corvic-engine 0.3.0rc81__cp38-abi3-win_amd64.whl → 0.3.0rc82__cp38-abi3-win_amd64.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.
corvic/engine/_native.pyd CHANGED
Binary file
corvic/op_graph/ops.py CHANGED
@@ -1260,7 +1260,9 @@ class _Base(OneofProtoWrapper[table_pb2.TableComputeOp], ABC):
1260
1260
  column_name=column_name,
1261
1261
  )
1262
1262
 
1263
- field = column.to_frame().to_arrow().schema.field(column_name)
1263
+ # TODO(aneesh): See https://github.com/pola-rs/polars/issues/23111 for
1264
+ # and remove the rechunk eventually.
1265
+ field = column.to_frame().rechunk().to_arrow().schema.field(column_name)
1264
1266
  dtype = field.type
1265
1267
 
1266
1268
  if ftype is None:
@@ -1268,8 +1270,10 @@ class _Base(OneofProtoWrapper[table_pb2.TableComputeOp], ABC):
1268
1270
 
1269
1271
  # Convert array to record batch with dummy column to use pa_scalar and then
1270
1272
  # remove the dummy column.
1273
+ # TODO(aneesh): See https://github.com/pola-rs/polars/issues/23111 for
1274
+ # and remove the rechunk eventually.
1271
1275
  value_batch = pa.record_batch(
1272
- [column.to_arrow()], schema=pa.schema([field]), metadata=None
1276
+ [column.rechunk().to_arrow()], schema=pa.schema([field]), metadata=None
1273
1277
  )
1274
1278
  structs = pa_scalar.batch_to_structs(value_batch)
1275
1279
  literal_values = [
corvic/system/__init__.py CHANGED
@@ -14,6 +14,7 @@ from corvic.system._embedder import (
14
14
  EmbedTextContext,
15
15
  EmbedTextResult,
16
16
  ImageEmbedder,
17
+ SigLIP2Text,
17
18
  TextEmbedder,
18
19
  )
19
20
  from corvic.system._image_embedder import (
@@ -68,23 +69,26 @@ __all__ = [
68
69
  "Client",
69
70
  "Clip",
70
71
  "ClipText",
72
+ "CombinedImageEmbedder",
71
73
  "DEFAULT_VECTOR_COLUMN_NAMES_TO_SIZES",
72
74
  "DataMisplacedError",
73
75
  "DimensionReducer",
76
+ "EmbedImageContext",
77
+ "EmbedImageResult",
74
78
  "EmbedTextContext",
75
79
  "EmbedTextResult",
76
80
  "ExecutionContext",
77
81
  "ExecutionResult",
78
- "EmbedImageContext",
79
- "EmbedImageResult",
82
+ "IdentityImageEmbedder",
83
+ "IdentityTextEmbedder",
80
84
  "ImageEmbedder",
81
85
  "InMemoryExecutionResult",
82
86
  "InMemoryExecutor",
83
87
  "OpGraphExecutor",
84
88
  "OpGraphPlanner",
85
89
  "RandomImageEmbedder",
86
- "CombinedImageEmbedder",
87
90
  "RandomTextEmbedder",
91
+ "SigLIP2Text",
88
92
  "StagingDB",
89
93
  "StorageManager",
90
94
  "TableComputeContext",
@@ -97,9 +101,7 @@ __all__ = [
97
101
  "VectorSimilarityMetric",
98
102
  "get_polars_embedding",
99
103
  "get_polars_embedding_length",
104
+ "image_from_bytes",
100
105
  "make_dict_bytes_human_readable",
101
106
  "make_list_bytes_human_readable",
102
- "image_from_bytes",
103
- "IdentityTextEmbedder",
104
- "IdentityImageEmbedder",
105
107
  ]
@@ -215,7 +215,12 @@ class _SchemaAndBatches:
215
215
  and not len(dataframe)
216
216
  ):
217
217
  return cls(expected_schema, [], metrics)
218
- table = dataframe.to_arrow()
218
+ # TODO(aneesh): without this rechunk, conversion to arrow will
219
+ # occasionally fail and complain about mismatched child array lengths.
220
+ # This should probably be fixed internally in polars (note that this
221
+ # still currently happens on polars 1.30.0 - the latest release).
222
+ # See https://github.com/pola-rs/polars/issues/23111.
