weave-python 0.10.0__py3-none-any.whl

weave/datamanagement/db/models.py

@@ -0,0 +1,131 @@
+# Code generated by sqlc. DO NOT EDIT.
+# versions:
+#   sqlc v1.28.0
+import dataclasses
+import datetime
+import enum
+from typing import Any, Optional
+import uuid
+
+
+class StorageCategory(enum.StrEnum):
+    OBJECT_STORE = "object_store"
+    SQL_DATABASE = "sql_database"
+    NOSQL_DATABASE = "nosql_database"
+
+
+class StorageVariant(enum.StrEnum):
+    AWS_S3 = "aws_s3"
+    AZURE_BLOB_STORAGE = "azure_blob_storage"
+    GOOGLE_CLOUD_STORAGE = "google_cloud_storage"
+    MYSQL = "mysql"
+    POSTGRES = "postgres"
+    SQL_SERVER = "sql_server"
+    ORACLE = "oracle"
+    MARIADB = "mariadb"
+    SNOWFLAKE = "snowflake"
+    BIGQUERY = "bigquery"
+    DATABRICKS = "databricks"
+    CASSANDRA = "cassandra"
+    MONGODB = "mongodb"
+    DYNAMODB = "dynamodb"
+    COSMOSDB = "cosmosdb"
+    REDIS = "redis"
+    VALKEY = "valkey"
+    ELASTICSEARCH = "elasticsearch"
+    OPENSEARCH = "opensearch"
+
+
+class SynthesizeV1ColumnDataType(enum.StrEnum):
+    STRING = "string"
+    INTEGER = "integer"
+    FLOAT = "float"
+    BOOLEAN = "boolean"
+    TIMESTAMP = "timestamp"
+    DATE = "date"
+    BINARY = "binary"
+    CATEGORICAL = "categorical"
+    ORDINAL = "ordinal"
+
+
+class SynthesizeV1ColumnRelationshipType(enum.StrEnum):
+    CONTEXT_FOREIGN_KEY = "context_foreign_key"
+    NON_CONTEXT_FOREIGN_KEY = "non_context_foreign_key"
+    ONE_TO_MANY = "one_to_many"
+    MANY_TO_ONE = "many_to_one"
+    MANY_TO_MANY = "many_to_many"
+    SELF_REFERENCE = "self_reference"
+
+
+@dataclasses.dataclass()
+class Organization:
+    id: uuid.UUID
+    name: str
+    description: Optional[str]
+
+
+@dataclasses.dataclass()
+class StorageConnection:
+    id: uuid.UUID
+    organization_id: uuid.UUID
+    name: str
+    description: Optional[str]
+    category: StorageCategory
+    variant: StorageVariant
+    details: Any
+
+
+@dataclasses.dataclass()
+class SynthesizeV1ColumnRelationship:
+    id: uuid.UUID
+    source_column_id: uuid.UUID
+    source_dataset_id: uuid.UUID
+    target_column_id: uuid.UUID
+    target_dataset_id: uuid.UUID
+    relationship_type: Any
+
+
+@dataclasses.dataclass()
+class SynthesizeV1DataColumn:
+    id: uuid.UUID
+    schema_id: uuid.UUID
+    name: str
+    data_type: Any
+    is_primary_key: Optional[bool]
+    description: Optional[str]
+
+
+@dataclasses.dataclass()
+class SynthesizeV1DataSchema:
+    id: uuid.UUID
+    organization_id: uuid.UUID
+    name: str
+    description: Optional[str]
+
+
+@dataclasses.dataclass()
+class SynthesizeV1Dataset:
+    id: uuid.UUID
+    organization_id: uuid.UUID
+    name: str
+    description: Optional[str]
+    storage_connection_id: uuid.UUID
+    schema_id: uuid.UUID
+    model_id: Optional[uuid.UUID]
+    is_synthetic: Optional[bool]
+
+
+@dataclasses.dataclass()
+class SynthesizeV1Model:
+    id: uuid.UUID
+    organization_id: uuid.UUID
+    name: str
+    description: Optional[str]
+    created_at: Optional[datetime.datetime]
+    configuration: Optional[Any]
+    storage_connection_id: uuid.UUID
+    storage_bucket: str
+    storage_key: str
+    model_type: str
+    model_version: Optional[str]
+    metadata: Optional[Any]

weave/datamanagement/db/queries.py

@@ -0,0 +1,140 @@
+# Code generated by sqlc. DO NOT EDIT.
