51 -72
  156. nucliadb/search/api/v1/router.py +1 -0
  157. nucliadb/search/api/v1/search.py +50 -197
  158. nucliadb/search/api/v1/suggest.py +40 -54
  159. nucliadb/search/api/v1/summarize.py +9 -5
  160. nucliadb/search/api/v1/utils.py +2 -1
  161. nucliadb/search/app.py +16 -48
  162. nucliadb/search/lifecycle.py +10 -3
  163. nucliadb/search/predict.py +176 -188
  164. nucliadb/search/py.typed +0 -0
  165. nucliadb/search/requesters/utils.py +41 -63
  166. nucliadb/search/search/cache.py +149 -20
  167. nucliadb/search/search/chat/ask.py +918 -0
  168. nucliadb/search/{tests/unit/test_run.py → search/chat/exceptions.py} +14 -13
  169. nucliadb/search/search/chat/images.py +41 -17
  170. nucliadb/search/search/chat/prompt.py +851 -282
  171. nucliadb/search/search/chat/query.py +274 -267
  172. nucliadb/{writer/resource/slug.py → search/search/cut.py} +8 -6
  173. nucliadb/search/search/fetch.py +43 -36
  174. nucliadb/search/search/filters.py +9 -15
  175. nucliadb/search/search/find.py +214 -54
  176. nucliadb/search/search/find_merge.py +408 -391
  177. nucliadb/search/search/hydrator.py +191 -0
  178. nucliadb/search/search/merge.py +198 -234
  179. nucliadb/search/search/metrics.py +73 -2
  180. nucliadb/search/search/paragraphs.py +64 -106
  181. nucliadb/search/search/pgcatalog.py +233 -0
  182. nucliadb/search/search/predict_proxy.py +1 -1
  183. nucliadb/search/search/query.py +386 -257
  184. nucliadb/search/search/query_parser/exceptions.py +22 -0
  185. nucliadb/search/search/query_parser/models.py +101 -0
  186. nucliadb/search/search/query_parser/parser.py +183 -0
  187. nucliadb/search/search/rank_fusion.py +204 -0
  188. nucliadb/search/search/rerankers.py +270 -0
  189. nucliadb/search/search/shards.py +4 -38
  190. nucliadb/search/search/summarize.py +14 -18
  191. nucliadb/search/search/utils.py +27 -4
  192. nucliadb/search/settings.py +15 -1
  193. nucliadb/standalone/api_router.py +4 -10
  194. nucliadb/standalone/app.py +17 -14
  195. nucliadb/standalone/auth.py +7 -21
  196. nucliadb/standalone/config.py +9 -12
  197. nucliadb/standalone/introspect.py +5 -5
  198. nucliadb/standalone/lifecycle.py +26 -25
  199. nucliadb/standalone/migrations.py +58 -0
  200. nucliadb/standalone/purge.py +9 -8
  201. nucliadb/standalone/py.typed +0 -0
  202. nucliadb/standalone/run.py +25 -18
  203. nucliadb/standalone/settings.py +10 -14
  204. nucliadb/standalone/versions.py +15 -5
  205. nucliadb/tasks/consumer.py +8 -12
  206. nucliadb/tasks/producer.py +7 -6
  207. nucliadb/tests/config.py +53 -0
  208. nucliadb/train/__init__.py +1 -3
  209. nucliadb/train/api/utils.py +1 -2
  210. nucliadb/train/api/v1/shards.py +2 -2
  211. nucliadb/train/api/v1/trainset.py +4 -6
  212. nucliadb/train/app.py +14 -47
  213. nucliadb/train/generator.py +10 -19
  214. nucliadb/train/generators/field_classifier.py +7 -19
  215. nucliadb/train/generators/field_streaming.py +156 -0
  216. nucliadb/train/generators/image_classifier.py +12 -18
  217. nucliadb/train/generators/paragraph_classifier.py +5 -9
  218. nucliadb/train/generators/paragraph_streaming.py +6 -9
  219. nucliadb/train/generators/question_answer_streaming.py +19 -20
  220. nucliadb/train/generators/sentence_classifier.py +9 -15
  221. nucliadb/train/generators/token_classifier.py +45 -36
  222. nucliadb/train/generators/utils.py +14 -18
  223. nucliadb/train/lifecycle.py +7 -3
  224. nucliadb/train/nodes.py +23 -32
  225. nucliadb/train/py.typed +0 -0
  226. nucliadb/train/servicer.py +13 -21
  227. nucliadb/train/settings.py +2 -6
  228. nucliadb/train/types.py +13 -10
  229. nucliadb/train/upload.py +3 -6
