data-designer-engine 0.4.0rc3__py3-none-any.whl → 0.5.0rc1__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.
- data_designer/engine/analysis/column_profilers/base.py +1 -2
- data_designer/engine/analysis/dataset_profiler.py +1 -2
- data_designer/engine/column_generators/generators/base.py +1 -6
- data_designer/engine/column_generators/generators/custom.py +195 -0
- data_designer/engine/column_generators/generators/llm_completion.py +32 -5
- data_designer/engine/column_generators/registry.py +3 -0
- data_designer/engine/column_generators/utils/errors.py +3 -0
- data_designer/engine/column_generators/utils/prompt_renderer.py +1 -1
- data_designer/engine/dataset_builders/column_wise_builder.py +23 -5
- data_designer/engine/dataset_builders/multi_column_configs.py +2 -2
- data_designer/engine/mcp/__init__.py +30 -0
- data_designer/engine/mcp/errors.py +22 -0
- data_designer/engine/mcp/facade.py +485 -0
- data_designer/engine/mcp/factory.py +46 -0
- data_designer/engine/mcp/io.py +487 -0
- data_designer/engine/mcp/registry.py +203 -0
- data_designer/engine/model_provider.py +68 -0
- data_designer/engine/models/facade.py +74 -9
- data_designer/engine/models/factory.py +18 -1
- data_designer/engine/models/utils.py +28 -1
- data_designer/engine/resources/resource_provider.py +72 -3
- data_designer/engine/testing/fixtures.py +233 -0
- data_designer/engine/testing/stubs.py +1 -2
- {data_designer_engine-0.4.0rc3.dist-info → data_designer_engine-0.5.0rc1.dist-info}/METADATA +3 -2
- {data_designer_engine-0.4.0rc3.dist-info → data_designer_engine-0.5.0rc1.dist-info}/RECORD +26 -19
- data_designer/engine/_version.py +0 -34
- {data_designer_engine-0.4.0rc3.dist-info → data_designer_engine-0.5.0rc1.dist-info}/WHEEL +0 -0
|
@@ -5,8 +5,7 @@ from __future__ import annotations
|
|
|
5
5
|
|
|
6
6
|
from typing import Literal
|
|
7
7
|
|
|
8
|
-
from data_designer.config.base import ConfigBase
|
|
9
|
-
from data_designer.config.column_configs import SingleColumnConfig
|
|
8
|
+
from data_designer.config.base import ConfigBase, SingleColumnConfig
|
|
10
9
|
from data_designer.engine.column_generators.generators.base import ColumnGeneratorCellByCell
|
|
11
10
|
from data_designer.engine.resources.seed_reader import SeedReader
|
|
12
11
|
from data_designer.plugins.plugin import Plugin, PluginType
|
{data_designer_engine-0.4.0rc3.dist-info → data_designer_engine-0.5.0rc1.dist-info}/METADATA
RENAMED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: data-designer-engine
|
|
3
|
-
Version: 0.
