data-designer 0.3.8rc2__py3-none-any.whl → 0.4.0__py3-none-any.whl

data_designer/config/seed.py

@@ -1,116 +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 enum import Enum
-
-from pydantic import Field, model_validator
-from typing_extensions import Self
-
-from data_designer.config.base import ConfigBase
-from data_designer.config.seed_source_types import SeedSourceT
-
-
-class SamplingStrategy(str, Enum):
-    ORDERED = "ordered"
-    SHUFFLE = "shuffle"
-
-
-class IndexRange(ConfigBase):
-    start: int = Field(ge=0, description="The start index of the index range (inclusive)")
-    end: int = Field(ge=0, description="The end index of the index range (inclusive)")
-
-    @model_validator(mode="after")
-    def _validate_index_range(self) -> Self:
-        if self.start > self.end:
-            raise ValueError("'start' index must be less than or equal to 'end' index")
-        return self
-
-    @property
-    def size(self) -> int:
-        return self.end - self.start + 1
-
-
-class PartitionBlock(ConfigBase):
-    index: int = Field(default=0, ge=0, description="The index of the partition to sample from")
-    num_partitions: int = Field(default=1, ge=1, description="The total number of partitions in the dataset")
-
-    @model_validator(mode="after")
-    def _validate_partition_block(self) -> Self:
-        if self.index >= self.num_partitions:
-            raise ValueError("'index' must be less than 'num_partitions'")
-        return self
-
-    def to_index_range(self, dataset_size: int) -> IndexRange:
-        partition_size = dataset_size // self.num_partitions
-        start = self.index * partition_size
-
-        # For the last partition, extend to the end of the dataset to include remainder rows
-        if self.index == self.num_partitions - 1:
-            end = dataset_size - 1
-        else:
-            end = ((self.index + 1) * partition_size) - 1
-        return IndexRange(start=start, end=end)
-
-
-class SeedConfig(ConfigBase):
-    """Configuration for sampling data from a seed dataset.
-
-    Args:
-        source: A SeedSource defining where the seed data exists
-        sampling_strategy: Strategy for how to sample rows from the dataset.
-            - ORDERED: Read rows sequentially in their original order.
-            - SHUFFLE: Randomly shuffle rows before sampling. When used with
-              selection_strategy, shuffling occurs within the selected range/partition.
-        selection_strategy: Optional strategy to select a subset of the dataset.
-            - IndexRange: Select a specific range of indices (e.g., rows 100-200).
-            - PartitionBlock: Select a partition by splitting the dataset into N equal parts.
-              Partition indices are zero-based (index=0 is the first partition, index=1 is
-              the second, etc.).
-
-    Examples:
-        Read rows sequentially from start to end:
-            SeedConfig(
-                source=LocalFileSeedSource(path="my_data.parquet"),
-                sampling_strategy=SamplingStrategy.ORDERED
-            )
-
-        Read rows in random order:
-            SeedConfig(
-                source=LocalFileSeedSource(path="my_data.parquet"),
-                sampling_strategy=SamplingStrategy.SHUFFLE
-            )
-
-        Read specific index range (rows 100-199):
-            SeedConfig(
-                source=LocalFileSeedSource(path="my_data.parquet"),
-                sampling_strategy=SamplingStrategy.ORDERED,
-                selection_strategy=IndexRange(start=100, end=199)
-            )
-
-        Read random rows from a specific index range (shuffles within rows 100-199):
-            SeedConfig(
-                source=LocalFileSeedSource(path="my_data.parquet"),
-                sampling_strategy=SamplingStrategy.SHUFFLE,
-                selection_strategy=IndexRange(start=100, end=199)
-            )
-
-        Read from partition 2 (3rd partition, zero-based) of 5 partitions (20% of dataset):
-            SeedConfig(
-                source=LocalFileSeedSource(path="my_data.parquet"),
-                sampling_strategy=SamplingStrategy.ORDERED,
-                selection_strategy=PartitionBlock(index=2, num_partitions=5)
-            )
-
-        Read shuffled rows from partition 0 of 10 partitions (shuffles within the partition):
-            SeedConfig(
-                source=LocalFileSeedSource(path="my_data.parquet"),
-                sampling_strategy=SamplingStrategy.SHUFFLE,
-                selection_strategy=PartitionBlock(index=0, num_partitions=10)
-            )
-    """
-
-    source: SeedSourceT
-    sampling_strategy: SamplingStrategy = SamplingStrategy.ORDERED
-    selection_strategy: IndexRange | PartitionBlock | None = None