  230. nucliadb/train/uploader.py +20 -25
  231. nucliadb/train/utils.py +1 -1
  232. nucliadb/writer/__init__.py +1 -3
  233. nucliadb/writer/api/constants.py +0 -5
  234. nucliadb/{ingest/fields/keywordset.py → writer/api/utils.py} +13 -10
  235. nucliadb/writer/api/v1/export_import.py +102 -49
  236. nucliadb/writer/api/v1/field.py +196 -620
  237. nucliadb/writer/api/v1/knowledgebox.py +221 -71
  238. nucliadb/writer/api/v1/learning_config.py +2 -2
  239. nucliadb/writer/api/v1/resource.py +114 -216
  240. nucliadb/writer/api/v1/services.py +64 -132
  241. nucliadb/writer/api/v1/slug.py +61 -0
  242. nucliadb/writer/api/v1/transaction.py +67 -0
  243. nucliadb/writer/api/v1/upload.py +184 -215
  244. nucliadb/writer/app.py +11 -61
  245. nucliadb/writer/back_pressure.py +62 -43
  246. nucliadb/writer/exceptions.py +0 -4
  247. nucliadb/writer/lifecycle.py +21 -15
  248. nucliadb/writer/py.typed +0 -0
  249. nucliadb/writer/resource/audit.py +2 -1
  250. nucliadb/writer/resource/basic.py +48 -62
  251. nucliadb/writer/resource/field.py +45 -135
  252. nucliadb/writer/resource/origin.py +1 -2
  253. nucliadb/writer/settings.py +14 -5
  254. nucliadb/writer/tus/__init__.py +17 -15
  255. nucliadb/writer/tus/azure.py +111 -0
  256. nucliadb/writer/tus/dm.py +17 -5
  257. nucliadb/writer/tus/exceptions.py +1 -3
  258. nucliadb/writer/tus/gcs.py +56 -84
  259. nucliadb/writer/tus/local.py +21 -37
  260. nucliadb/writer/tus/s3.py +28 -68
  261. nucliadb/writer/tus/storage.py +5 -56
  262. nucliadb/writer/vectorsets.py +125 -0
  263. nucliadb-6.2.1.post2777.dist-info/METADATA +148 -0
  264. nucliadb-6.2.1.post2777.dist-info/RECORD +343 -0
  265. {nucliadb-2.46.1.post382.dist-info → nucliadb-6.2.1.post2777.dist-info}/WHEEL +1 -1
  266. nucliadb/common/maindb/redis.py +0 -194
  267. nucliadb/common/maindb/tikv.py +0 -412
  268. nucliadb/ingest/fields/layout.py +0 -58
  269. nucliadb/ingest/tests/conftest.py +0 -30
  270. nucliadb/ingest/tests/fixtures.py +0 -771
  271. nucliadb/ingest/tests/integration/consumer/__init__.py +0 -18
  272. nucliadb/ingest/tests/integration/consumer/test_auditing.py +0 -80
  273. nucliadb/ingest/tests/integration/consumer/test_materializer.py +0 -89
  274. nucliadb/ingest/tests/integration/consumer/test_pull.py +0 -144
  275. nucliadb/ingest/tests/integration/consumer/test_service.py +0 -81
  276. nucliadb/ingest/tests/integration/consumer/test_shard_creator.py +0 -68
  277. nucliadb/ingest/tests/integration/ingest/test_ingest.py +0 -691
  278. nucliadb/ingest/tests/integration/ingest/test_processing_engine.py +0 -95
  279. nucliadb/ingest/tests/integration/ingest/test_relations.py +0 -272
  280. nucliadb/ingest/tests/unit/consumer/__init__.py +0 -18
  281. nucliadb/ingest/tests/unit/consumer/test_auditing.py +0 -140
  282. nucliadb/ingest/tests/unit/consumer/test_consumer.py +0 -69
  283. nucliadb/ingest/tests/unit/consumer/test_pull.py +0 -60
  284. nucliadb/ingest/tests/unit/consumer/test_shard_creator.py +0 -139
  285. nucliadb/ingest/tests/unit/consumer/test_utils.py +0 -67
  286. nucliadb/ingest/tests/unit/orm/__init__.py +0 -19
  287. nucliadb/ingest/tests/unit/orm/test_brain.py +0 -247
  288. nucliadb/ingest/tests/unit/orm/test_processor.py +0 -131
  289. nucliadb/ingest/tests/unit/orm/test_resource.py +0 -275
  290. nucliadb/ingest/tests/unit/test_partitions.py +0 -40
  291. nucliadb/ingest/tests/unit/test_processing.py +0 -171
  292. nucliadb/middleware/transaction.py +0 -117
  293. nucliadb/reader/api/v1/learning_collector.py +0 -63
  294. nucliadb/reader/tests/__init__.py +0 -19
  295. nucliadb/reader/tests/conftest.py +0 -31
