data-designer 0.2.3__py3-none-any.whl → 0.3.0__py3-none-any.whl

{data_designer-0.2.3.dist-info → data_designer-0.3.0.dist-info}/RECORD

@@ -1,8 +1,8 @@
 data_designer/__init__.py,sha256=iCeqRnb640RrL2QpA630GY5Ng7JiDt83Vq0DwLnNugU,461
-data_designer/_version.py,sha256=kBRz0P2plw1eVdIpt70W6m1LMbEIhLY3RyOfVGdubaI,704
+data_designer/_version.py,sha256=5zTqm8rgXsWYBpB2M3Zw_K1D-aV8wP7NsBLrmMKkrAQ,704
 data_designer/errors.py,sha256=Z4eN9XwzZvGRdBluSNoSqQYkPPzNQIDf0ET_OqWRZh8,179
 data_designer/logging.py,sha256=ZsruJ0tx_4NK0PIMyxCZJJ0wJugoDff9UP3PbsdEDxQ,5341
-data_designer/plugin_manager.py,sha256=xaMX274gdlYLNNPIrAOmJNLaZlG_0ROJ0H29v8t2aKs,2604
+data_designer/plugin_manager.py,sha256=NCYhBtMqbIGSMZwTY2F2NkkkdgBGPqnxZCmeiQzEH80,2604
 data_designer/cli/README.md,sha256=uPE3KdlF5Y3H8pQc8c6ZZ3h6YSFXNQW-iEXGQJuVnI4,9026
 data_designer/cli/__init__.py,sha256=kTfolrDol0izniNPXtuaUJ_oXRfJ-jGUPuVR5IwibEM,210
 data_designer/cli/main.py,sha256=v_vjyHbEF0n0Np-jc5KigtNFZflHR7tAnnea5mDzXHI,1933
@@ -22,7 +22,7 @@ data_designer/cli/forms/__init__.py,sha256=BGLbNJCHCgYiQWoAdTbUjzqgVlJymTQOV8sNW
 data_designer/cli/forms/builder.py,sha256=QMCutZb7l3DeL4nXFGCUaiS1bxBu1BdaBWwlb1rmiIE,1690
 data_designer/cli/forms/field.py,sha256=8EYfaqxSynyhPreFOa9JGnsTkeSXxwpRzV8xJb98FGg,7502
 data_designer/cli/forms/form.py,sha256=f6_LdSlk4kddB9a4mGotA-VlR2mlXAU_9RtLkbliI38,2025
-data_designer/cli/forms/model_builder.py,sha256=SEfJuhw22bYjRc0XvLZsorXc8EpEsugHlpoC0OHxhKo,13345
+data_designer/cli/forms/model_builder.py,sha256=voBv7_e0M3CwXxwuv75OSG0_CJQ0thkVVA8G7eCK798,13313
 data_designer/cli/forms/provider_builder.py,sha256=xphQlNlnfDLm0XwqbPC6SJ3wXwlU45xVo_35Pe1EBdU,2895
 data_designer/cli/repositories/__init__.py,sha256=RBOWAkIOOpr-L-kVz-PDIPmMXdlGLCinxkwvKS6bAB4,434
 data_designer/cli/repositories/base.py,sha256=LQ0i_KrTdhS5o48qphlr4uWoAVrz02Lf_ZH1JIhcuBQ,1054
@@ -37,20 +37,21 @@ data_designer/config/__init__.py,sha256=9eG4WHKyrJcNoK4GEz6BCw_E0Ewo9elQoDN4TLMb
 data_designer/config/base.py,sha256=ypam9XX6dg8Q_55su84WmVExNXsmt5jb3eeW3JLlHwc,2396
 data_designer/config/column_configs.py,sha256=pjpy5z3Kk7i4WmIjOxdiW5Awpjy5CxQSy0YMy0QxtvA,18961
 data_designer/config/column_types.py,sha256=EILVM42d4TMl2xbSj5htMsenJwybCHIc_G8AUXyrjWU,7197
-data_designer/config/config_builder.py,sha256=n8in3O-hR2j3wJBnZMCoT5NawlobJDWTyNZCIYSgWIo,29241
+data_designer/config/config_builder.py,sha256=eO7iXO4WeF3h4iJdH203ZFHET9Vj4XAgoIPEJpQDbkg,25371
 data_designer/config/data_designer_config.py,sha256=D2b4Dl8pR6kCkvPoZ3APxC9pVBqXi5EJMVK1WBZ6ni8,1886
 data_designer/config/dataset_builders.py,sha256=1pNFy_pkQ5lJ6AVZ43AeTuSbz6yC_l7Ndcyp5yaT8hQ,327
-data_designer/config/datastore.py,sha256=gEHR2hYlJwD_vzjuaSOMRiYjtwdQhyO9q1afZDrhBCo,7586
 data_designer/config/default_model_settings.py,sha256=YqucXdOdXV6-J2jOc3gSSjbtfXDVbKfmG94neC2Ynaw,4457
-data_designer/config/errors.py,sha256=MNMnqh8G1XzXAMeJ5ju6zkBiIH2aVgyITnzYJbGEwFY,461