+# versions:
+#   sqlc v1.28.0
+# source: queries.sql
+import dataclasses
+from typing import AsyncIterator, Iterator, List, Optional
+import uuid
+
+import sqlalchemy
+import sqlalchemy.ext.asyncio
+
+from weave.datamanagement.db import models
+
+
+GET_FOREIGN_KEY_RELATIONSHIPS = """-- name: get_foreign_key_relationships \\:many
+SELECT 
+    cr.source_dataset_id,
+    cr.target_dataset_id,
+    sc.name AS source_column_name,
+    tc.name AS target_column_name
+FROM 
+    synthesize_v1.column_relationship cr
+JOIN 
+    synthesize_v1.data_column sc ON cr.source_column_id = sc.id
+JOIN 
+    synthesize_v1.data_column tc ON cr.target_column_id = tc.id
+WHERE 
+    cr.relationship_type IN ('context_foreign_key', 'non_context_foreign_key')
+    AND cr.source_dataset_id = ANY(:p1\\:\\:UUID[])
+    AND cr.target_dataset_id = ANY(:p1\\:\\:UUID[])
+"""
+
+
+@dataclasses.dataclass()
+class GetForeignKeyRelationshipsRow:
+    source_dataset_id: uuid.UUID
+    target_dataset_id: uuid.UUID
+    source_column_name: str
+    target_column_name: str
+
+
+GET_STORAGE_CONNECTION = """-- name: get_storage_connection \\:one
+SELECT id, organization_id, name, description, category, variant, details
+FROM storage_connection
+WHERE id = :p1
+"""
+
+
+GET_STORAGE_CONNECTION_BY_DATASET_ID = """-- name: get_storage_connection_by_dataset_id \\:one
+SELECT sc.id, sc.organization_id, sc.name, sc.description, sc.category, sc.variant, sc.details
+FROM storage_connection sc
+JOIN synthesize_v1.dataset d ON d.storage_connection_id = sc.id
+WHERE d.id = :p1
+"""
+
+
+class Querier:
+    def __init__(self, conn: sqlalchemy.engine.Connection):
+        self._conn = conn
+
+    def get_foreign_key_relationships(self, *, dataset_ids: List[uuid.UUID]) -> Iterator[GetForeignKeyRelationshipsRow]:
+        result = self._conn.execute(sqlalchemy.text(GET_FOREIGN_KEY_RELATIONSHIPS), {"p1": dataset_ids})
+        for row in result:
+            yield GetForeignKeyRelationshipsRow(
+                source_dataset_id=row[0],
+                target_dataset_id=row[1],
+                source_column_name=row[2],
+                target_column_name=row[3],
+            )
+
+    def get_storage_connection(self, *, id: uuid.UUID) -> Optional[models.StorageConnection]:
+        row = self._conn.execute(sqlalchemy.text(GET_STORAGE_CONNECTION), {"p1": id}).first()
+        if row is None:
+            return None
+        return models.StorageConnection(
+            id=row[0],
+            organization_id=row[1],
+            name=row[2],
+            description=row[3],
+            category=row[4],
+            variant=row[5],
+            details=row[6],
+        )
+
+    def get_storage_connection_by_dataset_id(self, *, dataset_id: uuid.UUID) -> Optional[models.StorageConnection]:
+        row = self._conn.execute(sqlalchemy.text(GET_STORAGE_CONNECTION_BY_DATASET_ID), {"p1": dataset_id}).first()
+        if row is None:
+            return None
+        return models.StorageConnection(
+            id=row[0],
+            organization_id=row[1],
+            name=row[2],
+            description=row[3],
+            category=row[4],
+            variant=row[5],
+            details=row[6],
+        )
+
+
+class AsyncQuerier:
+    def __init__(self, conn: sqlalchemy.ext.asyncio.AsyncConnection):
