data-designer 0.3.8rc1__py3-none-any.whl → 0.4.0__py3-none-any.whl

data_designer/config/default_model_settings.py

@@ -1,121 +0,0 @@
-# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
-# SPDX-License-Identifier: Apache-2.0
-
-from __future__ import annotations
-
-import logging
-import os
-from functools import lru_cache
-from pathlib import Path
-from typing import Any, Literal
-
-from data_designer.config.models import (
-    ChatCompletionInferenceParams,
-    EmbeddingInferenceParams,
-    InferenceParamsT,
-    ModelConfig,
-    ModelProvider,
-)
-from data_designer.config.utils.constants import (
-    MANAGED_ASSETS_PATH,
-    MODEL_CONFIGS_FILE_PATH,
-    MODEL_PROVIDERS_FILE_PATH,
-    PREDEFINED_PROVIDERS,
-    PREDEFINED_PROVIDERS_MODEL_MAP,
-)
-from data_designer.config.utils.io_helpers import load_config_file, save_config_file
-
-logger = logging.getLogger(__name__)
-
-
-def get_default_inference_parameters(
-    model_alias: Literal["text", "reasoning", "vision", "embedding"],
-    inference_parameters: dict[str, Any],
-) -> InferenceParamsT:
-    if model_alias == "reasoning":
-        return ChatCompletionInferenceParams(**inference_parameters)
-    elif model_alias == "vision":
-        return ChatCompletionInferenceParams(**inference_parameters)
-    elif model_alias == "embedding":
-        return EmbeddingInferenceParams(**inference_parameters)
-    else:
-        return ChatCompletionInferenceParams(**inference_parameters)
-
-
-def get_builtin_model_configs() -> list[ModelConfig]:
-    model_configs = []
-    for provider, model_alias_map in PREDEFINED_PROVIDERS_MODEL_MAP.items():
-        for model_alias, settings in model_alias_map.items():
-            model_configs.append(
-                ModelConfig(
-                    alias=f"{provider}-{model_alias}",
-                    model=settings["model"],
-                    provider=provider,
-                    inference_parameters=get_default_inference_parameters(
-                        model_alias, settings["inference_parameters"]
-                    ),
-                )
-            )
-    return model_configs
-
-
-def get_builtin_model_providers() -> list[ModelProvider]:
-    return [ModelProvider.model_validate(provider) for provider in PREDEFINED_PROVIDERS]
-
-
-def get_default_model_configs() -> list[ModelConfig]:
-    if MODEL_CONFIGS_FILE_PATH.exists():
-        config_dict = load_config_file(MODEL_CONFIGS_FILE_PATH)
-        if "model_configs" in config_dict:
-            return [ModelConfig.model_validate(mc) for mc in config_dict["model_configs"]]
-    return []
-
-
-def get_default_model_providers_missing_api_keys() -> list[str]:
-    missing_api_keys = []
-    for predefined_provider in PREDEFINED_PROVIDERS:
-        if os.environ.get(predefined_provider["api_key"]) is None:
-            missing_api_keys.append(predefined_provider["api_key"])
-    return missing_api_keys
-
-
-def get_default_providers() -> list[ModelProvider]:
-    config_dict = _get_default_providers_file_content(MODEL_PROVIDERS_FILE_PATH)
-    if "providers" in config_dict:
-        return [ModelProvider.model_validate(p) for p in config_dict["providers"]]
-    return []
-
-
-def get_default_provider_name() -> str | None:
-    return _get_default_providers_file_content(MODEL_PROVIDERS_FILE_PATH).get("default")
-
-
-def resolve_seed_default_model_settings() -> None:
-    if not MODEL_CONFIGS_FILE_PATH.exists():
-        logger.debug(
-            f"🍾 Default model configs were not found, so writing the following to {str(MODEL_CONFIGS_FILE_PATH)!r}"
-        )
-        save_config_file(
-            MODEL_CONFIGS_FILE_PATH,
-            {"model_configs": [mc.model_dump(mode="json") for mc in get_builtin_model_configs()]},
-        )
-
-    if not MODEL_PROVIDERS_FILE_PATH.exists():
-        logger.debug(
-            f"🪄  Default model providers were not found, so writing the following to {str(MODEL_PROVIDERS_FILE_PATH)!r}"
-        )
-        save_config_file(
-            MODEL_PROVIDERS_FILE_PATH, {"providers": [p.model_dump(mode="json") for p in get_builtin_model_providers()]}
-        )
-
-    if not MANAGED_ASSETS_PATH.exists():
-        logger.debug(f"🏗️ Default managed assets path was not found, so creating it at {str(MANAGED_ASSETS_PATH)!r}")
-        MANAGED_ASSETS_PATH.mkdir(parents=True, exist_ok=True)
-
-
-@lru_cache(maxsize=1)
-def _get_default_providers_file_content(file_path: Path) -> dict[str, Any]:
-    """Load and cache the default providers file content."""
-    if file_path.exists():
-        return load_config_file(file_path)
-    raise FileNotFoundError(f"Default model providers file not found at {str(file_path)!r}")