-data_designer/config/exports.py,sha256=jPGjuFIpfApwygiTVq7lOI271guJF1oaMwcoyycXV3w,4716
+data_designer/config/errors.py,sha256=MvrZd7tLMaWKjnKHj_GHIap2mkb20O7x56H4c1hIyZI,519
+data_designer/config/exports.py,sha256=OFh-iHtkjqWPOtjUc1esRRaAssL3XVImOTPp0yWWSW0,4715
 data_designer/config/interface.py,sha256=ery8a93pnCW1JPbgtiaRsMKSR8Q2o7rDmsZfVYbfkeE,1619
-data_designer/config/models.py,sha256=_uLOh2TutJV3Fq_8YyAi5E7G37j47j64zcrCYnzpjbo,15713
+data_designer/config/models.py,sha256=EQCzN_pNIZ2enarKSs0Ry40oNzVFGr188jwplOQQGCI,15330
 data_designer/config/preview_results.py,sha256=bPRKX1enzNTY240ixc8jZVgO7EDHABZ1_er0TabhLZg,1345
 data_designer/config/processors.py,sha256=bA6SVF1kmAJSshmWseLE6HzlEBAsH9FtUtNJk0QzJtU,5987
+data_designer/config/run_config.py,sha256=6CDHjcmkZmzP3NSlaeyVkLbRVKsb7ry3b0ms6T-A7rc,1418
 data_designer/config/sampler_constraints.py,sha256=Q8-JrwTD69AJy8cvs_-0yf4yOBGemLwLZNmk-8Y5wPk,1156
 data_designer/config/sampler_params.py,sha256=-MLNFDqattNWrHuWPYyGTe2YdbaGMH-JKTCzxq1ji3E,27838
-data_designer/config/seed.py,sha256=n4iHDBkUlwNJSXqDu6BqD6uZZeFtLu6x1hyyOhcG9zM,5503
+data_designer/config/seed.py,sha256=FEi3O5eNMk3qLiAHNAKFyJ5ijAk0e0MaHcYpfo1pa9c,4621
+data_designer/config/seed_source.py,sha256=ajdlhpDSnXJZYRMdP-MpBc5q0hKE_niMdo75FhHyvp8,2240
 data_designer/config/validator_params.py,sha256=BSDNVZQvXB4hmhuX4EnJ89pR-1hdEfI_KWYO8POQlMk,3906
 data_designer/config/analysis/__init__.py,sha256=9eG4WHKyrJcNoK4GEz6BCw_E0Ewo9elQoDN4TLMbAog,137
 data_designer/config/analysis/column_profilers.py,sha256=PcFR6uhlJzz8VMYHYoYYMZ6Rj6zrk0RbjomSHDn9GDI,6215
@@ -59,20 +60,21 @@ data_designer/config/analysis/dataset_profiler.py,sha256=Omst6qNsUi9sdbV7c0kASK6
 data_designer/config/analysis/utils/errors.py,sha256=UbWKIo8uMNqGXJKf4XR6PbuDDZnBQ7qHyEdq8Oh97QY,290
 data_designer/config/analysis/utils/reporting.py,sha256=8tds-g6q1NLW8xHzT9OukgEWA1Y5qAnMq-BjP4u_Frk,7030
 data_designer/config/utils/code_lang.py,sha256=szSihIdVZsjgUOcbxndgI3P4GNN51DUeNlk5Z8nEYro,2349
-data_designer/config/utils/constants.py,sha256=MMb5-aJOHfsvfptCFxv2AyzOeryeDNsqoce9B-wCTJk,7880
+data_designer/config/utils/constants.py,sha256=mNP1r3ucImsB743UFbjd-VFc0ZcSuqOQXRu4jVBR8FI,8884
 data_designer/config/utils/errors.py,sha256=X8_ghPqHKWN6qDMW0WhBoxFNr9MNygOEawq0oGigPD8,479
 data_designer/config/utils/info.py,sha256=AW8GnmxGX-LahQCDT9BPl8eqUz3ymNr647VHHj5gBHg,3428
-data_designer/config/utils/io_helpers.py,sha256=2jpR0F0n4m5qBJCA6GXqEEUDyh289H0AsIBkC6RZn2E,9173
+data_designer/config/utils/io_helpers.py,sha256=xIN4FicjITOoNZB-nX5LnVr45-lvhsSYenlerXlq5_8,8331
 data_designer/config/utils/misc.py,sha256=qH2VgPYmr1FZTX_r8rXmtNTdKpCs0rg7aEos0w7ylNo,2467
 data_designer/config/utils/numerical_helpers.py,sha256=YujDvTOkm0FW3V5G6Ja_Etf7d8tJ71Rpj_BHRu5JlRY,797
 data_designer/config/utils/type_helpers.py,sha256=KOnxSYDHefadfOrlzRk-XixvwbZ31Ql7wOXAdQh0qoU,4018
-data_designer/config/utils/validation.py,sha256=VvQ2vYZKSp-nPSukGzKv9rXXkpr5Spz3fkIX8HC28lk,14440