+        self._conn = conn
+
+    async def get_foreign_key_relationships(self, *, dataset_ids: List[uuid.UUID]) -> AsyncIterator[GetForeignKeyRelationshipsRow]:
+        result = await self._conn.stream(sqlalchemy.text(GET_FOREIGN_KEY_RELATIONSHIPS), {"p1": dataset_ids})
+        async for row in result:
+            yield GetForeignKeyRelationshipsRow(
+                source_dataset_id=row[0],
+                target_dataset_id=row[1],
+                source_column_name=row[2],
+                target_column_name=row[3],
+            )
+
+    async def get_storage_connection(self, *, id: uuid.UUID) -> Optional[models.StorageConnection]:
+        row = (await self._conn.execute(sqlalchemy.text(GET_STORAGE_CONNECTION), {"p1": id})).first()
+        if row is None:
+            return None
+        return models.StorageConnection(
+            id=row[0],
+            organization_id=row[1],
+            name=row[2],
+            description=row[3],
+            category=row[4],
+            variant=row[5],
+            details=row[6],
+        )
+
+    async def get_storage_connection_by_dataset_id(self, *, dataset_id: uuid.UUID) -> Optional[models.StorageConnection]:
+        row = (await self._conn.execute(sqlalchemy.text(GET_STORAGE_CONNECTION_BY_DATASET_ID), {"p1": dataset_id})).first()
+        if row is None:
+            return None
+        return models.StorageConnection(
+            id=row[0],
+            organization_id=row[1],
+            name=row[2],
+            description=row[3],
+            category=row[4],
+            variant=row[5],
+            details=row[6],
+        )

weave/datamanagement/generate/v1/configuration_pb2.py

@@ -0,0 +1,51 @@
+# -*- coding: utf-8 -*-
+# Generated by the protocol buffer compiler.  DO NOT EDIT!
+# NO CHECKED-IN PROTOBUF GENCODE
+# source: weave/datamanagement/generate/v1/configuration.proto
+# Protobuf Python Version: 6.30.2
+"""Generated protocol buffer code."""
+from google.protobuf import descriptor as _descriptor
+from google.protobuf import descriptor_pool as _descriptor_pool
+from google.protobuf import runtime_version as _runtime_version
+from google.protobuf import symbol_database as _symbol_database
+from google.protobuf.internal import builder as _builder
+_runtime_version.ValidateProtobufRuntimeVersion(
+    _runtime_version.Domain.PUBLIC,
+    6,
+    30,
+    2,
+    '',
+    'weave/datamanagement/generate/v1/configuration.proto'
+)
+# @@protoc_insertion_point(imports)
+
+_sym_db = _symbol_database.Default()
+
+
+
+
+DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n4weave/datamanagement/generate/v1/configuration.proto\x12 weave.datamanagement.generate.v1\"\xbb\x02\n\rConfiguration\x12\x1f\n\x0bnum_records\x18\x01 \x01(\x03R\nnumRecords\x12!\n\x0c\x64\x61taset_name\x18\x02 \x01(\tR\x0b\x64\x61tasetName\x12V\n\x0c\x64\x61ta_quality\x18\x03 \x01(\x0b\x32\x33.weave.datamanagement.generate.v1.DataQualityConfigR\x0b\x64\x61taQuality\x12I\n\x07privacy\x18\x04 \x01(\x0b\x32/.weave.datamanagement.generate.v1.PrivacyConfigR\x07privacy\x12\x43\n\x05model\x18\x05 \x01(\x0b\x32-.weave.datamanagement.generate.v1.ModelConfigR\x05model\"\xb1\x02\n\x11\x44\x61taQualityConfig\x12\x31\n\x14\x63orrelation_accuracy\x18\x01 \x01(\x02R\x13\x63orrelationAccuracy\x12\x35\n\x16statistical_similarity\x18\x02 \x01(\x02R\x15statisticalSimilarity\x12+\n\x11preserve_outliers\x18\x03 \x01(\x08R\x10preserveOutliers\x12/\n\x13\x65nforce_constraints\x18\x04 \x01(\x08R\x12\x65nforceConstraints\x12T\n\x0b\x63onstraints\x18\x05 \x03(\x0b\x32\x32.weave.datamanagement.generate.v1.ColumnConstraintR\x0b\x63onstraints\"\xe2\x01\n\x10\x43olumnConstraint\x12\x1f\n\x0b\x63olumn_name\x18\x01 \x01(\tR\ncolumnName\x12\'\n\x0f\x63onstraint_type\x18\x02 \x01(\tR\x0e\x63onstraintType\x12\x1b\n\tmin_value\x18\x03 \x01(\tR\x08minValue\x12\x1b\n\tmax_value\x18\x04 \x01(\tR\x08maxValue\x12#\n\rregex_pattern\x18\x05 \x01(\tR\x0cregexPattern\x12%\n\x0e\x61llowed_values\x18\x06 \x03(\tR\rallowedValues\"\xd1\x01\n\rPrivacyConfig\x12\x18\n\x07\x65psilon\x18\x01 \x01(\x02R\x07\x65psilon\x12*\n\x11k_anonymity_check\x18\x02 \x01(\x08R\x0fkAnonymityCheck\x12\x17\n\x07k_value\x18\x03 \x01(\x05R\x06kValue\x12+\n\x11sensitive_columns\x18\x04 \x03(\tR\x10sensitiveColumns\x12\x34\n\x16\x65nable_privacy_metrics\x18\x05 \x01(\x08R\x14\x65nablePrivacyMetrics\"\xec\x02\n\x0bModelConfig\x12J\n\nmodel_type\x18\x01 \x01(\x0e\x32+.weave.datamanagement.generate.v1.ModelTypeR\tmodelType\x12\x16\n\x06\x65pochs\x18\x02 \x01(\x05R\x06\x65pochs\x12#\n\rlearning_rate\x18\x03 \x01(\x02R\x0clearningRate\x12\x1d\n\nbatch_size\x18\x04 \x01(\x05R\tbatchSize\x12p\n\x11\x63ustom_parameters\x18\x05 \x03(\x0b\x32\x43.weave.datamanagement.generate.v1.ModelConfig.CustomParametersEntryR\x10\x63ustomParameters\x1a\x43\n\x15\x43ustomParametersEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12\x14\n\x05value\x18\x02 \x01(\tR\x05value:\x02\x38\x01*\xea\x01\n\tModelType\x12\x1a\n\x16MODEL_TYPE_UNSPECIFIED\x10\x00\x12\x14\n\x10MODEL_TYPE_CTGAN\x10\x01\x12\x13\n\x0fMODEL_TYPE_TVAE\x10\x02\x12\x15\n\x11MODEL_TYPE_COPULA\x10\x03\x12\x13\n\x0fMODEL_TYPE_FAST\x10\x04\x12\x12\n\x0eMODEL_TYPE_GAN\x10\x05\x12\x13\n\x0fMODEL_TYPE_WGAN\x10\x06\x12\x14\n\x10MODEL_TYPE_SMOTE\x10\x07\x12\x17\n\x13MODEL_TYPE_BAYESIAN\x10\x08\x12\x12\n\x0eMODEL_TYPE_HMA\x10\tB\xa7\x02\n$com.weave.datamanagement.generate.v1B\x12\x43onfigurationProtoP\x01ZHgithub.com/weave-labs/weave-go/weave/datamanagement/generate/v1;generate\xa2\x02\x03WDG\xaa\x02 Weave.Datamanagement.Generate.V1\xca\x02 Weave\\Datamanagement\\Generate\\V1\xe2\x02,Weave\\Datamanagement\\Generate\\V1\\GPBMetadata\xea\x02#Weave::Datamanagement::Generate::V1b\x06proto3')
+
+_globals = globals()
+_builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, _globals)
+_builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, 'weave.datamanagement.generate.v1.configuration_pb2', _globals)
+if not _descriptor._USE_C_DESCRIPTORS:
+  _globals['DESCRIPTOR']._loaded_options = None
+  _globals['DESCRIPTOR']._serialized_options = b'\n$com.weave.datamanagement.generate.v1B\022ConfigurationProtoP\001ZHgithub.com/weave-labs/weave-go/weave/datamanagement/generate/v1;generate\242\002\003WDG\252\002 Weave.Datamanagement.Generate.V1\312\002 Weave\\Datamanagement\\Generate\\V1\342\002,Weave\\Datamanagement\\Generate\\V1\\GPBMetadata\352\002#Weave::Datamanagement::Generate::V1'
+  _globals['_MODELCONFIG_CUSTOMPARAMETERSENTRY']._loaded_options = None
+  _globals['_MODELCONFIG_CUSTOMPARAMETERSENTRY']._serialized_options = b'8\001'
+  _globals['_MODELTYPE']._serialized_start=1525