data_designer/config/errors.py

@@ -1,24 +0,0 @@
-# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
-# SPDX-License-Identifier: Apache-2.0
-
-from __future__ import annotations
-
-from data_designer.errors import DataDesignerError
-
-
-class BuilderConfigurationError(DataDesignerError): ...
-
-
-class BuilderSerializationError(DataDesignerError): ...
-
-
-class InvalidColumnTypeError(DataDesignerError): ...
-
-
-class InvalidConfigError(DataDesignerError): ...
-
-
-class InvalidFilePathError(DataDesignerError): ...
-
-
-class InvalidFileFormatError(DataDesignerError): ...

data_designer/config/exports.py

@@ -1,145 +0,0 @@
-# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
-# SPDX-License-Identifier: Apache-2.0
-
-from __future__ import annotations
-
-from data_designer.config.analysis.column_profilers import JudgeScoreProfilerConfig
-from data_designer.config.column_configs import (
-    EmbeddingColumnConfig,
-    ExpressionColumnConfig,
-    LLMCodeColumnConfig,
-    LLMJudgeColumnConfig,
-    LLMStructuredColumnConfig,
-    LLMTextColumnConfig,
-    SamplerColumnConfig,
-    Score,
-    SeedDatasetColumnConfig,
-    ValidationColumnConfig,
-)
-from data_designer.config.column_types import DataDesignerColumnType
-from data_designer.config.config_builder import DataDesignerConfigBuilder
-from data_designer.config.data_designer_config import DataDesignerConfig
-from data_designer.config.dataset_builders import BuildStage
-from data_designer.config.models import (
-    ChatCompletionInferenceParams,
-    EmbeddingInferenceParams,
-    GenerationType,
-    ImageContext,
-    ImageFormat,
-    ManualDistribution,
-    ManualDistributionParams,
-    Modality,
-    ModalityContext,
-    ModalityDataType,
-    ModelConfig,
-    ModelProvider,
-    UniformDistribution,
-    UniformDistributionParams,
-)
-from data_designer.config.processors import (
-    DropColumnsProcessorConfig,
-    ProcessorType,
-    SchemaTransformProcessorConfig,
-)
-from data_designer.config.sampler_constraints import ColumnInequalityConstraint, ScalarInequalityConstraint
-from data_designer.config.sampler_params import (
-    BernoulliMixtureSamplerParams,
-    BernoulliSamplerParams,
-    BinomialSamplerParams,
-    CategorySamplerParams,
-    DatetimeSamplerParams,
-    GaussianSamplerParams,
-    PersonFromFakerSamplerParams,
-    PersonSamplerParams,
-    PoissonSamplerParams,
-    SamplerType,
-    ScipySamplerParams,
-    SubcategorySamplerParams,
-    TimeDeltaSamplerParams,
-    UniformSamplerParams,
-    UUIDSamplerParams,
-)
-from data_designer.config.seed import (
-    IndexRange,
-    PartitionBlock,
-    SamplingStrategy,
-    SeedConfig,
-)
-from data_designer.config.seed_source import (
-    DataFrameSeedSource,
-    HuggingFaceSeedSource,
-    LocalFileSeedSource,
-)
-from data_designer.config.utils.code_lang import CodeLang
-from data_designer.config.utils.info import InfoType
-from data_designer.config.validator_params import (
-    CodeValidatorParams,
-    RemoteValidatorParams,
-    ValidatorType,
-)
-
-
-def get_config_exports() -> list[str]:
-    return [
-        SchemaTransformProcessorConfig.__name__,
-        BernoulliMixtureSamplerParams.__name__,
-        BernoulliSamplerParams.__name__,
-        BinomialSamplerParams.__name__,
-        CategorySamplerParams.__name__,
-        CodeLang.__name__,
-        CodeValidatorParams.__name__,
-        ColumnInequalityConstraint.__name__,
-        ChatCompletionInferenceParams.__name__,
-        DataDesignerColumnType.__name__,
-        DataDesignerConfig.__name__,
-        DataDesignerConfigBuilder.__name__,
-        DataFrameSeedSource.__name__,
-        BuildStage.__name__,
-        DatetimeSamplerParams.__name__,
-        DropColumnsProcessorConfig.__name__,
-        EmbeddingColumnConfig.__name__,
-        EmbeddingInferenceParams.__name__,
-        ExpressionColumnConfig.__name__,
-        GaussianSamplerParams.__name__,
-        GenerationType.__name__,
-        HuggingFaceSeedSource.__name__,
-        IndexRange.__name__,
-        InfoType.__name__,
-        ImageContext.__name__,
-        ImageFormat.__name__,
-        JudgeScoreProfilerConfig.__name__,
-        LLMCodeColumnConfig.__name__,
-        LLMJudgeColumnConfig.__name__,
-        LLMStructuredColumnConfig.__name__,
-        LLMTextColumnConfig.__name__,
-        LocalFileSeedSource.__name__,
-        ManualDistribution.__name__,
-        ManualDistributionParams.__name__,
-        Modality.__name__,
-        ModalityContext.__name__,
-        ModalityDataType.__name__,
-        ModelConfig.__name__,
-        ModelProvider.__name__,
-        PartitionBlock.__name__,
-        PersonSamplerParams.__name__,
-        PersonFromFakerSamplerParams.__name__,
-        PoissonSamplerParams.__name__,
-        ProcessorType.__name__,
-        RemoteValidatorParams.__name__,
-        SamplerColumnConfig.__name__,
-        SamplerType.__name__,
-        SamplingStrategy.__name__,
-        ScalarInequalityConstraint.__name__,
-        ScipySamplerParams.__name__,
-        Score.__name__,
-        SeedConfig.__name__,
-        SeedDatasetColumnConfig.__name__,
-        SubcategorySamplerParams.__name__,
-        TimeDeltaSamplerParams.__name__,
-        UniformDistribution.__name__,
-        UniformDistributionParams.__name__,
-        UniformSamplerParams.__name__,
-        UUIDSamplerParams.__name__,
-        ValidationColumnConfig.__name__,
-        ValidatorType.__name__,
-    ]