 data_designer/config/utils/visualization.py,sha256=ql0rnRIF7AhkuyS6zE35FockYzCkDRamzFUs6J7g23I,18186
 data_designer/engine/__init__.py,sha256=9eG4WHKyrJcNoK4GEz6BCw_E0Ewo9elQoDN4TLMbAog,137
+data_designer/engine/compiler.py,sha256=dQOCnjIU3SC6TrwpJVY8Nnv2Ql8-_aEAeY9TdewO6T0,2853
 data_designer/engine/configurable_task.py,sha256=nLUUzmVQ_RcX4l97wwROspFeYtVfdh0llxiau49d5Ic,3118
 data_designer/engine/errors.py,sha256=DUoKhQCSwIBoLSQGv7dstzO3DFGDRqW3MBoWnRPcm1I,1262
 data_designer/engine/model_provider.py,sha256=w_7EZpDKgOLdzmCWJ6v6oKdM0GdRijir3iK102bBtg8,2782
 data_designer/engine/secret_resolver.py,sha256=IyvLvx_me9oiLk6uaVddTnd01Pz7qeYsleOhtKtcm3A,2427
+data_designer/engine/validation.py,sha256=VvQ2vYZKSp-nPSukGzKv9rXXkpr5Spz3fkIX8HC28lk,14440
 data_designer/engine/analysis/column_statistics.py,sha256=M_IxRwPeIaaN37UtPFMW09eXYQ-hEgu_NnLzlQj8AtY,5752
 data_designer/engine/analysis/dataset_profiler.py,sha256=jmK0VFKH6mVkRaAA-upvCFBtxVeT-02ss9X0gRInP0A,7238
 data_designer/engine/analysis/errors.py,sha256=VBeKREcPcInWhjAo3U2x_9UnJBi8zcGnUjLXNippPtA,255
@@ -82,31 +84,31 @@ data_designer/engine/analysis/column_profilers/registry.py,sha256=GpudnadaJxb8ub
 data_designer/engine/analysis/utils/column_statistics_calculations.py,sha256=B5g1j8f0z1AFAEUVXf3roLZUI--jEs01Tj9g9yREWxk,8851
 data_designer/engine/analysis/utils/judge_score_processing.py,sha256=rl11e3PxAOQPDSmK9G9kxOMUCJrZddQusUobDKZhIzw,4758
 data_designer/engine/column_generators/__init__.py,sha256=9eG4WHKyrJcNoK4GEz6BCw_E0Ewo9elQoDN4TLMbAog,137
-data_designer/engine/column_generators/registry.py,sha256=Eg6tqNM7mmEPNom1fWF9S5D3qABpMennOHGEGePwJN0,3060
+data_designer/engine/column_generators/registry.py,sha256=qiC7B1MvcEgzfPtWBPHqF9vNpWGHpUg9YekR-lAZJl0,3060
 data_designer/engine/column_generators/generators/__init__.py,sha256=9eG4WHKyrJcNoK4GEz6BCw_E0Ewo9elQoDN4TLMbAog,137
 data_designer/engine/column_generators/generators/base.py,sha256=zurwtamM2l3shLa4SLjUOE0zOTDozQ5wPGAvDkrNYqE,3231
 data_designer/engine/column_generators/generators/embedding.py,sha256=xYnFWRJ2W7JuwK8CRIUhv4QiT_DCGDuQkuHFKXCxrow,1724
 data_designer/engine/column_generators/generators/expression.py,sha256=7xniEj8aPscWDYLrnNbG2mF3s08C7aR8ZgNUCzr_x8g,2539
 data_designer/engine/column_generators/generators/llm_completion.py,sha256=XqpXzYczbZ6efUIVuvcm2O_mXBnXCMAvcjeyaB5dIFA,5301
 data_designer/engine/column_generators/generators/samplers.py,sha256=YHoTWi8Wo9TyR-98I-rOHJUHOIJXxvbil-PrhNKMWxQ,3579
-data_designer/engine/column_generators/generators/seed_dataset.py,sha256=QUegAT55AxyBHY5VhAtJKv9BRgGJ2jxN0Yff7YvkLDI,7018
-data_designer/engine/column_generators/generators/validation.py,sha256=MbDFXzieftv6-77rRdltNUnquUe5FxCVkBEHsAwvwh4,6591
+data_designer/engine/column_generators/generators/seed_dataset.py,sha256=6fG1ybsil7kqKfEL8AXS7L96tdloWbh8X9nYzf803AY,6996
+data_designer/engine/column_generators/generators/validation.py,sha256=QxDE4HIBLtZ-_12eYwJxPXOaYo81vCDifM5YHdk7tow,6772