  296. nucliadb/reader/tests/fixtures.py +0 -136
  297. nucliadb/reader/tests/test_list_resources.py +0 -75
  298. nucliadb/reader/tests/test_reader_file_download.py +0 -273
  299. nucliadb/reader/tests/test_reader_resource.py +0 -379
  300. nucliadb/reader/tests/test_reader_resource_field.py +0 -219
  301. nucliadb/search/api/v1/chat.py +0 -258
  302. nucliadb/search/api/v1/resource/chat.py +0 -94
  303. nucliadb/search/tests/__init__.py +0 -19
  304. nucliadb/search/tests/conftest.py +0 -33
  305. nucliadb/search/tests/fixtures.py +0 -199
  306. nucliadb/search/tests/node.py +0 -465
  307. nucliadb/search/tests/unit/__init__.py +0 -18
  308. nucliadb/search/tests/unit/api/__init__.py +0 -19
  309. nucliadb/search/tests/unit/api/v1/__init__.py +0 -19
  310. nucliadb/search/tests/unit/api/v1/resource/__init__.py +0 -19
  311. nucliadb/search/tests/unit/api/v1/resource/test_ask.py +0 -67
  312. nucliadb/search/tests/unit/api/v1/resource/test_chat.py +0 -97
  313. nucliadb/search/tests/unit/api/v1/test_chat.py +0 -96
  314. nucliadb/search/tests/unit/api/v1/test_predict_proxy.py +0 -98
  315. nucliadb/search/tests/unit/api/v1/test_summarize.py +0 -93
  316. nucliadb/search/tests/unit/search/__init__.py +0 -18
  317. nucliadb/search/tests/unit/search/requesters/__init__.py +0 -18
  318. nucliadb/search/tests/unit/search/requesters/test_utils.py +0 -210
  319. nucliadb/search/tests/unit/search/search/__init__.py +0 -19
  320. nucliadb/search/tests/unit/search/search/test_shards.py +0 -45
  321. nucliadb/search/tests/unit/search/search/test_utils.py +0 -82
  322. nucliadb/search/tests/unit/search/test_chat_prompt.py +0 -266
  323. nucliadb/search/tests/unit/search/test_fetch.py +0 -108
  324. nucliadb/search/tests/unit/search/test_filters.py +0 -125
  325. nucliadb/search/tests/unit/search/test_paragraphs.py +0 -157
  326. nucliadb/search/tests/unit/search/test_predict_proxy.py +0 -106
  327. nucliadb/search/tests/unit/search/test_query.py +0 -201
  328. nucliadb/search/tests/unit/test_app.py +0 -79
  329. nucliadb/search/tests/unit/test_find_merge.py +0 -112
  330. nucliadb/search/tests/unit/test_merge.py +0 -34
  331. nucliadb/search/tests/unit/test_predict.py +0 -584
  332. nucliadb/standalone/tests/__init__.py +0 -19
  333. nucliadb/standalone/tests/conftest.py +0 -33
  334. nucliadb/standalone/tests/fixtures.py +0 -38
  335. nucliadb/standalone/tests/unit/__init__.py +0 -18
  336. nucliadb/standalone/tests/unit/test_api_router.py +0 -61
  337. nucliadb/standalone/tests/unit/test_auth.py +0 -169
  338. nucliadb/standalone/tests/unit/test_introspect.py +0 -35
  339. nucliadb/standalone/tests/unit/test_versions.py +0 -68
  340. nucliadb/tests/benchmarks/__init__.py +0 -19
  341. nucliadb/tests/benchmarks/test_search.py +0 -99
  342. nucliadb/tests/conftest.py +0 -32
  343. nucliadb/tests/fixtures.py +0 -736
  344. nucliadb/tests/knowledgeboxes/philosophy_books.py +0 -203
  345. nucliadb/tests/knowledgeboxes/ten_dummy_resources.py +0 -109
  346. nucliadb/tests/migrations/__init__.py +0 -19
  347. nucliadb/tests/migrations/test_migration_0017.py +0 -80
  348. nucliadb/tests/tikv.py +0 -240
  349. nucliadb/tests/unit/__init__.py +0 -19
  350. nucliadb/tests/unit/common/__init__.py +0 -19
  351. nucliadb/tests/unit/common/cluster/__init__.py +0 -19
  352. nucliadb/tests/unit/common/cluster/discovery/__init__.py +0 -19
  353. nucliadb/tests/unit/common/cluster/discovery/test_k8s.py +0 -170
  354. nucliadb/tests/unit/common/cluster/standalone/__init__.py +0 -18
  355. nucliadb/tests/unit/common/cluster/standalone/test_service.py +0 -113
  356. nucliadb/tests/unit/common/cluster/standalone/test_utils.py +0 -59