data_designer/config/seed_source.py

@@ -1,84 +0,0 @@
-# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
-# SPDX-License-Identifier: Apache-2.0
-
-from __future__ import annotations
-
-from abc import ABC
-from typing import TYPE_CHECKING, Literal
-
-from pydantic import BaseModel, ConfigDict, Field, field_validator
-from pydantic.json_schema import SkipJsonSchema
-from typing_extensions import Self
-
-from data_designer.config.utils.io_helpers import (
-    VALID_DATASET_FILE_EXTENSIONS,
-    validate_dataset_file_path,
-    validate_path_contains_files_of_type,
-)
-from data_designer.lazy_heavy_imports import pd
-
-if TYPE_CHECKING:
-    import pandas as pd
-
-
-class SeedSource(BaseModel, ABC):
-    """Base class for seed dataset configurations.
-
-    All subclasses must define a `seed_type` field with a Literal value.
-    This serves as a discriminated union discriminator.
-    """
-
-    seed_type: str
-
-
-class LocalFileSeedSource(SeedSource):
-    seed_type: Literal["local"] = "local"
-
-    path: str
-
-    @field_validator("path", mode="after")
-    def validate_path(cls, v: str) -> str:
-        valid_wild_card_versions = {f"*{ext}" for ext in VALID_DATASET_FILE_EXTENSIONS}
-        if any(v.endswith(wildcard) for wildcard in valid_wild_card_versions):
-            parts = v.split("*.")
-            file_path = parts[0]
-            file_extension = parts[-1]
-            validate_path_contains_files_of_type(file_path, file_extension)
-        else:
-            validate_dataset_file_path(v)
-        return v
-
-    @classmethod
-    def from_dataframe(cls, df: pd.DataFrame, path: str) -> Self:
-        df.to_parquet(path, index=False)
-        return cls(path=path)
-
-
-class HuggingFaceSeedSource(SeedSource):
-    seed_type: Literal["hf"] = "hf"
-
-    path: str = Field(
-        ...,
-        description=(
-            "Path to the seed data in HuggingFace. Wildcards are allowed. Examples include "
-            "'datasets/my-username/my-dataset/data/000_00000.parquet', 'datasets/my-username/my-dataset/data/*.parquet', "
-            "and 'datasets/my-username/my-dataset/**/*.parquet'"
-        ),
-    )
-    token: str | None = None
-    endpoint: str = "https://huggingface.co"
-
-
-class DataFrameSeedSource(SeedSource):
-    seed_type: Literal["df"] = "df"
-
-    model_config = ConfigDict(arbitrary_types_allowed=True)
-
-    df: SkipJsonSchema[pd.DataFrame] = Field(
-        ...,
-        exclude=True,
-        description=(
-            "DataFrame to use directly as the seed dataset. NOTE: if you need to write a Data Designer config, "
-            "you must use `LocalFileSeedSource` instead, since DataFrame objects are not serializable."
-        ),
-    )

data_designer/config/seed_source_types.py

@@ -1,19 +0,0 @@
-# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
-# SPDX-License-Identifier: Apache-2.0
-
-from __future__ import annotations
-
-from typing import Annotated
-
-from pydantic import Field
-from typing_extensions import TypeAlias
-
-from data_designer.config.seed_source import DataFrameSeedSource, HuggingFaceSeedSource, LocalFileSeedSource
-from data_designer.plugin_manager import PluginManager
-
-plugin_manager = PluginManager()
-
-_SeedSourceT: TypeAlias = LocalFileSeedSource | HuggingFaceSeedSource | DataFrameSeedSource
-_SeedSourceT = plugin_manager.inject_into_seed_source_type_union(_SeedSourceT)
-
-SeedSourceT = Annotated[_SeedSourceT, Field(discriminator="seed_type")]