223
+ table = dataframe.rechunk().to_arrow()
219
224
  schema = table.schema
220
225
  return cls(schema, table.to_batches(), metrics)
221
226
 
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: corvic-engine
3
- Version: 0.3.0rc81
3
+ Version: 0.3.0rc82
4
4
  Classifier: Environment :: Console
5
5
  Classifier: License :: Other/Proprietary License
6
6
  Classifier: Programming Language :: Python :: Implementation :: CPython
@@ -27,6 +27,7 @@ Requires-Dist: umap-learn>=0.5.5 ; extra == 'ml'
27
27
  Requires-Dist: pillow>=10.0.0 ; extra == 'ml'
28
28
  Requires-Dist: scikit-learn>=1.4.0 ; extra == 'ml'
29
29
  Requires-Dist: transformers[torch]>=4.45.0 ; extra == 'ml'
30
+ Requires-Dist: sentencepiece>=0.2.0 ; extra == 'ml'
30
31
  Requires-Dist: opentelemetry-api>=1.20.0 ; extra == 'telemetry'
31
32
  Requires-Dist: opentelemetry-sdk>=1.20.0 ; extra == 'telemetry'
32
33
  Provides-Extra: ml
@@ -11,7 +11,7 @@ corvic/embedding_metric/__init__.py,sha256=8a-QKSQNbiksueHk5LdkugjZr6wasP4ff8A-J
11
11
  corvic/embedding_metric/embeddings.py,sha256=XCiMzoGdRSmCOJnBDnxm3xlU0L_vrXwUxEjwdMv1FMI,14036
12
12
  corvic/embedding_metric/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
13
13
  corvic/engine/__init__.py,sha256=XL4Vg7rNcBi29ccVelpeFizR9oJtGYXDn84W9zok9d4,975
14
- corvic/engine/_native.pyd,sha256=qr5bmOjrt1JfUr_JrvlhPY8Cz3GcqJ_REeAchdUnKm4,438272
14
+ corvic/engine/_native.pyd,sha256=KrvuFBZt0V2hqkvW0c1KSXEhN5HOkVs0IBs-rg9nCrM,438272
15
15
  corvic/engine/_native.pyi,sha256=KYMPtvXqHZ-jMgZohLf4se3rr-rBpCihmjANcr6s8ag,1390
16
16
  corvic/engine/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
17
17
  corvic/eorm/__init__.py,sha256=b4dFnu4fW7wj3Y0SMNVXOp8KoKOp_HAL4GyDN-S8fOY,13704
@@ -36,7 +36,7 @@ corvic/op_graph/aggregation.py,sha256=8X6vqXD7dLHrhYJU0BqmhUsWGbzD1zSP5Db5VHdIru
36
36
  corvic/op_graph/encoders.py,sha256=93wYoBCn_us5lRCkqvjaP0LTg3LBB3yEfhzICv06bB0,10460
37
37
  corvic/op_graph/errors.py,sha256=I4NE5053d0deGm5xx5EmyP4f98qx42xnIsW1IA-2hy4,163
38
38
  corvic/op_graph/feature_types.py,sha256=YVbPzvMnHHmUfR5QAMSvQ6hjQcOrIjqR-su0VypYWFA,9627
39
- corvic/op_graph/ops.py,sha256=vKs6lXvXWUqJusp0SKp0y94OOvtJ5KAITejoPMb810w,111833
39
+ corvic/op_graph/ops.py,sha256=aNXcBwrwSyX7seCYqhn0vmlcP-YblphP1ZnRwS3MHl0,112105
40
40
  corvic/op_graph/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
41
41
  corvic/op_graph/row_filters/__init__.py,sha256=1sibH_kLw7t_9bpRccnEGWqdCiN0VaUh9LMMIMCRyL8,575
42
42
  corvic/op_graph/row_filters/_jsonlogic.py,sha256=0UdwOZmIGp4yuExHM3qqAnJYmcGv7iuc3vLub3GD-9Y,7685
@@ -68,7 +68,7 @@ corvic/result/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
68
68
  corvic/sql/__init__.py,sha256=kZ1a39KVZ08P8Bg6XuXDLD_dTQX0k620u4nwxZF4SnY,303
69
69
  corvic/sql/parse_ops.py,sha256=5jm2CHycTqzdu9apXTgcvwwyBVpjf7n5waqKfIa84JA,29940
70
70
  corvic/sql/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
71
- corvic/system/__init__.py,sha256=Qddpk3SoHgoiBJyr9w2bPkp477NZv5MDR8701A17nCY,2697
71