  357. nucliadb/tests/unit/common/cluster/test_cluster.py +0 -399
  358. nucliadb/tests/unit/common/cluster/test_kb_shard_manager.py +0 -178
  359. nucliadb/tests/unit/common/cluster/test_rollover.py +0 -279
  360. nucliadb/tests/unit/common/maindb/__init__.py +0 -18
  361. nucliadb/tests/unit/common/maindb/test_driver.py +0 -127
  362. nucliadb/tests/unit/common/maindb/test_tikv.py +0 -53
  363. nucliadb/tests/unit/common/maindb/test_utils.py +0 -81
  364. nucliadb/tests/unit/common/test_context.py +0 -36
  365. nucliadb/tests/unit/export_import/__init__.py +0 -19
  366. nucliadb/tests/unit/export_import/test_datamanager.py +0 -37
  367. nucliadb/tests/unit/export_import/test_utils.py +0 -294
  368. nucliadb/tests/unit/migrator/__init__.py +0 -19
  369. nucliadb/tests/unit/migrator/test_migrator.py +0 -87
  370. nucliadb/tests/unit/tasks/__init__.py +0 -19
  371. nucliadb/tests/unit/tasks/conftest.py +0 -42
  372. nucliadb/tests/unit/tasks/test_consumer.py +0 -93
  373. nucliadb/tests/unit/tasks/test_producer.py +0 -95
  374. nucliadb/tests/unit/tasks/test_tasks.py +0 -60
  375. nucliadb/tests/unit/test_field_ids.py +0 -49
  376. nucliadb/tests/unit/test_health.py +0 -84
  377. nucliadb/tests/unit/test_kb_slugs.py +0 -54
  378. nucliadb/tests/unit/test_learning_proxy.py +0 -252
  379. nucliadb/tests/unit/test_metrics_exporter.py +0 -77
  380. nucliadb/tests/unit/test_purge.py +0 -138
  381. nucliadb/tests/utils/__init__.py +0 -74
  382. nucliadb/tests/utils/aiohttp_session.py +0 -44
  383. nucliadb/tests/utils/broker_messages/__init__.py +0 -167
  384. nucliadb/tests/utils/broker_messages/fields.py +0 -181
  385. nucliadb/tests/utils/broker_messages/helpers.py +0 -33
  386. nucliadb/tests/utils/entities.py +0 -78
  387. nucliadb/train/api/v1/check.py +0 -60
  388. nucliadb/train/tests/__init__.py +0 -19
  389. nucliadb/train/tests/conftest.py +0 -29
  390. nucliadb/train/tests/fixtures.py +0 -342
  391. nucliadb/train/tests/test_field_classification.py +0 -122
  392. nucliadb/train/tests/test_get_entities.py +0 -80
  393. nucliadb/train/tests/test_get_info.py +0 -51
  394. nucliadb/train/tests/test_get_ontology.py +0 -34
  395. nucliadb/train/tests/test_get_ontology_count.py +0 -63
  396. nucliadb/train/tests/test_image_classification.py +0 -222
  397. nucliadb/train/tests/test_list_fields.py +0 -39
  398. nucliadb/train/tests/test_list_paragraphs.py +0 -73
  399. nucliadb/train/tests/test_list_resources.py +0 -39
  400. nucliadb/train/tests/test_list_sentences.py +0 -71
  401. nucliadb/train/tests/test_paragraph_classification.py +0 -123
  402. nucliadb/train/tests/test_paragraph_streaming.py +0 -118
  403. nucliadb/train/tests/test_question_answer_streaming.py +0 -239
  404. nucliadb/train/tests/test_sentence_classification.py +0 -143
  405. nucliadb/train/tests/test_token_classification.py +0 -136
  406. nucliadb/train/tests/utils.py +0 -108
  407. nucliadb/writer/layouts/__init__.py +0 -51
  408. nucliadb/writer/layouts/v1.py +0 -59
  409. nucliadb/writer/resource/vectors.py +0 -120
  410. nucliadb/writer/tests/__init__.py +0 -19
  411. nucliadb/writer/tests/conftest.py +0 -31
  412. nucliadb/writer/tests/fixtures.py +0 -192
  413. nucliadb/writer/tests/test_fields.py +0 -486
  414. nucliadb/writer/tests/test_files.py +0 -743
  415. nucliadb/writer/tests/test_knowledgebox.py +0 -49
  416. nucliadb/writer/tests/test_reprocess_file_field.py +0 -139
  417. nucliadb/writer/tests/test_resources.py +0 -546
  418. nucliadb/writer/tests/test_service.py +0 -137
  419. nucliadb/writer/tests/test_tus.py +0 -203
  420. nucliadb/writer/tests/utils.py +0 -35