data_designer/config/utils/code_lang.py

@@ -1,82 +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 enum import Enum
-
-
-class CodeLang(str, Enum):
-    GO = "go"
-    JAVASCRIPT = "javascript"
-    JAVA = "java"
-    KOTLIN = "kotlin"
-    PYTHON = "python"
-    RUBY = "ruby"
-    RUST = "rust"
-    SCALA = "scala"
-    SWIFT = "swift"
-    TYPESCRIPT = "typescript"
-    SQL_SQLITE = "sql:sqlite"
-    SQL_TSQL = "sql:tsql"
-    SQL_BIGQUERY = "sql:bigquery"
-    SQL_MYSQL = "sql:mysql"
-    SQL_POSTGRES = "sql:postgres"
-    SQL_ANSI = "sql:ansi"
-
-    @staticmethod
-    def parse(value: str | CodeLang) -> tuple[str, str | None]:
-        value = value.value if isinstance(value, CodeLang) else value
-        split_vals = value.split(":")
-        return (split_vals[0], split_vals[1] if len(split_vals) > 1 else None)
-
-    @staticmethod
-    def parse_lang(value: str | CodeLang) -> str:
-        return CodeLang.parse(value)[0]
-
-    @staticmethod
-    def parse_dialect(value: str | CodeLang) -> str | None:
-        return CodeLang.parse(value)[1]
-
-    @staticmethod
-    def supported_values() -> set[str]:
-        return {lang.value for lang in CodeLang}
-
-
-SQL_DIALECTS: set[CodeLang] = {
-    CodeLang.SQL_SQLITE,
-    CodeLang.SQL_TSQL,
-    CodeLang.SQL_BIGQUERY,
-    CodeLang.SQL_MYSQL,
-    CodeLang.SQL_POSTGRES,
-    CodeLang.SQL_ANSI,
-}
-
-##########################################################
-# Helper functions
-##########################################################
-
-
-def code_lang_to_syntax_lexer(code_lang: CodeLang | str) -> str:
-    """Convert the code language to a syntax lexer for Pygments.
-
-    Reference: https://pygments.org/docs/lexers/
-    """
-    code_lang_to_lexer = {
-        CodeLang.GO: "golang",
-        CodeLang.JAVASCRIPT: "javascript",
-        CodeLang.JAVA: "java",
-        CodeLang.KOTLIN: "kotlin",
-        CodeLang.PYTHON: "python",
-        CodeLang.RUBY: "ruby",
-        CodeLang.RUST: "rust",
-        CodeLang.SCALA: "scala",
-        CodeLang.SWIFT: "swift",
-        CodeLang.SQL_SQLITE: "sql",
-        CodeLang.SQL_ANSI: "sql",
-        CodeLang.SQL_TSQL: "tsql",
-        CodeLang.SQL_BIGQUERY: "sql",
-        CodeLang.SQL_MYSQL: "mysql",
-        CodeLang.SQL_POSTGRES: "postgres",
-    }
-    return code_lang_to_lexer.get(code_lang, code_lang)