+  _globals['_MODELTYPE']._serialized_end=1759
+  _globals['_CONFIGURATION']._serialized_start=91
+  _globals['_CONFIGURATION']._serialized_end=406
+  _globals['_DATAQUALITYCONFIG']._serialized_start=409
+  _globals['_DATAQUALITYCONFIG']._serialized_end=714
+  _globals['_COLUMNCONSTRAINT']._serialized_start=717
+  _globals['_COLUMNCONSTRAINT']._serialized_end=943
+  _globals['_PRIVACYCONFIG']._serialized_start=946
+  _globals['_PRIVACYCONFIG']._serialized_end=1155
+  _globals['_MODELCONFIG']._serialized_start=1158
+  _globals['_MODELCONFIG']._serialized_end=1522
+  _globals['_MODELCONFIG_CUSTOMPARAMETERSENTRY']._serialized_start=1455
+  _globals['_MODELCONFIG_CUSTOMPARAMETERSENTRY']._serialized_end=1522
+# @@protoc_insertion_point(module_scope)

weave/datamanagement/generate/v1/configuration_pb2.pyi

@@ -0,0 +1,283 @@
+"""
+@generated by mypy-protobuf.  Do not edit manually!
+isort:skip_file
+"""
+
+import builtins
+import collections.abc
+import google.protobuf.descriptor
+import google.protobuf.internal.containers
+import google.protobuf.internal.enum_type_wrapper
+import google.protobuf.message
+import sys
+import typing
+
+if sys.version_info >= (3, 10):
+    import typing as typing_extensions
+else:
+    import typing_extensions
+
+DESCRIPTOR: google.protobuf.descriptor.FileDescriptor
+
+class _ModelType:
+    ValueType = typing.NewType("ValueType", builtins.int)
+    V: typing_extensions.TypeAlias = ValueType
+
+class _ModelTypeEnumTypeWrapper(google.protobuf.internal.enum_type_wrapper._EnumTypeWrapper[_ModelType.ValueType], builtins.type):
+    DESCRIPTOR: google.protobuf.descriptor.EnumDescriptor
+    MODEL_TYPE_UNSPECIFIED: _ModelType.ValueType  # 0
+    MODEL_TYPE_CTGAN: _ModelType.ValueType  # 1
+    """Conditional Tabular GAN"""
+    MODEL_TYPE_TVAE: _ModelType.ValueType  # 2
+    """Tabular Variational Autoencoder"""
+    MODEL_TYPE_COPULA: _ModelType.ValueType  # 3
+    """Gaussian Copula"""
+    MODEL_TYPE_FAST: _ModelType.ValueType  # 4
+    """Fast mode (less accurate but quicker)"""
+    MODEL_TYPE_GAN: _ModelType.ValueType  # 5
+    """Generic GAN implementation"""
+    MODEL_TYPE_WGAN: _ModelType.ValueType  # 6
+    """Wasserstein GAN"""
+    MODEL_TYPE_SMOTE: _ModelType.ValueType  # 7
+    """Synthetic Minority Over-sampling Technique"""
+    MODEL_TYPE_BAYESIAN: _ModelType.ValueType  # 8
+    """Bayesian Network"""
+    MODEL_TYPE_HMA: _ModelType.ValueType  # 9
+    """Hierarchical Modeling Algorithm"""
+
+class ModelType(_ModelType, metaclass=_ModelTypeEnumTypeWrapper):
+    """ModelType defines the available synthetic data generation models"""
+
+MODEL_TYPE_UNSPECIFIED: ModelType.ValueType  # 0
+MODEL_TYPE_CTGAN: ModelType.ValueType  # 1
+"""Conditional Tabular GAN"""
+MODEL_TYPE_TVAE: ModelType.ValueType  # 2
+"""Tabular Variational Autoencoder"""
+MODEL_TYPE_COPULA: ModelType.ValueType  # 3
+"""Gaussian Copula"""
+MODEL_TYPE_FAST: ModelType.ValueType  # 4
+"""Fast mode (less accurate but quicker)"""
+MODEL_TYPE_GAN: ModelType.ValueType  # 5
+"""Generic GAN implementation"""
+MODEL_TYPE_WGAN: ModelType.ValueType  # 6
+"""Wasserstein GAN"""
+MODEL_TYPE_SMOTE: ModelType.ValueType  # 7
+"""Synthetic Minority Over-sampling Technique"""
+MODEL_TYPE_BAYESIAN: ModelType.ValueType  # 8
+"""Bayesian Network"""