  421. nucliadb/writer/tus/pg.py +0 -125
  422. nucliadb-2.46.1.post382.dist-info/METADATA +0 -134
  423. nucliadb-2.46.1.post382.dist-info/RECORD +0 -451
  424. {nucliadb/ingest/tests → migrations/pg}/__init__.py +0 -0
  425. /nucliadb/{ingest/tests/integration → common/external_index_providers}/__init__.py +0 -0
  426. /nucliadb/{ingest/tests/integration/ingest → common/models_utils}/__init__.py +0 -0
  427. /nucliadb/{ingest/tests/unit → search/search/query_parser}/__init__.py +0 -0
  428. /nucliadb/{ingest/tests → tests}/vectors.py +0 -0
  429. {nucliadb-2.46.1.post382.dist-info → nucliadb-6.2.1.post2777.dist-info}/entry_points.txt +0 -0
  430. {nucliadb-2.46.1.post382.dist-info → nucliadb-6.2.1.post2777.dist-info}/top_level.txt +0 -0
  431. {nucliadb-2.46.1.post382.dist-info → nucliadb-6.2.1.post2777.dist-info}/zip-safe +0 -0
@@ -1,19 +0,0 @@
1
- # Copyright (C) 2021 Bosutech XXI S.L.
2
- #
3
- # nucliadb is offered under the AGPL v3.0 and as commercial software.
4
- # For commercial licensing, contact us at info@nuclia.com.
5
- #
6
- # AGPL:
7
- # This program is free software: you can redistribute it and/or modify
8
- # it under the terms of the GNU Affero General Public License as
9
- # published by the Free Software Foundation, either version 3 of the
10
- # License, or (at your option) any later version.
11
- #
12
- # This program is distributed in the hope that it will be useful,
13
- # but WITHOUT ANY WARRANTY; without even the implied warranty of
14
- # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
15
- # GNU Affero General Public License for more details.
16
- #
17
- # You should have received a copy of the GNU Affero General Public License
18
- # along with this program. If not, see <http://www.gnu.org/licenses/>.
19
- #
@@ -1,19 +0,0 @@
1
- # Copyright (C) 2021 Bosutech XXI S.L.
2
- #
3
- # nucliadb is offered under the AGPL v3.0 and as commercial software.
4
- # For commercial licensing, contact us at info@nuclia.com.
5
- #
6
- # AGPL:
7
- # This program is free software: you can redistribute it and/or modify
8
- # it under the terms of the GNU Affero General Public License as
9
- # published by the Free Software Foundation, either version 3 of the
10
- # License, or (at your option) any later version.
11
- #
12
- # This program is distributed in the hope that it will be useful,
13
- # but WITHOUT ANY WARRANTY; without even the implied warranty of
14
- # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
15
- # GNU Affero General Public License for more details.
16
- #
17
- # You should have received a copy of the GNU Affero General Public License
18
- # along with this program. If not, see <http://www.gnu.org/licenses/>.
19
- #
@@ -1,170 +0,0 @@
1
- # Copyright (C) 2021 Bosutech XXI S.L.
2
- #
3
- # nucliadb is offered under the AGPL v3.0 and as commercial software.
4
- # For commercial licensing, contact us at info@nuclia.com.
5
- #
6
- # AGPL:
7
- # This program is free software: you can redistribute it and/or modify
8
- # it under the terms of the GNU Affero General Public License as
9
- # published by the Free Software Foundation, either version 3 of the
10
- # License, or (at your option) any later version.
11
- #
12
- # This program is distributed in the hope that it will be useful,
13
- # but WITHOUT ANY WARRANTY; without even the implied warranty of
14
- # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
15
- # GNU Affero General Public License for more details.
16
- #
17
- # You should have received a copy of the GNU Affero General Public License
18
- # along with this program. If not, see <http://www.gnu.org/licenses/>.