+ corvic/system/__init__.py,sha256=_ETA1pZ5UhjdYHkfTiVGeB82UZCBRhVCB0PM69r4fPI,2735
72
72
  corvic/system/_column_encoding.py,sha256=feSWIv4vKstVq-aavWPk53YucUiq7rZvuyofqTicXBE,7574
73
73
  corvic/system/_dimension_reduction.py,sha256=2tg5SIHY4P480DJQj6PSjW1VgAJCAVJAH8D3BY-ZYXA,2964
74
74
  corvic/system/_embedder.py,sha256=WJC4RtPLoPDDIgquKhpmPmYi2bAoR5_oVkWyBAepJTE,6864
@@ -76,7 +76,7 @@ corvic/system/_image_embedder.py,sha256=Af3MI3VkiZQxCQjgDwaCNNpgEsnAiqfa4bdET63b
76
76
  corvic/system/_planner.py,sha256=ecL-HW8PVz5eWJ1Ktf-RAD2IdZkHu3GuBtXdqElo4ts,8210
77
77
  corvic/system/_text_embedder.py,sha256=NDi--3_tzwIWVImjhFWmp8dHmydGGXNu6GYH8qODsIc,4000
78
78
  corvic/system/client.py,sha256=JcA-fPraqDkl9f8BiClS0qeGY6wzKcEDPymutWrJo54,812
79
- corvic/system/in_memory_executor.py,sha256=KzX8baGFROpv-5hqVC1qOMf7AlPD22ffYtyBesV-W-M,66076
79
+ corvic/system/in_memory_executor.py,sha256=H51fob98zZ8weZtyaWd5TpZHv5KPIW3buTixYqCsOqU,66454
80
80
  corvic/system/op_graph_executor.py,sha256=tSKro-yb_y1_sgajZluM-6FCvDqO1oUPsiWw2DRxyMQ,3641
81
81
  corvic/system/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
82
82
  corvic/system/staging.py,sha256=K5P5moiuAMfPx7lxK4mArxeURBwKoyB6x9HGu9JJ16E,1846
@@ -94,9 +94,9 @@ corvic/version/__init__.py,sha256=JlkRLvKXsu3zIxhdynO_0Ub5NfQOvGjfwCRkNnaOu9U,11
94
94
  corvic/version/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
95
95
  corvic/well_known_types/__init__.py,sha256=Btbeqieik2AcmijeOXeqBptzueBpgNitvH9J5VNm12w,1289
96
96
  corvic/well_known_types/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
97
- corvic_engine-0.3.0rc81.dist-info/METADATA,sha256=xgNR-_243a1DK7ug0D9mgjiwstj5ht4OBfduUojkwMI,1814
98
- corvic_engine-0.3.0rc81.dist-info/WHEEL,sha256=qo08K5WTt1v9liGoFGXfI182ciKs5521XAErJtzFynQ,94
99
- corvic_engine-0.3.0rc81.dist-info/licenses/LICENSE,sha256=DSS1OD0oIgssKOmAzkMRBv5jvvVuZQbrIv8lpl9DXY8,1035
97
+ corvic_engine-0.3.0rc82.dist-info/METADATA,sha256=mFp19x59OwAwoOhqU-H2n1aSOkmYpefdmHVbWovBh-c,1866
98
+ corvic_engine-0.3.0rc82.dist-info/WHEEL,sha256=qo08K5WTt1v9liGoFGXfI182ciKs5521XAErJtzFynQ,94
99
+ corvic_engine-0.3.0rc82.dist-info/licenses/LICENSE,sha256=DSS1OD0oIgssKOmAzkMRBv5jvvVuZQbrIv8lpl9DXY8,1035
100
100
  corvic_generated/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
101
101
  corvic_generated/algorithm/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
102
102
  corvic_generated/algorithm/graph/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -207,4 +207,4 @@ corvic_generated/status/v1/service_pb2.py,sha256=CKXPX2ahq8O4cFhPpt6wo6l--6VZcgj
207
207
  corvic_generated/status/v1/service_pb2.pyi,sha256=iXLR2FOKQJpBgvBzpD2kVwcYOCksP2aRwK4JYaI9CBw,558
208
208
  corvic_generated/status/v1/service_pb2_grpc.py,sha256=y-a5ldrphWlNJW-yKswyjNmXokK4-5bbEEfczjagJHo,2736
209
209
  corvic_generated/status/v1/service_pb2_grpc.pyi,sha256=OoAnaZ64FD0UTzPoRhYvQU8ecoilhHj3ySjSfHbVDaU,1501
210
- corvic_engine-0.3.0rc81.dist-info/RECORD,,
210
+ corvic_engine-0.3.0rc82.dist-info/RECORD,,