|
|
3
|
+
Version: 0.5.0rc1
|
|
4
4
|
Summary: Generation engine for DataDesigner synthetic data generation
|
|
5
5
|
License-Expression: Apache-2.0
|
|
6
6
|
Classifier: Development Status :: 4 - Beta
|
|
@@ -14,7 +14,7 @@ Classifier: Programming Language :: Python :: 3.13
|
|
|
14
14
|
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
|
|
15
15
|
Requires-Python: >=3.10
|
|
16
16
|
Requires-Dist: anyascii<1,>=0.3.3
|
|
17
|
-
Requires-Dist: data-designer-config
|
|
17
|
+
Requires-Dist: data-designer-config==0.5.0rc1
|
|
18
18
|
Requires-Dist: duckdb<2,>=1.1.3
|
|
19
19
|
Requires-Dist: faker<21,>=20.1.0
|
|
20
20
|
Requires-Dist: httpx-retries<1,>=0.4.2
|
|
@@ -26,6 +26,7 @@ Requires-Dist: jsonschema<5,>=4.0.0
|
|
|
26
26
|
Requires-Dist: litellm<1.80.12,>=1.73.6
|
|
27
27
|
Requires-Dist: lxml<7,>=6.0.2
|
|
28
28
|
Requires-Dist: marko<3,>=2.1.2
|
|
29
|
+
Requires-Dist: mcp<2,>=1.26.0
|
|
29
30
|
Requires-Dist: networkx<4,>=3.0
|
|
30
31
|
Requires-Dist: ruff<1,>=0.14.10
|
|
31
32
|
Requires-Dist: scipy<2,>=1.11.0
|
|
@@ -1,37 +1,37 @@
|
|
|
1
1
|
data_designer/engine/__init__.py,sha256=ObZ6NUPeEvvpGTJ5WIGKUyIrIjaI747OM6ErweRtHxQ,137
|
|
2
|
-
data_designer/engine/_version.py,sha256=DTeqqEr2nu3d0J3qZZfx7FpCHf1Ai3akZDbCReLKmgY,714
|
|
3
2
|
data_designer/engine/compiler.py,sha256=4QAeCJjINtH0afSXygdhiKMyq2KIfaDthK3ApZLgrQ0,4152
|
|
4
3
|
data_designer/engine/configurable_task.py,sha256=6R4FPXPzIeK0lqNVSEXzRDtK14B3dFz38lplr-nkvRE,2539
|
|
5
4
|
data_designer/engine/errors.py,sha256=YXI7ny83BQ16sOK43CpTm384hJTKuZkPTEAjlHlDIfA,1303
|
|
6
|
-
data_designer/engine/model_provider.py,sha256=
|
|
5
|
+
data_designer/engine/model_provider.py,sha256=CkXUKeBTijJgq9yGp5M1sebJEJWLDBlJdA3le3M6j50,5005
|
|
7
6
|
data_designer/engine/secret_resolver.py,sha256=srIAnwbTfsDfgzhWojGTR1u8Vx6SY4vSp0_hJU0_i9A,2468
|
|
8
7
|
data_designer/engine/validation.py,sha256=q9wZqCcRAFoW8p1BtkblFQ3CWgeBHT5JTKVCoYlqZeA,14544
|
|
9
8
|
data_designer/engine/analysis/column_statistics.py,sha256=UW14ooahDgeEdkurgj2d0L6DIX4qce1faWSss_2IR6M,5843
|
|
10
|
-
data_designer/engine/analysis/dataset_profiler.py,sha256=
|
|
9
|
+
data_designer/engine/analysis/dataset_profiler.py,sha256=ajlQEyhuLETvy8Hxaly1G3n-3X-ilMi9wok4X5goEjg,7276
|
|
11
10
|
data_designer/engine/analysis/errors.py,sha256=QRmvkNjcMpQ5QDlM7YOSbR2key4d6dsiknk994Ewvv4,296
|
|
12
|
-
data_designer/engine/analysis/column_profilers/base.py,sha256=
|
|
11
|
+
data_designer/engine/analysis/column_profilers/base.py,sha256=cjk5mvg3S02p-ovBR6AkWhMHonXujWc6ipNdHrODujs,1664
|
|
13
12
|
data_designer/engine/analysis/column_profilers/judge_score_profiler.py,sha256=nSkdb7OumaOWFRq64Abiii43G9MgF3OeOvOH9XpdqFg,6572