19
- #
20
- import asyncio
21
- import time
22
- from unittest.mock import ANY, AsyncMock, MagicMock, patch
23
-
24
- import kubernetes_asyncio.client.models.v1_container_status # type: ignore
25
- import kubernetes_asyncio.client.models.v1_object_meta # type: ignore
26
- import kubernetes_asyncio.client.models.v1_pod # type: ignore
27
- import kubernetes_asyncio.client.models.v1_pod_status # type: ignore
28
- import pytest
29
-
30
- from nucliadb.common.cluster import manager
31
- from nucliadb.common.cluster.discovery.k8s import EventType, KubernetesDiscovery
32
- from nucliadb.common.cluster.discovery.types import IndexNodeMetadata
33
- from nucliadb.common.cluster.settings import Settings
34
- from nucliadb_protos import nodewriter_pb2
35
-
36
- pytestmark = pytest.mark.asyncio
37
-
38
-
39
- @pytest.fixture()
40
- def writer_stub():
41
- writer_stub = MagicMock()
42
- writer_stub.GetMetadata = AsyncMock(
43
- return_value=nodewriter_pb2.NodeMetadata(
44
- node_id="node_id", shard_count=1, available_disk=10, total_disk=10
45
- )
46
- )
47
- with patch(
48
- "nucliadb.common.cluster.discovery.base.nodewriter_pb2_grpc.NodeWriterStub",
49
- return_value=writer_stub,
50
- ), patch(
51
- "nucliadb.common.cluster.discovery.base.replication_pb2_grpc.ReplicationServiceStub",
52
- return_value=writer_stub,
53
- ), patch(
54
- "nucliadb.common.cluster.discovery.base.get_traced_grpc_channel"
55
- ):
56
- yield writer_stub
57
-
58
-
59
- @pytest.fixture()
60
- def k8s_discovery(writer_stub):
61
- disc = KubernetesDiscovery(Settings())
62
- disc.node_heartbeat_interval = 0.1
63
- manager.INDEX_NODES.clear()
64
- yield disc
65
- manager.INDEX_NODES.clear()
66
-
67
-
68
- def create_k8s_event(
69
- type_: str = "ADDED",
70
- name: str = "node-0",
71
- container_name="reader",
72
- ready: bool = True,
73
- ) -> EventType:
74
- return {
75
- "type": type_,
76
- "object": kubernetes_asyncio.client.models.v1_pod.V1Pod(
77
- status=kubernetes_asyncio.client.models.v1_pod_status.V1PodStatus(
78
- container_statuses=[
79
- kubernetes_asyncio.client.models.v1_container_status.V1ContainerStatus(
80
- name=container_name,
81
- ready=ready,
82
- image="image",
83
- image_id="image_id",
84
- restart_count=0,
85
- )
86
- ],
87
- pod_ip="1.2.3.4",
88
- ),
89
- metadata=kubernetes_asyncio.client.models.v1_object_meta.V1ObjectMeta(
90
- name=name, labels={"readReplica": "false"}
91
- ),
92
- ),
93
- }
94
-
95
-
96
- async def test_get_node_metadata(k8s_discovery: KubernetesDiscovery, writer_stub):
97
- assert await k8s_discovery.get_node_metadata(
98
- "node-0", "1.1.1.1", read_replica=False
99
- ) == IndexNodeMetadata(
100
- node_id="node_id",
101
- shard_count=1,
102
- name="node_id",
103
- address="1.1.1.1",
104
- updated_at=ANY,
105
- available_disk=10,
106
- )
107
-
108
- writer_stub.GetMetadata.assert_awaited_once()
109
-
110
- # should be cached now
111
- await k8s_discovery.get_node_metadata("node-0", "1.1.1.1", read_replica=False)
112
-
113
- assert len(writer_stub.GetMetadata.mock_calls) == 1
114
-
115
-
116
- async def test_update_node(k8s_discovery: KubernetesDiscovery):
117
- await k8s_discovery.update_node(create_k8s_event())
118
- assert len(manager.INDEX_NODES) == 1
119
-
120
- # update again
121
- await k8s_discovery.update_node(create_k8s_event())
122
- assert len(manager.INDEX_NODES) == 1
123
-
124
-
125
- async def test_remove_node(k8s_discovery: KubernetesDiscovery):
126
- await k8s_discovery.update_node(create_k8s_event())
127
-
128
- assert len(manager.INDEX_NODES) == 1
129
-
130
- await k8s_discovery.update_node(create_k8s_event(ready=False))
131
-
132
- assert len(manager.INDEX_NODES) == 0
133
-
134
-
135
- async def test_update_node_data_cache(k8s_discovery: KubernetesDiscovery, writer_stub):
136
- await k8s_discovery.update_node(create_k8s_event())
137
-
138
- task = asyncio.create_task(k8s_discovery.update_node_data_cache())
139
-
140
- await asyncio.sleep(k8s_discovery.node_heartbeat_interval + 0.1)
141
-
142
- task.cancel()
143
-
144