data_designer/config/utils/constants.py

@@ -1,363 +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 os
-from enum import Enum
-from pathlib import Path
-
-from rich.theme import Theme
-
-DEFAULT_NUM_RECORDS = 10
-
-EPSILON = 1e-8
-REPORTING_PRECISION = 2
-
-DEFAULT_REPR_HTML_STYLE = "nord"
-
-REPR_HTML_FIXED_WIDTH = 1000
-REPR_HTML_TEMPLATE = """
-<meta charset="UTF-8">
-<style>
-{{css}}
-
-.code {{{{
-  padding: 4px;
-  border: 1px solid grey;
-  border-radius: 4px;
-  max-width: {fixed_width}px;
-  width: 100%;
-  display: inline-block;
-  box-sizing: border-box;
-  text-align: left;
-  vertical-align: top;
-  line-height: normal;
-  overflow-x: auto;
-}}}}
-
-.code pre {{{{
-  white-space: pre-wrap;       /* CSS 3 */
-  white-space: -moz-pre-wrap;  /* Mozilla, since 1999 */
-  white-space: -pre-wrap;      /* Opera 4-6 */
-  white-space: -o-pre-wrap;    /* Opera 7 */
-  word-wrap: break-word;
-  overflow-wrap: break-word;
-  margin: 0;
-}}}}
-</style>
-{{highlighted_html}}
-""".format(fixed_width=REPR_HTML_FIXED_WIDTH)
-
-
-class NordColor(Enum):
-    NORD0 = "#2E3440"  # Darkest gray (background)
-    NORD1 = "#3B4252"  # Dark gray
-    NORD2 = "#434C5E"  # Medium dark gray
-    NORD3 = "#4C566A"  # Lighter dark gray
-    NORD4 = "#D8DEE9"  # Light gray (default text)
-    NORD5 = "#E5E9F0"  # Very light gray
-    NORD6 = "#ECEFF4"  # Almost white
-    NORD7 = "#8FBCBB"  # Teal
-    NORD8 = "#88C0D0"  # Light cyan
-    NORD9 = "#81A1C1"  # Soft blue
-    NORD10 = "#5E81AC"  # Darker blue
-    NORD11 = "#BF616A"  # Red
-    NORD12 = "#D08770"  # Orange
-    NORD13 = "#EBCB8B"  # Yellow
-    NORD14 = "#A3BE8C"  # Green
-    NORD15 = "#B48EAD"  # Purple
-
-
-RICH_CONSOLE_THEME = Theme(
-    {
-        "repr.number": NordColor.NORD15.value,  # Purple for numbers
-        "repr.string": NordColor.NORD14.value,  # Green for strings
-        "repr.bool_true": NordColor.NORD9.value,  # Blue for True
-        "repr.bool_false": NordColor.NORD9.value,  # Blue for False
-        "repr.none": NordColor.NORD11.value,  # Red for None
-        "repr.brace": NordColor.NORD7.value,  # Teal for brackets/braces
-        "repr.comma": NordColor.NORD7.value,  # Teal for commas
-        "repr.ellipsis": NordColor.NORD7.value,  # Teal for ellipsis
-        "repr.attrib_name": NordColor.NORD3.value,  # Light gray for dict keys
-        "repr.attrib_equal": NordColor.NORD7.value,  # Teal for equals signs
-        "repr.call": NordColor.NORD10.value,  # Darker blue for function calls
-        "repr.function_name": NordColor.NORD10.value,  # Darker blue for function names
-        "repr.class_name": NordColor.NORD12.value,  # Orange for class names
-        "repr.module_name": NordColor.NORD8.value,  # Light cyan for module names
-        "repr.error": NordColor.NORD11.value,  # Red for errors
-        "repr.warning": NordColor.NORD13.value,  # Yellow for warnings
-    }
-)
-
-DEFAULT_HIST_NAME_COLOR = "medium_purple1"
-
-DEFAULT_HIST_VALUE_COLOR = "pale_green3"
-
-
-DEFAULT_AGE_RANGE = [18, 114]
-MIN_AGE = 0
-MAX_AGE = 114
-
-US_STATES_AND_MAJOR_TERRITORIES = {
-    # States
-    "AK",
-    "AL",
-    "AR",
-    "AZ",
-    "CA",
-    "CO",
-    "CT",
-    "DE",