 data_designer/engine/column_generators/utils/errors.py,sha256=ugNwaqnPdrPZI7YnKLbYwFjYUSm0WAzgaVu_u6i5Rc8,365
 data_designer/engine/column_generators/utils/judge_score_factory.py,sha256=umo8-iMWbvkAztWkB5m_pU1cY1eBpR5L2gHt_fuZPD4,2100
 data_designer/engine/column_generators/utils/prompt_renderer.py,sha256=d4tbyPsgmFDikW3nxL5is9RNaajMkoPDCrfkQkxw7rc,4760
 data_designer/engine/dataset_builders/artifact_storage.py,sha256=mVCqcW8shylofi_pjYEeHUa9Mo-tjIcl4nR8D8oy2bw,8420
-data_designer/engine/dataset_builders/column_wise_builder.py,sha256=h6R6YfU2sfhxewIyTaLdcgSI6FpfIouyc1qdfnWfUZ0,14801
+data_designer/engine/dataset_builders/column_wise_builder.py,sha256=UDZce0nxh6t3d6PgVlJdOJl0T7tseAdGocLHeGdJP5I,14983
 data_designer/engine/dataset_builders/errors.py,sha256=1kChleChG4rASWIiL4Bel6Ox6aFZjQUrh5ogPt1CDWo,359
 data_designer/engine/dataset_builders/multi_column_configs.py,sha256=t28fhI-WRIBohFnAJ80l5EAETEDB5rJ5RSWInMiRfyE,1619
 data_designer/engine/dataset_builders/utils/__init__.py,sha256=9eG4WHKyrJcNoK4GEz6BCw_E0Ewo9elQoDN4TLMbAog,137
 data_designer/engine/dataset_builders/utils/concurrency.py,sha256=Qvf5H-FdUCikIocOry_E3jkSC7qVZQjAXOY9dxdtMGg,7336
-data_designer/engine/dataset_builders/utils/config_compiler.py,sha256=verC3CBA0MjuTQN32RBX10fFvVOefG-DnPDF5Ql2hjg,2402
+data_designer/engine/dataset_builders/utils/config_compiler.py,sha256=e_Y9WdcHE-H-fGwm-4Qgs2FlD6qO08Gw2SLafUtoqTE,2400
 data_designer/engine/dataset_builders/utils/dag.py,sha256=8h7jEu0XiYGSKHIe4CGFi6SC9HGyAgvkD23ZECNWDC0,2388
 data_designer/engine/dataset_builders/utils/dataset_batch_manager.py,sha256=xLN_cAu5xb4V-RjSPezNivOkCAigA3-qNfv_kAWRAHs,7769
 data_designer/engine/dataset_builders/utils/errors.py,sha256=qW_TFOKNVODbb8bYrUlbqMAkheDAg12DDo3RmAhHrCg,370
 data_designer/engine/models/__init__.py,sha256=9eG4WHKyrJcNoK4GEz6BCw_E0Ewo9elQoDN4TLMbAog,137
 data_designer/engine/models/errors.py,sha256=AQlZ-cf0IqFW-e-K9HZFH3YhXXOTLLI2eZCXr7_58Yk,12174
-data_designer/engine/models/facade.py,sha256=sqTSqW7jQ1vbRc1fCOoKuhb7vTVil5Z8RqN_NBp6exY,12410
+data_designer/engine/models/facade.py,sha256=rONeAGTRwvoYBN3Dyq3Xe012NNOpVQj-pj3N3deGpsU,12528
 data_designer/engine/models/litellm_overrides.py,sha256=FpCztZQrHYGrVweLR0_NAqxVRs-UXmpkMPdFWqciu84,5539
 data_designer/engine/models/registry.py,sha256=-TbGhvs8WRq6f7z6cH_DDdo7uhs4Hb5qkJce_Y4UBWM,6840
 data_designer/engine/models/telemetry.py,sha256=3g4jDz8xxOOkPtIYit94c4D4mGUwgfiCDaDdnbTLhFQ,12407
@@ -130,7 +132,7 @@ data_designer/engine/processing/gsonschema/__init__.py,sha256=9eG4WHKyrJcNoK4GEz
 data_designer/engine/processing/gsonschema/exceptions.py,sha256=IoMlQE-eRJcBUlzKnkCCBSVSlGjsoYZSE0OVwcikxlI,281
 data_designer/engine/processing/gsonschema/schema_transformers.py,sha256=__-dfrCFxDs5-XcTzi1Z-FZL9z0eWUS7Zppr32OxgiY,3066
 data_designer/engine/processing/gsonschema/types.py,sha256=-x_K2HrVnZ_Z7fzYl4T2Gd7QHf6B6ADvn7E7iYvw5Kc,313
-data_designer/engine/processing/gsonschema/validators.py,sha256=5Jh864KnA5gWBeLbpz1cE5Kk_GMxI6kPWvunAbLI3vI,4704