|
|
14
13
|
data_designer/engine/analysis/column_profilers/registry.py,sha256=yFEE3gwNUzPI8WMGKfNcObtJSs1b3a87GKrL_ksIqBs,923
|
|
15
14
|
data_designer/engine/analysis/utils/column_statistics_calculations.py,sha256=ry0QxRqLFRn7N4OAn6z7TqSAPEGwxiiUEUtsG_bI-98,8958
|
|
16
15
|
data_designer/engine/analysis/utils/judge_score_processing.py,sha256=QkFMHp0WFhxW3YwwmAnKoEFTULSCxnJ2DSkq8v9kiaE,4884
|
|
17
16
|
data_designer/engine/column_generators/__init__.py,sha256=ObZ6NUPeEvvpGTJ5WIGKUyIrIjaI747OM6ErweRtHxQ,137
|
|
18
|
-
data_designer/engine/column_generators/registry.py,sha256=
|
|
17
|
+
data_designer/engine/column_generators/registry.py,sha256=U8y09tQF54z-CFc-cOdr0s9QxDz1lPkLpfwP7b1SQEI,3312
|
|
19
18
|
data_designer/engine/column_generators/generators/__init__.py,sha256=ObZ6NUPeEvvpGTJ5WIGKUyIrIjaI747OM6ErweRtHxQ,137
|
|
20
|
-
data_designer/engine/column_generators/generators/base.py,sha256=
|
|
19
|
+
data_designer/engine/column_generators/generators/base.py,sha256=s7yTTX6C_tHkghwGa8u3nY9WWF7TakNTZILeeQEwxnw,4149
|
|
20
|
+
data_designer/engine/column_generators/generators/custom.py,sha256=qzrUwR0tZvAvCMgJ26kfZly8UiBK-GSqJv9lryzbaNk,9237
|
|
21
21
|
data_designer/engine/column_generators/generators/embedding.py,sha256=uB0jgHlCgctgIUf9ZfMqG1YThbJ0g-GCX3VdNbdDSko,1407
|
|
22
22
|
data_designer/engine/column_generators/generators/expression.py,sha256=BiQcfVTinvQl3OI9nkdhB9B7FGBueWiHJwxTA8uNVuY,2330
|
|
23
|
-
data_designer/engine/column_generators/generators/llm_completion.py,sha256=
|
|
23
|
+
data_designer/engine/column_generators/generators/llm_completion.py,sha256=uIUdhfNil8vxoBSPDhJuvmVMMqrR3zCpTPGL-BXUyW0,6115
|
|
24
24
|
data_designer/engine/column_generators/generators/samplers.py,sha256=gNzURmu9K8Zb5MHamKvZPIxmWlFgl2W4FIVgaFcy4f0,3371
|
|
25
25
|
data_designer/engine/column_generators/generators/seed_dataset.py,sha256=CoQPbz4Ww7pBLaGw8-CYqIk1sjfkBaoRMKZQexdfgKY,6824
|
|
26
26
|
data_designer/engine/column_generators/generators/validation.py,sha256=YfYbk-8_ZUye0No6_Q7hIqpZv_tunnEZ6HkLSMFXlDE,6659
|
|
27
|
-
data_designer/engine/column_generators/utils/errors.py,sha256=
|
|
27
|
+
data_designer/engine/column_generators/utils/errors.py,sha256=UGKQFqxF8vCUfUa2VectgmLRrIMUTdRRLWlevDyuj0Q,466
|
|
28
28
|
data_designer/engine/column_generators/utils/generator_classification.py,sha256=XBA_vagEXKBQK54OHANKeHw6Mm2B4RuAmXu0QrRdEEo,1958
|
|
29
29
|
data_designer/engine/column_generators/utils/judge_score_factory.py,sha256=gESiqMrQzbbcFpZas0sAAAkrH2DL0Z4Nq5ywBO-pQ6k,2141
|
|
30
|
-