-    "FL",
-    "GA",
-    "HI",
-    "IA",
-    "ID",
-    "IL",
-    "IN",
-    "KS",
-    "KY",
-    "LA",
-    "MA",
-    "MD",
-    "ME",
-    "MI",
-    "MN",
-    "MO",
-    "MS",
-    "MT",
-    "NC",
-    "ND",
-    "NE",
-    "NH",
-    "NJ",
-    "NM",
-    "NV",
-    "NY",
-    "OH",
-    "OK",
-    "OR",
-    "PA",
-    "RI",
-    "SC",
-    "SD",
-    "TN",
-    "TX",
-    "UT",
-    "VA",
-    "VT",
-    "WA",
-    "WI",
-    "WV",
-    "WY",
-    # D.C.
-    "DC",
-    # Territories
-    "AS",
-    "GU",
-    "MP",
-    "PR",
-    "VI",
-}
-
-MAX_TEMPERATURE = 2.0
-MIN_TEMPERATURE = 0.0
-MAX_TOP_P = 1.0
-MIN_TOP_P = 0.0
-MIN_MAX_TOKENS = 1
-REASONING_TRACE_COLUMN_POSTFIX = "__reasoning_trace"
-
-AVAILABLE_LOCALES = [
-    "ar_AA",
-    "ar_AE",
-    "ar_BH",
-    "ar_EG",
-    "ar_JO",
-    "ar_PS",
-    "ar_SA",
-    "az_AZ",
-    "bg_BG",
-    "bn_BD",
-    "bs_BA",
-    "cs_CZ",
-    "da_DK",
-    "de",
-    "de_AT",
-    "de_CH",
-    "de_DE",
-    "dk_DK",
-    "el_CY",
-    "el_GR",
-    "en",
-    "en_AU",
-    "en_BD",
-    "en_CA",
-    "en_GB",
-    "en_IE",
-    "en_IN",
-    "en_NZ",
-    "en_PH",
-    "en_TH",
-    "en_US",
-    "es",
-    "es_AR",
-    "es_CA",
-    "es_CL",
-    "es_CO",
-    "es_ES",
-    "es_MX",
-    "et_EE",
-    "fa_IR",
-    "fi_FI",
-    "fil_PH",
-    "fr_BE",
-    "fr_CA",
-    "fr_CH",
-    "fr_FR",
-    #    "fr_QC", deprecated, use fr_CA instead
-    "ga_IE",
-    "he_IL",
-    "hi_IN",
-    "hr_HR",
-    "hu_HU",
-    "hy_AM",
-    "id_ID",
-    "it_CH",
-    "it_IT",
-    "ja_JP",
-    "ka_GE",
-    "ko_KR",
-    "la",
-    "lb_LU",
-    "lt_LT",
-    "lv_LV",
-    "mt_MT",
-    "ne_NP",
-    "nl_BE",
-    "nl_NL",
-    "no_NO",
-    "or_IN",
-    "pl_PL",
-    "pt_BR",
-    "pt_PT",
-    "ro_RO",
-    "ru_RU",
-    "sk_SK",
-    "sl_SI",
-    "sq_AL",
-    "sv_SE",
-    "ta_IN",
-    "th",
-    "th_TH",
-    "tl_PH",
-    "tr_TR",
-    "tw_GH",
-    "uk_UA",
-    "vi_VN",
-    "zh_CN",
-    "zh_TW",
-    "zu_ZA",
-]
-
-DATA_DESIGNER_HOME_ENV_VAR = "DATA_DESIGNER_HOME"
-
-DATA_DESIGNER_HOME = Path(os.getenv(DATA_DESIGNER_HOME_ENV_VAR, Path.home() / ".data-designer"))
-
-MANAGED_ASSETS_PATH_ENV_VAR = "DATA_DESIGNER_MANAGED_ASSETS_PATH"
-
-MANAGED_ASSETS_PATH = Path(os.getenv(MANAGED_ASSETS_PATH_ENV_VAR, DATA_DESIGNER_HOME / "managed-assets"))
-
-MODEL_CONFIGS_FILE_NAME = "model_configs.yaml"
-
-MODEL_CONFIGS_FILE_PATH = DATA_DESIGNER_HOME / MODEL_CONFIGS_FILE_NAME
-
-MODEL_PROVIDERS_FILE_NAME = "model_providers.yaml"
-
-MODEL_PROVIDERS_FILE_PATH = DATA_DESIGNER_HOME / MODEL_PROVIDERS_FILE_NAME
-
-NVIDIA_PROVIDER_NAME = "nvidia"
-
-NVIDIA_API_KEY_ENV_VAR_NAME = "NVIDIA_API_KEY"
-
-OPENAI_PROVIDER_NAME = "openai"
-
-OPENAI_API_KEY_ENV_VAR_NAME = "OPENAI_API_KEY"
-
-OPENROUTER_PROVIDER_NAME = "openrouter"
-
-OPENROUTER_API_KEY_ENV_VAR_NAME = "OPENROUTER_API_KEY"
-
-PREDEFINED_PROVIDERS = [
-    {
-        "name": NVIDIA_PROVIDER_NAME,
-        "endpoint": "https://integrate.api.nvidia.com/v1",
-        "provider_type": "openai",
-        "api_key": NVIDIA_API_KEY_ENV_VAR_NAME,
-    },
-    {
-        "name": OPENAI_PROVIDER_NAME,
-        "endpoint": "https://api.openai.com/v1",