- assert len(writer_stub.GetMetadata.mock_calls) == 2
145
-
146
-
147
- async def test_remove_stale_nodes(k8s_discovery: KubernetesDiscovery):
148
- manager.add_index_node(
149
- id="node_id",
150
- address="1.1.1.1",
151
- shard_count=1,
152
- available_disk=100,
153
- )
154
- nmd = IndexNodeMetadata(
155
- node_id="node_id",
156
- shard_count=1,
157
- available_disk=100,
158
- name="node_id",
159
- address="1.1.1.1",
160
- updated_at=time.time() - k8s_discovery.node_heartbeat_interval * 3,
161
- )
162
- k8s_discovery.node_id_cache["node_id"] = nmd
163
-
164
- assert len(k8s_discovery.node_id_cache) == 1
165
- assert len(manager.get_index_nodes()) == 1
166
-
167
- k8s_discovery._maybe_remove_stale_node("node_id")
168
-
169
- assert len(k8s_discovery.node_id_cache) == 0
170
- assert len(manager.get_index_nodes()) == 0
@@ -1,18 +0,0 @@
1
- # Copyright (C) 2021 Bosutech XXI S.L.
2
- #
3
- # nucliadb is offered under the AGPL v3.0 and as commercial software.
4
- # For commercial licensing, contact us at info@nuclia.com.
5
- #
6
- # AGPL:
7
- # This program is free software: you can redistribute it and/or modify
8
- # it under the terms of the GNU Affero General Public License as
9
- # published by the Free Software Foundation, either version 3 of the
10
- # License, or (at your option) any later version.
11
- #
12
- # This program is distributed in the hope that it will be useful,
13
- # but WITHOUT ANY WARRANTY; without even the implied warranty of
14
- # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
15
- # GNU Affero General Public License for more details.
16
- #
17
- # You should have received a copy of the GNU Affero General Public License
18
- # along with this program. If not, see <http://www.gnu.org/licenses/>.
@@ -1,113 +0,0 @@
1
- # Copyright (C) 2021 Bosutech XXI S.L.
2
- #
3
- # nucliadb is offered under the AGPL v3.0 and as commercial software.
4
- # For commercial licensing, contact us at info@nuclia.com.
5
- #
6
- # AGPL:
7
- # This program is free software: you can redistribute it and/or modify
8
- # it under the terms of the GNU Affero General Public License as
9
- # published by the Free Software Foundation, either version 3 of the
10
- # License, or (at your option) any later version.
11
- #
12
- # This program is distributed in the hope that it will be useful,
13
- # but WITHOUT ANY WARRANTY; without even the implied warranty of
14
- # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
15
- # GNU Affero General Public License for more details.
16
- #
17
- # You should have received a copy of the GNU Affero General Public License
18
- # along with this program. If not, see <http://www.gnu.org/licenses/>.
19
- #
20
- import os
21
- import tempfile
22
- from unittest.mock import AsyncMock, MagicMock, patch
23
-
24
- import pytest
25
- from nucliadb_protos.noderesources_pb2 import ShardId
26
- from nucliadb_protos.utils_pb2 import RelationNode
27
-
28
- from nucliadb.common.cluster.settings import Settings
29
- from nucliadb.common.cluster.standalone import service
30
- from nucliadb_protos import nodereader_pb2, standalone_pb2
31
-
32
- pytestmark = pytest.mark.asyncio
33
-
34
-
35
- @pytest.fixture
36
- def cluster_settings():
37
- settings = Settings()
38
- with patch(
39
- "nucliadb.common.cluster.standalone.service.cluster_settings", settings
40
- ), tempfile.TemporaryDirectory() as tmpdir:
41
- settings.data_path = tmpdir
42
- os.makedirs(os.path.join(tmpdir, "shards"))
43
- yield settings
44
-
45
-
46
- @pytest.fixture
47
- def self_node(cluster_settings):
48
- self_node = MagicMock(id="id", address="address", shard_count=0, available_disk=10)
49
- self_node.reader = AsyncMock()
50
- self_node.writer = AsyncMock()
51
- self_node.reader.Search.return_value = nodereader_pb2.SearchResponse()
52
-
53
- relation_edges = nodereader_pb2.EdgeList()
54
- edge = nodereader_pb2.RelationEdge(
55
- edge_type=RelationNode.NodeType.ENTITY, property="foo"
56
- )
57
- relation_edges.list.append(edge)
58
- self_node.reader.RelationEdges.return_value = relation_edges