data_designer/engine/column_generators/utils/prompt_renderer.py,sha256=
|
|
30
|
+
data_designer/engine/column_generators/utils/prompt_renderer.py,sha256=lvatLy5UqMmBEZbkJeSdqYR2d7QkHxlNfgbApjr88Dk,4809
|
|
31
31
|
data_designer/engine/dataset_builders/artifact_storage.py,sha256=CKpTBtJTde7OQvsFZQa1v1autVz5yUxlBHkIKeATFnE,10999
|
|
32
|
-
data_designer/engine/dataset_builders/column_wise_builder.py,sha256=
|
|
32
|
+
data_designer/engine/dataset_builders/column_wise_builder.py,sha256=6pQTZ8yKuf0U65dVxla6Zj22FD0KY04RanUlI6pNs20,17431
|
|
33
33
|
data_designer/engine/dataset_builders/errors.py,sha256=gLXtPcGSMBG10PzQ85dOXskdA0mKbBQrHa_VtP9sbVY,400
|
|
34
|
-
data_designer/engine/dataset_builders/multi_column_configs.py,sha256=
|
|
34
|
+
data_designer/engine/dataset_builders/multi_column_configs.py,sha256=a5YaZn-epCk5_sEzp7UuqL3MtN0nGQVQmujqbiY6FSY,1660
|
|
35
35
|
data_designer/engine/dataset_builders/utils/__init__.py,sha256=ObZ6NUPeEvvpGTJ5WIGKUyIrIjaI747OM6ErweRtHxQ,137
|
|
36
36
|
data_designer/engine/dataset_builders/utils/concurrency.py,sha256=Lga_xd8i3ZAPqJlKCB4GHG7uxWxws1m-UGAz9UeqU_8,8283
|
|
37
37
|
data_designer/engine/dataset_builders/utils/config_compiler.py,sha256=NGI6U0vgG88d5YKj7oW_SIJ4-_fhA6VFhPbjqGRHea4,2441
|
|
@@ -39,15 +39,21 @@ data_designer/engine/dataset_builders/utils/dag.py,sha256=RIEI75OtiphkuDl1vfI_MQ
|
|
|
39
39
|
data_designer/engine/dataset_builders/utils/dataset_batch_manager.py,sha256=IfWd_HcfEzIPhgFp2dJaxNIKRlrPsHqYATFXauvCfaw,8133
|
|
40
40
|
data_designer/engine/dataset_builders/utils/errors.py,sha256=G1MIkQDXguSqHK1EP-60FkG_bys7bJ1UgJnSvcNgtt8,411
|
|
41
41
|
data_designer/engine/dataset_builders/utils/progress_tracker.py,sha256=3zSljzDHwhqgP9IqPUR3XbwC231JvLNWslpmhqKIbUg,4255
|
|
42
|
+
data_designer/engine/mcp/__init__.py,sha256=nqUgeDqem73zQYxzdP3zrVGBbNuV8JjY3qzVvbun5JY,853
|
|
43
|
+
data_designer/engine/mcp/errors.py,sha256=V-9tCCWkP_mwXSjfoMZLpoaIuZAa_WSrfOvvd6Pa7jc,542
|
|
44
|
+
data_designer/engine/mcp/facade.py,sha256=kUh8u1vGwkuF-c8swT_-h8KXVmOBjc5lMu0L2dwXiYw,20744
|
|
45
|
+
data_designer/engine/mcp/factory.py,sha256=hA6l10vl6w6C-ZfotbOWYyAsMS7r2VvK1rTtHvpbutY,1714
|
|
46
|
+
data_designer/engine/mcp/io.py,sha256=Mm6etyjwsRkpemDi91kyf2ccz5AWNdrd1ASAStm3Rbw,19232
|
|
47
|
+
data_designer/engine/mcp/registry.py,sha256=ZQuKiufPQBySvRcoiH-0LsiEs_W05P4zf4byVOIGrBc,7807
|
|
42
48
|
data_designer/engine/models/__init__.py,sha256=ObZ6NUPeEvvpGTJ5WIGKUyIrIjaI747OM6ErweRtHxQ,137
|
|
43
49
|
data_designer/engine/models/errors.py,sha256=k9oZnmk8DRD8U2SVKJJRLwrcdsCcVoJiOb_Q7ZyEdvg,12271
|
|
44
|
-
data_designer/engine/models/facade.py,sha256=
|
|
45
|
-