+data_designer/engine/processing/gsonschema/validators.py,sha256=jmY51MJC0kfBExAXGED9Uqc9sxT47_sZ1K3X7OuvCXM,6848
 data_designer/engine/processing/processors/base.py,sha256=WJl7_0dtiUppjfY-lrQ3lDiIgYqRDSEYUwSAQNN7nFE,548
 data_designer/engine/processing/processors/drop_columns.py,sha256=MIb_CVrpoM3kyN5-8dHZrdFAAUiCCWgDEyQjAk8nZqE,2060
 data_designer/engine/processing/processors/registry.py,sha256=nhB1O4b0wSUkWQeleV9l1MykwZD-dSvY0ydqmSscEY8,1056
@@ -141,8 +143,8 @@ data_designer/engine/registry/errors.py,sha256=nO794QVy4DovKGKWEjycVDN9cdDlH-skb
 data_designer/engine/resources/managed_dataset_generator.py,sha256=KXrWdgod-NFaCZvmWSwoJKp2daQgqf8XBIVXvrk6fHI,1369
 data_designer/engine/resources/managed_dataset_repository.py,sha256=IzolKh2n_8BLd0XRuWEZhddYpXqc9YYpVUFC7DH7Qz8,7547
 data_designer/engine/resources/managed_storage.py,sha256=BOdOtUChfNJL6S2Cxw_hrQF28ZnJvObtTIVNkQMUgX0,2079
-data_designer/engine/resources/resource_provider.py,sha256=CbB2D538ECGkvyHF1V63_TDn-wStCoklV7bF0y4mabY,1859
-data_designer/engine/resources/seed_dataset_data_store.py,sha256=dM2HgfyUgbF7MidN8dn5S-LAR0GVPJfjqXpDPTP2XoA,3035
+data_designer/engine/resources/resource_provider.py,sha256=guDKOGenQfi2VHH6ZevVbGwKmG9nTtNaW2TEWybhcw8,2318
+data_designer/engine/resources/seed_reader.py,sha256=-UgqYH_iAaMrw73y09p2rskTiu3q9-XhNKJoTM3KlRo,5591
 data_designer/engine/sampling_gen/column.py,sha256=gDIPth7vK2797rGtLhf_kVGMAC-khefKHodeeDoqV-I,3946
 data_designer/engine/sampling_gen/constraints.py,sha256=e-gLItnSobUR8eSfQdkXkmvrBYLScpBcE97Xd0H2wV8,3004
 data_designer/engine/sampling_gen/errors.py,sha256=UBZBtosD07EisCdeo8r-Uq4h0QL3tYS1qwtEmca8_jM,828
@@ -170,17 +172,20 @@ data_designer/engine/validators/local_callable.py,sha256=oCUXj_NRt0gVqUIh0fLrvw-
 data_designer/engine/validators/python.py,sha256=jAp1u8yLjqfebh60xGapkHVjMz58WHB0QjfMc2zQCaY,7894
 data_designer/engine/validators/remote.py,sha256=jtDIvWzfHh17m2ac_Fp93p49Th8RlkBzzih2jiqD7gk,2929
 data_designer/engine/validators/sql.py,sha256=bxbyxPxDT9yuwjhABVEY40iR1pzWRFi65WU4tPgG2bE,2250
-data_designer/essentials/__init__.py,sha256=eHuZFJTmeRf_b6KQZ2vZeqy1afJ7y7RMTm7q4Jrg58s,1012
+data_designer/essentials/__init__.py,sha256=viyPs-sIVMuHuFpWhZVKtwRsDQFMsmtw6B7veK_No_I,1094
 data_designer/interface/__init__.py,sha256=9eG4WHKyrJcNoK4GEz6BCw_E0Ewo9elQoDN4TLMbAog,137
-data_designer/interface/data_designer.py,sha256=O6PehBIdL4_2d9rFW86J9b3jfJ_CJmFId8T2AviM2zM,16844
+data_designer/interface/data_designer.py,sha256=jiPI0vbzTAT4Oug4W4RCBS69bCQOfCE9awfClwBeDnI,17175
 data_designer/interface/errors.py,sha256=jagKT3tPUnYq4e3e6AkTnBkcayHyEfxjPMBzx-GEKe4,565
 data_designer/interface/results.py,sha256=zYVX589OUyFuB-8XLmjjdKk3hCDNKu189sH-gOOFreQ,3511
 data_designer/plugins/__init__.py,sha256=c_V7q4QhfVoNf_uc9UwmXCsWqwtyWogI7YoN_0PzzE4,234
-data_designer/plugins/errors.py,sha256=yPIHpSddEr-o9ZcNVibb2hI-73O15Kg_Od8SlmQlnRs,297
-data_designer/plugins/plugin.py,sha256=a2KfoCNhYa8U0uQrPSBWfuyjXOb5WeITzFRpEdZFo6s,2516