59
-
60
- with patch("nucliadb.common.cluster.standalone.service.get_self") as mock_get_self:
61
- mock_get_self.return_value = self_node
62
- yield self_node
63
-
64
-
65
- @pytest.fixture
66
- def servicer(self_node):
67
- yield service.StandaloneClusterServiceServicer()
68
-
69
-
70
- async def test_node_action(
71
- servicer: service.StandaloneClusterServiceServicer,
72
- self_node,
73
- cluster_settings,
74
- ):
75
- resp = await servicer.NodeAction(
76
- standalone_pb2.NodeActionRequest(
77
- service="reader",
78
- action="Search",
79
- payload=nodereader_pb2.SearchRequest(body="test").SerializeToString(),
80
- ),
81
- None,
82
- )
83
- assert resp == standalone_pb2.NodeActionResponse(
84
- payload=self_node.reader.Search.return_value.SerializeToString()
85
- )
86
-
87
-
88
- async def test_reader_node_action_relations(
89
- servicer: service.StandaloneClusterServiceServicer,
90
- self_node,
91
- cluster_settings,
92
- ):
93
- resp = await servicer.NodeAction(
94
- standalone_pb2.NodeActionRequest(
95
- service="reader",
96
- action="RelationEdges",
97
- payload=ShardId(id="test").SerializeToString(),
98
- ),
99
- None,
100
- )
101
- assert resp == standalone_pb2.NodeActionResponse(
102
- payload=self_node.reader.RelationEdges.return_value.SerializeToString()
103
- )
104
-
105
-
106
- async def test_node_info(
107
- servicer: service.StandaloneClusterServiceServicer, self_node, cluster_settings
108
- ):
109
- resp = await servicer.NodeInfo(standalone_pb2.NodeInfoRequest(), None)
110
- assert resp.id == self_node.id
111
- assert resp.address == self_node.address
112
- assert resp.shard_count == self_node.shard_count
113
- assert resp.available_disk > 0
@@ -1,59 +0,0 @@
1
- # Copyright (C) 2021 Bosutech XXI S.L.
2
- #
3
- # nucliadb is offered under the AGPL v3.0 and as commercial software.
4
- # For commercial licensing, contact us at info@nuclia.com.
5
- #
6
- # AGPL:
7
- # This program is free software: you can redistribute it and/or modify
8
- # it under the terms of the GNU Affero General Public License as
9
- # published by the Free Software Foundation, either version 3 of the
10
- # License, or (at your option) any later version.
11
- #
12
- # This program is distributed in the hope that it will be useful,
13
- # but WITHOUT ANY WARRANTY; without even the implied warranty of
14
- # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
15
- # GNU Affero General Public License for more details.
16
- #
17
- # You should have received a copy of the GNU Affero General Public License
18
- # along with this program. If not, see <http://www.gnu.org/licenses/>.
19
- #
20
- import os
21
- import tempfile
22
- from unittest.mock import patch
23
-
24
- import pytest
25
-
26
- from nucliadb.common.cluster.settings import Settings
27
- from nucliadb.common.cluster.standalone import utils
28
-
29
-
30
- @pytest.fixture
31
- def cluster_settings():
32
- settings = Settings()
33
- with patch(
34
- "nucliadb.common.cluster.standalone.utils.cluster_settings", settings
35
- ), tempfile.TemporaryDirectory() as tmpdir:
36
- settings.data_path = tmpdir
37
- yield settings
38
-
39
-
40
- def test_get_standalone_node_id(cluster_settings: Settings):
41
- assert utils.get_standalone_node_id()
42
- assert os.path.exists(os.path.join(cluster_settings.data_path, "node.key"))
43
-
44
-
45
- def test_get_self(cluster_settings: Settings):
46
- os.makedirs(os.path.join(cluster_settings.data_path, "shards", "1"))
47
-
48
- assert utils.get_self().shard_count == 1
49
-
50
-
51
- def test_get_self_k8s_host(cluster_settings: Settings, monkeypatch):
52
- monkeypatch.setenv("NUCLIADB_SERVICE_HOST", "host")
53
- monkeypatch.setenv("HOSTNAME", "nucliadb-0")
54
-
55
- with patch(
56
- "nucliadb.common.cluster.standalone.grpc_node_binding.NodeWriter"
57
- ), patch("nucliadb.common.cluster.standalone.grpc_node_binding.NodeReader"):
58
- # patch because loading settings validates address now
59
- assert utils.get_self().address == "nucliadb-0.nucliadb"