+MODEL_TYPE_HMA: ModelType.ValueType  # 9
+"""Hierarchical Modeling Algorithm"""
+global___ModelType = ModelType
+
+@typing.final
+class Configuration(google.protobuf.message.Message):
+    """SynthesizerConfig defines customization options for synthetic data generation"""
+
+    DESCRIPTOR: google.protobuf.descriptor.Descriptor
+
+    NUM_RECORDS_FIELD_NUMBER: builtins.int
+    DATASET_NAME_FIELD_NUMBER: builtins.int
+    DATA_QUALITY_FIELD_NUMBER: builtins.int
+    PRIVACY_FIELD_NUMBER: builtins.int
+    MODEL_FIELD_NUMBER: builtins.int
+    num_records: builtins.int
+    """Basic configuration
+    Number of synthetic records to generate
+    """
+    dataset_name: builtins.str
+    """Name for the generated dataset"""
+    @property
+    def data_quality(self) -> global___DataQualityConfig:
+        """Data quality settings
+        Controls data quality aspects
+        """
+
+    @property
+    def privacy(self) -> global___PrivacyConfig:
+        """Privacy settings
+        Privacy and anonymization settings
+        """
+
+    @property
+    def model(self) -> global___ModelConfig:
+        """Advanced model configuration
+        ML model configuration options
+        """
+
+    def __init__(
+        self,
+        *,
+        num_records: builtins.int = ...,
+        dataset_name: builtins.str = ...,
+        data_quality: global___DataQualityConfig | None = ...,
+        privacy: global___PrivacyConfig | None = ...,
+        model: global___ModelConfig | None = ...,
+    ) -> None: ...
+    def HasField(self, field_name: typing.Literal["data_quality", b"data_quality", "model", b"model", "privacy", b"privacy"]) -> builtins.bool: ...
+    def ClearField(self, field_name: typing.Literal["data_quality", b"data_quality", "dataset_name", b"dataset_name", "model", b"model", "num_records", b"num_records", "privacy", b"privacy"]) -> None: ...
+
+global___Configuration = Configuration
+
+@typing.final
+class DataQualityConfig(google.protobuf.message.Message):
+    """DataQualityConfig controls the quality of generated data"""
+
+    DESCRIPTOR: google.protobuf.descriptor.Descriptor
+
+    CORRELATION_ACCURACY_FIELD_NUMBER: builtins.int
+    STATISTICAL_SIMILARITY_FIELD_NUMBER: builtins.int
+    PRESERVE_OUTLIERS_FIELD_NUMBER: builtins.int
+    ENFORCE_CONSTRAINTS_FIELD_NUMBER: builtins.int
+    CONSTRAINTS_FIELD_NUMBER: builtins.int
+    correlation_accuracy: builtins.float
+    """How closely to maintain correlations (0.0-1.0)"""
+    statistical_similarity: builtins.float
+    """Statistical similarity to original data (0.0-1.0)"""
+    preserve_outliers: builtins.bool
+    """Whether to preserve outlier patterns"""
+    enforce_constraints: builtins.bool
+    """Whether to enforce data constraints"""
+    @property
+    def constraints(self) -> google.protobuf.internal.containers.RepeatedCompositeFieldContainer[global___ColumnConstraint]:
+        """Column-specific constraints"""
+
+    def __init__(
+        self,
+        *,
+        correlation_accuracy: builtins.float = ...,
+        statistical_similarity: builtins.float = ...,
+        preserve_outliers: builtins.bool = ...,
+        enforce_constraints: builtins.bool = ...,
+        constraints: collections.abc.Iterable[global___ColumnConstraint] | None = ...,
+    ) -> None: ...