data_designer/config/interface.py

@@ -1,55 +0,0 @@
-# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
-# SPDX-License-Identifier: Apache-2.0
-
-from __future__ import annotations
-
-from abc import ABC, abstractmethod
-from typing import TYPE_CHECKING, Generic, Protocol, TypeVar
-
-from data_designer.config.models import ModelConfig, ModelProvider
-from data_designer.config.utils.constants import DEFAULT_NUM_RECORDS
-from data_designer.config.utils.info import InterfaceInfo
-from data_designer.lazy_heavy_imports import pd
-
-if TYPE_CHECKING:
-    import pandas as pd
-
-    from data_designer.config.analysis.dataset_profiler import DatasetProfilerResults
-    from data_designer.config.config_builder import DataDesignerConfigBuilder
-    from data_designer.config.preview_results import PreviewResults
-
-
-class ResultsProtocol(Protocol):
-    def load_analysis(self) -> DatasetProfilerResults: ...
-    def load_dataset(self) -> pd.DataFrame: ...
-
-
-ResultsT = TypeVar("ResultsT", bound=ResultsProtocol)
-
-
-class DataDesignerInterface(ABC, Generic[ResultsT]):
-    @abstractmethod
-    def create(
-        self,
-        config_builder: DataDesignerConfigBuilder,
-        *,
-        num_records: int = DEFAULT_NUM_RECORDS,
-    ) -> ResultsT: ...
-
-    @abstractmethod
-    def preview(
-        self,
-        config_builder: DataDesignerConfigBuilder,
-        *,
-        num_records: int = DEFAULT_NUM_RECORDS,
-    ) -> PreviewResults: ...
-
-    @abstractmethod
-    def get_default_model_configs(self) -> list[ModelConfig]: ...
-
-    @abstractmethod
-    def get_default_model_providers(self) -> list[ModelProvider]: ...
-
-    @property
-    @abstractmethod
-    def info(self) -> InterfaceInfo: ...