data_designer/engine/models/factory.py,sha256=
|
|
50
|
+
data_designer/engine/models/facade.py,sha256=slTZvCDD3Av5-OwYA7EdTorKxQnO682ubII0IpgyqFo,15341
|
|
51
|
+
data_designer/engine/models/factory.py,sha256=LEYP2omzAv0taZ9o4BzEbCXvGMA0DCiupcREX6wmk_8,2243
|
|
46
52
|
data_designer/engine/models/litellm_overrides.py,sha256=e9IZCFQ6BhNWlOTncm8ErL8w4rtE1_4USh2mtUYxCZI,6207
|
|
47
53
|
data_designer/engine/models/registry.py,sha256=Bid7Mv_ebzbTrlfzN-1wbcFxp_qQwilL0h2iwN5UPJ0,7099
|
|
48
54
|
data_designer/engine/models/telemetry.py,sha256=_VZR6Iatr6-5Hypw3bes5Jr4y7Y3VagxFEVAv36eHcE,12733
|
|
49
55
|
data_designer/engine/models/usage.py,sha256=A0LV9Ycuj_7snOsaqnirs4mlkAjozv2mzj2om2FpDoU,2410
|
|
50
|
-
data_designer/engine/models/utils.py,sha256=
|
|
56
|
+
data_designer/engine/models/utils.py,sha256=FVQ0AAVj8Qt9DjzqGJEjCTLWQg3l5H_JbiJXj0g3iV0,4627
|
|
51
57
|
data_designer/engine/models/parsers/__init__.py,sha256=ObZ6NUPeEvvpGTJ5WIGKUyIrIjaI747OM6ErweRtHxQ,137
|
|
52
58
|
data_designer/engine/models/parsers/errors.py,sha256=ODcZ4TOsmZyH4-MoNkKXhjiMm_4gLWPsz90qKtNF9_Q,1053
|
|
53
59
|
data_designer/engine/models/parsers/parser.py,sha256=XkdDt2WEnolvsv2bArq4hhujfJ3kLmG6G2jkRXMYA8c,9489
|
|
@@ -77,7 +83,7 @@ data_designer/engine/registry/errors.py,sha256=k1EaV7egNQwNmRsI8EfymTfeNprcDutPf
|
|
|
77
83
|
data_designer/engine/resources/managed_dataset_generator.py,sha256=2wGc-tH5usXAPXgDkXzslLsCkAsAQgYa3uIYJC5_Oa0,1495
|
|
78
84
|
data_designer/engine/resources/managed_dataset_repository.py,sha256=lx8NTtAPxheZdqkgilYSmqZv4Nd_CeHXXUaXHzGLLVk,7684
|
|
79
85
|
data_designer/engine/resources/managed_storage.py,sha256=8tLJjKGvDbuHnsESL2VZVu9vfEH3--OLZaiZe-LZo_8,2120
|
|
80
|
-
data_designer/engine/resources/resource_provider.py,sha256
|
|
86
|
+
data_designer/engine/resources/resource_provider.py,sha256=-SxgMx7a0bwnNJg3EUWQpesJ6tmzALkRkSXiKtyXTWc,5732
|
|
81
87
|
data_designer/engine/resources/seed_reader.py,sha256=GQiOqf9t-yRag2g5Io3-kQPhpyKJbXgHn2YTUoAgftI,5717
|
|
82
88
|
data_designer/engine/sampling_gen/column.py,sha256=0aQzeJtcM0DNEaarG1ybXV4LLJH0iiOaXvi46Ay4qOE,3987
|
|
83
89
|
data_designer/engine/sampling_gen/constraints.py,sha256=AvFoyZ1QU--R9kGyIaPHClm3mG_ZoPuOE3IQQqYUPqw,3157
|
|
@@ -101,7 +107,8 @@ data_designer/engine/sampling_gen/entities/person.py,sha256=9S-xAj6_8ZaFX4G_I7CM
|
|
|
101
107
|
data_designer/engine/sampling_gen/entities/phone_number.py,sha256=dGY5LRwCz19RBH0mJDTpnBb0a98piDSNgkQRemgwqV0,4818
|
|
102
108
|
data_designer/engine/sampling_gen/entities/assets/zip_area_code_map.parquet,sha256=L6G4laXExB7uRCWHlF4XGDk0yMh41jbDnp9LIy7jNHM,576064
|
|
103
109
|