+data_designer/plugins/errors.py,sha256=nljerskefztjy84UARpw3ogm4GI8CmJCi4FrfaVJI2w,345
+data_designer/plugins/plugin.py,sha256=n4nlFHZZ0INY7vFJylTGoh1ij9k3TSVw-15OGSdROGE,5355
 data_designer/plugins/registry.py,sha256=c0X03TnA_J60RWpxaVJEmtIXKvA9up-LznrUHXDcYxg,3012
-data_designer-0.2.3.dist-info/METADATA,sha256=JUXSRI21S_Sp_Jwh060AHSCvqEERjHXG9sNhwxJUfSU,7636
-data_designer-0.2.3.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-data_designer-0.2.3.dist-info/entry_points.txt,sha256=NWWWidyDxN6CYX6y664PhBYMhbaYTQTyprqfYAgkyCg,57
-data_designer-0.2.3.dist-info/licenses/LICENSE,sha256=cSWJDwVqHyQgly8Zmt3pqXJ2eQbZVYwN9qd0NMssxXY,11336
-data_designer-0.2.3.dist-info/RECORD,,
+data_designer/plugins/testing/__init__.py,sha256=fyFqJcdyYcU5nj55RjqD6NjkXl4nhNZw5Bd6-sLnnjQ,255
+data_designer/plugins/testing/stubs.py,sha256=IqriaMWtQbhPSoWAkbcKsTga-Xi5rTZBlW70IC0cpd0,4699
+data_designer/plugins/testing/utils.py,sha256=2Pk0BJ7tx6gKLCoJr72EqpqfTWzHnlk_Lkwi89aDQQs,578
+data_designer-0.3.0.dist-info/METADATA,sha256=lb_Mn3vMSrflnJZYdRaWMBXK69VrTa3xZdvyRj8lqB8,7652
+data_designer-0.3.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+data_designer-0.3.0.dist-info/entry_points.txt,sha256=NWWWidyDxN6CYX6y664PhBYMhbaYTQTyprqfYAgkyCg,57
+data_designer-0.3.0.dist-info/licenses/LICENSE,sha256=cSWJDwVqHyQgly8Zmt3pqXJ2eQbZVYwN9qd0NMssxXY,11336
+data_designer-0.3.0.dist-info/RECORD,,

data_designer/config/datastore.py

@@ -1,187 +0,0 @@
-# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
-# SPDX-License-Identifier: Apache-2.0
-
-from __future__ import annotations
-
-import logging
-from pathlib import Path
-from typing import TYPE_CHECKING
-
-import pandas as pd
-import pyarrow.parquet as pq
-from huggingface_hub import HfApi, HfFileSystem
-from pydantic import BaseModel, Field
-
-from data_designer.config.errors import InvalidConfigError, InvalidFileFormatError, InvalidFilePathError
-from data_designer.config.utils.io_helpers import VALID_DATASET_FILE_EXTENSIONS, validate_path_contains_files_of_type
-
-if TYPE_CHECKING:
-    from data_designer.config.seed import SeedDatasetReference
-
-logger = logging.getLogger(__name__)
-
-
-class DatastoreSettings(BaseModel):
-    """Configuration for interacting with a datastore."""
-
-    endpoint: str = Field(
-        ...,
-        description="Datastore endpoint. Use 'https://huggingface.co' for the Hugging Face Hub.",
-    )
-    token: str | None = Field(default=None, description="If needed, token to use for authentication.")
-
-
-def get_file_column_names(file_reference: str | Path | HfFileSystem, file_type: str) -> list[str]:
-    """Get column names from a dataset file.
-
-    Args:
-        file_reference: Path to the dataset file, or an HfFileSystem object.
-        file_type: Type of the dataset file. Must be one of: 'parquet', 'json', 'jsonl', 'csv'.
-
-    Raises:
-        InvalidFilePathError: If the file type is not supported.
-
-    Returns:
-        List of column names.