+    def ClearField(self, field_name: typing.Literal["constraints", b"constraints", "correlation_accuracy", b"correlation_accuracy", "enforce_constraints", b"enforce_constraints", "preserve_outliers", b"preserve_outliers", "statistical_similarity", b"statistical_similarity"]) -> None: ...
+
+global___DataQualityConfig = DataQualityConfig
+
+@typing.final
+class ColumnConstraint(google.protobuf.message.Message):
+    """ColumnConstraint defines constraints for specific columns"""
+
+    DESCRIPTOR: google.protobuf.descriptor.Descriptor
+
+    COLUMN_NAME_FIELD_NUMBER: builtins.int
+    CONSTRAINT_TYPE_FIELD_NUMBER: builtins.int
+    MIN_VALUE_FIELD_NUMBER: builtins.int
+    MAX_VALUE_FIELD_NUMBER: builtins.int
+    REGEX_PATTERN_FIELD_NUMBER: builtins.int
+    ALLOWED_VALUES_FIELD_NUMBER: builtins.int
+    column_name: builtins.str
+    """Name of the column"""
+    constraint_type: builtins.str
+    """Type of constraint (e.g., "range", "regex", "categorical")"""
+    min_value: builtins.str
+    """Minimum value (for numeric constraints)"""
+    max_value: builtins.str
+    """Maximum value (for numeric constraints)"""
+    regex_pattern: builtins.str
+    """Regex pattern (for string constraints)"""
+    @property
+    def allowed_values(self) -> google.protobuf.internal.containers.RepeatedScalarFieldContainer[builtins.str]:
+        """List of allowed values (for categorical constraints)"""
+
+    def __init__(
+        self,
+        *,
+        column_name: builtins.str = ...,
+        constraint_type: builtins.str = ...,
+        min_value: builtins.str = ...,
+        max_value: builtins.str = ...,
+        regex_pattern: builtins.str = ...,
+        allowed_values: collections.abc.Iterable[builtins.str] | None = ...,
+    ) -> None: ...
+    def ClearField(self, field_name: typing.Literal["allowed_values", b"allowed_values", "column_name", b"column_name", "constraint_type", b"constraint_type", "max_value", b"max_value", "min_value", b"min_value", "regex_pattern", b"regex_pattern"]) -> None: ...
+
+global___ColumnConstraint = ColumnConstraint
+
+@typing.final
+class PrivacyConfig(google.protobuf.message.Message):
+    """PrivacyConfig controls privacy aspects of synthetic data"""
+
+    DESCRIPTOR: google.protobuf.descriptor.Descriptor
+
+    EPSILON_FIELD_NUMBER: builtins.int
+    K_ANONYMITY_CHECK_FIELD_NUMBER: builtins.int
+    K_VALUE_FIELD_NUMBER: builtins.int
+    SENSITIVE_COLUMNS_FIELD_NUMBER: builtins.int
+    ENABLE_PRIVACY_METRICS_FIELD_NUMBER: builtins.int
+    epsilon: builtins.float
+    """Differential privacy epsilon parameter"""
+    k_anonymity_check: builtins.bool
+    """Whether to enforce k-anonymity"""
+    k_value: builtins.int
+    """k value for k-anonymity (if enabled)"""
+    enable_privacy_metrics: builtins.bool
+    """Whether to compute privacy metrics"""
+    @property
+    def sensitive_columns(self) -> google.protobuf.internal.containers.RepeatedScalarFieldContainer[builtins.str]:
+        """Columns that contain sensitive information"""
+
+    def __init__(
+        self,
+        *,
+        epsilon: builtins.float = ...,
+        k_anonymity_check: builtins.bool = ...,
+        k_value: builtins.int = ...,
+        sensitive_columns: collections.abc.Iterable[builtins.str] | None = ...,
+        enable_privacy_metrics: builtins.bool = ...,
+    ) -> None: ...