data_designer/engine/testing/__init__.py,sha256=ICYoOcewhvzZmuaF4A8fn-LDaaOBGhBQf-RQ9QyNdhs,396
|
|
104
|
-
data_designer/engine/testing/
|
|
110
|
+
data_designer/engine/testing/fixtures.py,sha256=8SD3sZV_Kl3gN7VvQgdd-VXj3d1UvIMEFYqrmmkexV4,7574
|
|
111
|
+
data_designer/engine/testing/stubs.py,sha256=qDyHNAGQj0KUfxfFJzShs5_7tkFKI9VzvEfWAttmZlE,3870
|
|
105
112
|
data_designer/engine/testing/utils.py,sha256=a9LEgK827cnIzHEkgXOdgywrKDLBE36cyttrpG1ctT4,973
|
|
106
113
|
data_designer/engine/validators/__init__.py,sha256=uT0CTJF9Ce97zoAdMSWvfYn7mO5ja0lIgyPRKJLcsOU,693
|
|
107
114
|
data_designer/engine/validators/base.py,sha256=XfDDMMP0PusoKAjM9rXdIYkyWlLiQPAJChMgtkcdspw,1005
|
|
@@ -109,6 +116,6 @@ data_designer/engine/validators/local_callable.py,sha256=JaL-yOXrTFpubiO2QlSt4Qb
|
|
|
109
116
|
data_designer/engine/validators/python.py,sha256=omXjwMaomQYiyq4g6XqKt2wexVuI_rWue9Dk-CYc-do,8039
|
|
110
117
|
data_designer/engine/validators/remote.py,sha256=rythhIrH2GvqncMQeF3FiJa9Om0KZWeK3cWjW-ZubaM,3077
|
|
111
118
|
data_designer/engine/validators/sql.py,sha256=AMaEdA-gj9j0zwVp809x3ycKltd51wVEhI8mMYGyxd4,2408
|
|
112
|
-
data_designer_engine-0.
|
|
113
|
-
data_designer_engine-0.
|
|
114
|
-
data_designer_engine-0.
|
|
119
|
+
data_designer_engine-0.5.0rc1.dist-info/METADATA,sha256=6hK0RVqcTc01Q8xJ8X_j4PGuFJt0lH6OovrfdMExqVI,1916
|
|
120
|
+
data_designer_engine-0.5.0rc1.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
|
|
121
|
+
data_designer_engine-0.5.0rc1.dist-info/RECORD,,
|
data_designer/engine/_version.py
DELETED
|
@@ -1,34 +0,0 @@
|
|
|
1
|
-
# file generated by setuptools-scm
|
|
2
|
-
# don't change, don't track in version control
|
|
3
|
-
|
|
4
|
-
__all__ = [
|
|
5
|
-
"__version__",
|
|
6
|
-
"__version_tuple__",
|
|
7
|
-
"version",
|
|
8
|
-
"version_tuple",
|
|
9
|
-
"__commit_id__",
|
|
10
|
-
"commit_id",
|
|
11
|
-
]
|
|
12
|
-
|
|
13
|
-
TYPE_CHECKING = False
|
|
14
|
-
if TYPE_CHECKING:
|
|
15
|
-
from typing import Tuple
|
|
16
|
-
from typing import Union
|
|
17
|
-
|
|
18
|
-
VERSION_TUPLE = Tuple[Union[int, str], ...]
|
|
19
|
-
COMMIT_ID = Union[str, None]
|
|
20
|
-
else:
|
|
21
|
-
VERSION_TUPLE = object
|
|
22
|
-
COMMIT_ID = object
|
|
23
|
-
|
|
24
|
-
version: str
|
|
25
|
-
__version__: str
|
|
26
|
-
__version_tuple__: VERSION_TUPLE
|
|
27
|
-
version_tuple: VERSION_TUPLE
|
|
28
|
-
commit_id: COMMIT_ID
|
|
29
|
-
__commit_id__: COMMIT_ID
|
|
30
|
-
|
|
31
|
-
__version__ = version = '0.4.0rc3'
|
|
32
|
-
__version_tuple__ = version_tuple = (0, 4, 0, 'rc3')
|
|
33
|
-
|
|
34
|
-
__commit_id__ = commit_id = None
|
|
File without changes
|