-    """
-    if file_type == "parquet":
-        try:
-            schema = pq.read_schema(file_reference)
-            if hasattr(schema, "names"):
-                return schema.names
-            else:
-                return [field.name for field in schema]
-        except Exception as e:
-            logger.warning(f"Failed to process parquet file {file_reference}: {e}")
-            return []
-    elif file_type in ["json", "jsonl"]:
-        return pd.read_json(file_reference, orient="records", lines=True, nrows=1).columns.tolist()
-    elif file_type == "csv":
-        try:
-            df = pd.read_csv(file_reference, nrows=1)
-            return df.columns.tolist()
-        except (pd.errors.EmptyDataError, pd.errors.ParserError) as e:
-            logger.warning(f"Failed to process CSV file {file_reference}: {e}")
-            return []
-    else:
-        raise InvalidFilePathError(f"🛑 Unsupported file type: {file_type!r}")
-
-
-def fetch_seed_dataset_column_names(seed_dataset_reference: SeedDatasetReference) -> list[str]:
-    if hasattr(seed_dataset_reference, "datastore_settings"):
-        return fetch_seed_dataset_column_names_from_datastore(
-            seed_dataset_reference.repo_id,
-            seed_dataset_reference.filename,
-            seed_dataset_reference.datastore_settings,
-        )
-    return fetch_seed_dataset_column_names_from_local_file(seed_dataset_reference.dataset)
-
-
-def fetch_seed_dataset_column_names_from_datastore(
-    repo_id: str,
-    filename: str,
-    datastore_settings: DatastoreSettings | dict | None = None,
-) -> list[str]:
-    file_type = filename.split(".")[-1]
-    if f".{file_type}" not in VALID_DATASET_FILE_EXTENSIONS:
-        raise InvalidFileFormatError(f"🛑 Unsupported file type: {filename!r}")
-
-    datastore_settings = resolve_datastore_settings(datastore_settings)
-    fs = HfFileSystem(endpoint=datastore_settings.endpoint, token=datastore_settings.token, skip_instance_cache=True)
-
-    file_path = _extract_single_file_path_from_glob_pattern_if_present(f"datasets/{repo_id}/{filename}", fs=fs)
-
-    with fs.open(file_path) as f:
-        return get_file_column_names(f, file_type)
-
-
-def fetch_seed_dataset_column_names_from_local_file(dataset_path: str | Path) -> list[str]:
-    dataset_path = _validate_dataset_path(dataset_path, allow_glob_pattern=True)
-    dataset_path = _extract_single_file_path_from_glob_pattern_if_present(dataset_path)
-    return get_file_column_names(dataset_path, str(dataset_path).split(".")[-1])
-
-
-def resolve_datastore_settings(datastore_settings: DatastoreSettings | dict | None) -> DatastoreSettings:
-    if datastore_settings is None:
-        raise InvalidConfigError("🛑 Datastore settings are required in order to upload datasets to the datastore.")
-    if isinstance(datastore_settings, DatastoreSettings):
-        return datastore_settings
-    elif isinstance(datastore_settings, dict):
-        return DatastoreSettings.model_validate(datastore_settings)
-    else:
-        raise InvalidConfigError(
-            "🛑 Invalid datastore settings format. Must be DatastoreSettings object or dictionary."
-        )
-
-
-def upload_to_hf_hub(
-    dataset_path: str | Path,
-    filename: str,
-    repo_id: str,
-    datastore_settings: DatastoreSettings,
-    **kwargs,
-) -> str:
-    datastore_settings = resolve_datastore_settings(datastore_settings)
-    dataset_path = _validate_dataset_path(dataset_path)
-    filename_ext = filename.split(".")[-1].lower()
-    if dataset_path.suffix.lower()[1:] != filename_ext:
-        raise InvalidFileFormatError(
-            f"🛑 Dataset file extension {dataset_path.suffix!r} does not match `filename` extension .{filename_ext!r}"
-        )
-
-    hfapi = HfApi(endpoint=datastore_settings.endpoint, token=datastore_settings.token)
-    hfapi.create_repo(repo_id, exist_ok=True, repo_type="dataset")
-    hfapi.upload_file(
-        path_or_fileobj=dataset_path,
-        path_in_repo=filename,
-        repo_id=repo_id,
-        repo_type="dataset",
-        **kwargs,
-    )
-    return f"{repo_id}/{filename}"
-
-
-def _extract_single_file_path_from_glob_pattern_if_present(
-    file_path: str | Path,
-    fs: HfFileSystem | None = None,
-) -> Path:
-    file_path = Path(file_path)
-
-    # no glob pattern
-    if "*" not in str(file_path):
-        return file_path
-
-    # glob pattern with HfFileSystem
-    if fs is not None:
-        file_to_check = None
-        file_extension = file_path.name.split(".")[-1]
-        for file in fs.ls(str(file_path.parent)):
-            filename = file["name"]
-            if filename.endswith(f".{file_extension}"):
-                file_to_check = filename
-        if file_to_check is None:
-            raise InvalidFilePathError(f"🛑 No files found matching pattern: {str(file_path)!r}")
-        logger.debug(f"Using the first matching file in {str(file_path)!r} to determine column names in seed dataset")
-        return Path(file_to_check)
-
-    # glob pattern with local file system
-    if not (matching_files := sorted(file_path.parent.glob(file_path.name))):
-        raise InvalidFilePathError(f"🛑 No files found matching pattern: {str(file_path)!r}")
-    logger.debug(f"Using the first matching file in {str(file_path)!r} to determine column names in seed dataset")
-    return matching_files[0]
-
-
-def _validate_dataset_path(dataset_path: str | Path, allow_glob_pattern: bool = False) -> Path:
-    if allow_glob_pattern and "*" in str(dataset_path):
-        parts = str(dataset_path).split("*.")