+    def ClearField(self, field_name: typing.Literal["enable_privacy_metrics", b"enable_privacy_metrics", "epsilon", b"epsilon", "k_anonymity_check", b"k_anonymity_check", "k_value", b"k_value", "sensitive_columns", b"sensitive_columns"]) -> None: ...
+
+global___PrivacyConfig = PrivacyConfig
+
+@typing.final
+class ModelConfig(google.protobuf.message.Message):
+    """ModelConfig controls the ML model used for synthesis"""
+
+    DESCRIPTOR: google.protobuf.descriptor.Descriptor
+
+    @typing.final
+    class CustomParametersEntry(google.protobuf.message.Message):
+        DESCRIPTOR: google.protobuf.descriptor.Descriptor
+
+        KEY_FIELD_NUMBER: builtins.int
+        VALUE_FIELD_NUMBER: builtins.int
+        key: builtins.str
+        value: builtins.str
+        def __init__(
+            self,
+            *,
+            key: builtins.str = ...,
+            value: builtins.str = ...,
+        ) -> None: ...
+        def ClearField(self, field_name: typing.Literal["key", b"key", "value", b"value"]) -> None: ...
+
+    MODEL_TYPE_FIELD_NUMBER: builtins.int
+    EPOCHS_FIELD_NUMBER: builtins.int
+    LEARNING_RATE_FIELD_NUMBER: builtins.int
+    BATCH_SIZE_FIELD_NUMBER: builtins.int
+    CUSTOM_PARAMETERS_FIELD_NUMBER: builtins.int
+    model_type: global___ModelType.ValueType
+    """Type of model to use for synthesis"""
+    epochs: builtins.int
+    """Training epochs"""
+    learning_rate: builtins.float
+    """Learning rate for training"""
+    batch_size: builtins.int
+    """Batch size for training"""
+    @property
+    def custom_parameters(self) -> google.protobuf.internal.containers.ScalarMap[builtins.str, builtins.str]:
+        """Additional model-specific parameters"""
+
+    def __init__(
+        self,
+        *,
+        model_type: global___ModelType.ValueType = ...,
+        epochs: builtins.int = ...,
+        learning_rate: builtins.float = ...,
+        batch_size: builtins.int = ...,
+        custom_parameters: collections.abc.Mapping[builtins.str, builtins.str] | None = ...,
+    ) -> None: ...
+    def ClearField(self, field_name: typing.Literal["batch_size", b"batch_size", "custom_parameters", b"custom_parameters", "epochs", b"epochs", "learning_rate", b"learning_rate", "model_type", b"model_type"]) -> None: ...
+
+global___ModelConfig = ModelConfig

weave/datamanagement/generate/v1/configuration_pb2_grpc.py

@@ -0,0 +1,4 @@
+# Generated by the gRPC Python protocol compiler plugin. DO NOT EDIT!
+"""Client and server classes corresponding to protobuf-defined services."""
+import grpc
+

weave/datamanagement/generate/v1/configuration_pb2_grpc.pyi

@@ -0,0 +1,17 @@
+"""
+@generated by mypy-protobuf.  Do not edit manually!
+isort:skip_file
+"""
+
+import abc
+import collections.abc
+import grpc
+import grpc.aio
+import typing
+
+_T = typing.TypeVar("_T")
+
+class _MaybeAsyncIterator(collections.abc.AsyncIterator[_T], collections.abc.Iterator[_T], metaclass=abc.ABCMeta): ...
+
+class _ServicerContext(grpc.ServicerContext, grpc.aio.ServicerContext):  # type: ignore[misc, type-arg]
+    ...