-        "provider_type": "openai",
-        "api_key": OPENAI_API_KEY_ENV_VAR_NAME,
-    },
-    {
-        "name": OPENROUTER_PROVIDER_NAME,
-        "endpoint": "https://openrouter.ai/api/v1",
-        "provider_type": "openai",
-        "api_key": OPENROUTER_API_KEY_ENV_VAR_NAME,
-    },
-]
-
-
-DEFAULT_TEXT_INFERENCE_PARAMS = {"temperature": 0.85, "top_p": 0.95}
-DEFAULT_REASONING_INFERENCE_PARAMS = {"temperature": 0.35, "top_p": 0.95}
-DEFAULT_VISION_INFERENCE_PARAMS = {"temperature": 0.85, "top_p": 0.95}
-DEFAULT_EMBEDDING_INFERENCE_PARAMS = {"encoding_format": "float"}
-NEMOTRON_3_NANO_30B_A3B_INFERENCE_PARAMS = {"temperature": 1.0, "top_p": 1.0}
-
-PREDEFINED_PROVIDERS_MODEL_MAP = {
-    NVIDIA_PROVIDER_NAME: {
-        "text": {
-            "model": "nvidia/nemotron-3-nano-30b-a3b",
-            "inference_parameters": NEMOTRON_3_NANO_30B_A3B_INFERENCE_PARAMS,
-        },
-        "reasoning": {"model": "openai/gpt-oss-20b", "inference_parameters": DEFAULT_REASONING_INFERENCE_PARAMS},
-        "vision": {"model": "nvidia/nemotron-nano-12b-v2-vl", "inference_parameters": DEFAULT_VISION_INFERENCE_PARAMS},
-        "embedding": {
-            "model": "nvidia/llama-3.2-nv-embedqa-1b-v2",
-            "inference_parameters": DEFAULT_EMBEDDING_INFERENCE_PARAMS | {"extra_body": {"input_type": "query"}},
-        },
-    },
-    OPENAI_PROVIDER_NAME: {
-        "text": {"model": "gpt-4.1", "inference_parameters": DEFAULT_TEXT_INFERENCE_PARAMS},
-        "reasoning": {"model": "gpt-5", "inference_parameters": DEFAULT_REASONING_INFERENCE_PARAMS},
-        "vision": {"model": "gpt-5", "inference_parameters": DEFAULT_VISION_INFERENCE_PARAMS},
-        "embedding": {"model": "text-embedding-3-large", "inference_parameters": DEFAULT_EMBEDDING_INFERENCE_PARAMS},
-    },
-    OPENROUTER_PROVIDER_NAME: {
-        "text": {
-            "model": "nvidia/nemotron-3-nano-30b-a3b",
-            "inference_parameters": NEMOTRON_3_NANO_30B_A3B_INFERENCE_PARAMS,
-        },
-        "reasoning": {"model": "openai/gpt-oss-20b", "inference_parameters": DEFAULT_REASONING_INFERENCE_PARAMS},
-        "vision": {"model": "nvidia/nemotron-nano-12b-v2-vl", "inference_parameters": DEFAULT_VISION_INFERENCE_PARAMS},
-        "embedding": {
-            "model": "openai/text-embedding-3-large",
-            "inference_parameters": DEFAULT_EMBEDDING_INFERENCE_PARAMS,
-        },
-    },
-}
-
-# Persona locale metadata - used by the CLI and the person sampler.
-NEMOTRON_PERSONAS_DATASET_SIZES = {
-    "en_US": "1.24 GB",
-    "en_IN": "2.39 GB",
-    "hi_Deva_IN": "4.14 GB",
-    "hi_Latn_IN": "2.7 GB",
-    "ja_JP": "1.69 GB",
-}
-
-LOCALES_WITH_MANAGED_DATASETS = list[str](NEMOTRON_PERSONAS_DATASET_SIZES.keys())
-
-NEMOTRON_PERSONAS_DATASET_PREFIX = "nemotron-personas-dataset-"

data_designer/config/utils/errors.py

@@ -1,21 +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 UserJinjaTemplateSyntaxError(DataDesignerError): ...
-
-
-class InvalidEnumValueError(DataDesignerError): ...
-
-
-class InvalidTypeUnionError(DataDesignerError): ...
-
-
-class InvalidDiscriminatorFieldError(DataDesignerError): ...
-
-
-class DatasetSampleDisplayError(DataDesignerError): ...