-        file_path = parts[0]
-        file_extension = parts[-1]
-        validate_path_contains_files_of_type(file_path, file_extension)
-        return Path(dataset_path)
-    if not Path(dataset_path).is_file():
-        raise InvalidFilePathError("🛑 To upload a dataset to the datastore, you must provide a valid file path.")
-    if not Path(dataset_path).name.endswith(tuple(VALID_DATASET_FILE_EXTENSIONS)):
-        raise InvalidFileFormatError(
-            "🛑 Dataset files must be in `parquet`, `csv`, or `json` (orient='records', lines=True) format."
-        )
-    return Path(dataset_path)

data_designer/engine/resources/seed_dataset_data_store.py

@@ -1,84 +0,0 @@
-# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
-# SPDX-License-Identifier: Apache-2.0
-
-from abc import ABC, abstractmethod
-
-import duckdb
-from huggingface_hub import HfApi, HfFileSystem
-
-from data_designer.logging import quiet_noisy_logger
-
-quiet_noisy_logger("httpx")
-
-_HF_DATASETS_PREFIX = "hf://datasets/"
-
-
-class MalformedFileIdError(Exception):
-    """Raised when file_id format is invalid."""
-
-
-class SeedDatasetDataStore(ABC):
-    """Abstract base class for dataset storage implementations."""
-
-    @abstractmethod
-    def create_duckdb_connection(self) -> duckdb.DuckDBPyConnection: ...
-
-    @abstractmethod
-    def get_dataset_uri(self, file_id: str) -> str: ...
-
-
-class LocalSeedDatasetDataStore(SeedDatasetDataStore):
-    """Local filesystem-based dataset storage."""
-
-    def create_duckdb_connection(self) -> duckdb.DuckDBPyConnection:
-        return duckdb.connect()
-
-    def get_dataset_uri(self, file_id: str) -> str:
-        return file_id
-
-
-class HfHubSeedDatasetDataStore(SeedDatasetDataStore):
-    """Hugging Face and Data Store dataset storage."""
-
-    def __init__(self, endpoint: str, token: str | None):
-        self.hfapi = HfApi(endpoint=endpoint, token=token)
-        self.endpoint = endpoint
-        self.token = token
-
-    def create_duckdb_connection(self) -> duckdb.DuckDBPyConnection:
-        """Create a DuckDB connection with a fresh HfFileSystem registered.
-
-        Creates a new HfFileSystem instance for each connection to ensure file metadata
-        is fetched fresh from the datastore, avoiding cache-related issues when reading
-        recently updated parquet files.
-
-        Returns:
-            A DuckDB connection with the HfFileSystem registered for hf:// URI support.
-        """
-        # Use skip_instance_cache to avoid fsspec-level caching
-        hffs = HfFileSystem(endpoint=self.endpoint, token=self.token, skip_instance_cache=True)
-
-        # Clear all internal caches to avoid stale metadata issues
-        # HfFileSystem caches file metadata (size, etc.) which can become stale when files are re-uploaded
-        if hasattr(hffs, "dircache"):
-            hffs.dircache.clear()
-
-        conn = duckdb.connect()
-        conn.register_filesystem(hffs)
-        return conn
-
-    def get_dataset_uri(self, file_id: str) -> str:
-        identifier = file_id.removeprefix(_HF_DATASETS_PREFIX)
-        repo_id, filename = self._get_repo_id_and_filename(identifier)
-        return f"{_HF_DATASETS_PREFIX}{repo_id}/{filename}"
-
-    def _get_repo_id_and_filename(self, identifier: str) -> tuple[str, str]:
-        """Extract repo_id and filename from identifier."""
-        parts = identifier.split("/", 2)
-        if len(parts) < 3:
-            raise MalformedFileIdError(
-                "Could not extract repo id and filename from file_id, "
-                "expected 'hf://datasets/{repo-namespace}/{repo-name}/{filename}'"
-            )
-        repo_ns, repo_name, filename = parts
-        return f"{repo_ns}/{repo_name}", filename