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

data_designer/cli/commands/__init__.py

@@ -1,2 +1,2 @@
-# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0

data_designer/interface/__init__.py

@@ -1,2 +1,22 @@
-# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
+
+from data_designer.config.default_model_settings import resolve_seed_default_model_settings
+from data_designer.interface.data_designer import DataDesigner
+from data_designer.interface.errors import (
+    DataDesignerGenerationError,
+    DataDesignerProfilingError,
+)
+from data_designer.interface.results import DatasetCreationResults
+from data_designer.logging import configure_logging
+
+configure_logging()
+resolve_seed_default_model_settings()
+
+
+__all__ = [
+    "DataDesigner",
+    "DataDesignerGenerationError",
+    "DataDesignerProfilingError",
+    "DatasetCreationResults",
+]

data_designer/{_version.py → interface/_version.py}

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.3.8rc1'
-__version_tuple__ = version_tuple = (0, 3, 8, 'rc1')
+__version__ = version = '0.4.0'
+__version_tuple__ = version_tuple = (0, 4, 0)
 
 __commit_id__ = commit_id = None

data_designer/interface/data_designer.py

@@ -12,9 +12,9 @@ from data_designer.config.config_builder import DataDesignerConfigBuilder
 from data_designer.config.data_designer_config import DataDesignerConfig
 from data_designer.config.default_model_settings import (
     get_default_model_configs,
-    get_default_model_providers_missing_api_keys,
     get_default_provider_name,
     get_default_providers,
+    get_providers_with_missing_api_keys,
 )
 from data_designer.config.interface import DataDesignerInterface
 from data_designer.config.models import (
@@ -28,7 +28,6 @@ from data_designer.config.utils.constants import (
     MANAGED_ASSETS_PATH,
     MODEL_CONFIGS_FILE_PATH,
     MODEL_PROVIDERS_FILE_PATH,
-    PREDEFINED_PROVIDERS,
 )
 from data_designer.config.utils.info import InfoType, InterfaceInfo
 from data_designer.engine.analysis.dataset_profiler import DataDesignerDatasetProfiler, DatasetProfilerConfig
@@ -317,13 +316,8 @@ class DataDesigner(DataDesignerInterface[DatasetCreationResults]):
 
         Args:
             run_config: A RunConfig instance containing runtime settings such as
-                early shutdown behavior and batch sizing via `buffer_size`. Import RunConfig from
-                data_designer.essentials.
-
-        Example:
-            >>> from data_designer.essentials import DataDesigner, RunConfig
-            >>> dd = DataDesigner()
-            >>> dd.set_run_config(RunConfig(disable_early_shutdown=True))
+                early shutdown behavior, batch sizing via `buffer_size`, and non-inference worker
+                concurrency via `non_inference_max_parallel_workers`.
 
         Notes:
             When `disable_early_shutdown=True`, DataDesigner will never terminate generation early
@@ -334,8 +328,11 @@ class DataDesigner(DataDesignerInterface[DatasetCreationResults]):
     def _resolve_model_providers(self, model_providers: list[ModelProvider] | None) -> list[ModelProvider]:
         if model_providers is None:
             model_providers = get_default_providers()
-            missing_api_keys = get_default_model_providers_missing_api_keys()
-            if len(missing_api_keys) == len(PREDEFINED_PROVIDERS):
+            # Check which providers have missing API keys (from YAML file or env vars)
+            providers_with_missing_keys = get_providers_with_missing_api_keys(model_providers)
+
+            if len(providers_with_missing_keys) == len(model_providers):
+                # All providers have missing API keys
                 logger.warning(
                     "🚨 You are trying to use a default model provider but your API keys are missing."
                     "\n\t\t\tSet the API key for the default providers you intend to use and re-initialize the Data Designer object."

{data_designer-0.3.8rc1.dist-info → data_designer-0.4.0.dist-info}/METADATA

@@ -1,9 +1,8 @@
 Metadata-Version: 2.4
 Name: data-designer
-Version: 0.3.8rc1
+Version: 0.4.0
 Summary: General framework for synthetic data generation
 License-Expression: Apache-2.0
-License-File: LICENSE
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
@@ -15,33 +14,9 @@ Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Topic :: Software Development
 Requires-Python: >=3.10
-Requires-Dist: anyascii<1,>=0.3.3
-Requires-Dist: duckdb<2,>=1.1.3
-Requires-Dist: faker<21,>=20.1.0
-Requires-Dist: httpx-retries<1,>=0.4.2
-Requires-Dist: httpx<1,>=0.27.2
-Requires-Dist: huggingface-hub<2,>=1.0.1
-Requires-Dist: jinja2<4,>=3.1.6
-Requires-Dist: json-repair<1,>=0.48.0
-Requires-Dist: jsonpath-rust-bindings<2,>=1.0
-Requires-Dist: litellm<1.80.12,>=1.73.6
-Requires-Dist: lxml<7,>=6.0.2
-Requires-Dist: marko<3,>=2.1.2
-Requires-Dist: networkx<4,>=3.0
-Requires-Dist: numpy<3,>=1.23.5
-Requires-Dist: pandas<3,>=2.3.3
+Requires-Dist: data-designer-config
+Requires-Dist: data-designer-engine
 Requires-Dist: prompt-toolkit<4,>=3.0.0
-Requires-Dist: pyarrow<20,>=19.0.1
-Requires-Dist: pydantic[email]<3,>=2.9.2
-Requires-Dist: pygments<3,>=2.19.2
-Requires-Dist: python-json-logger<4,>=3
-Requires-Dist: pyyaml<7,>=6.0.1
-Requires-Dist: requests<3,>=2.32.2
-Requires-Dist: rich<15,>=13.7.1
-Requires-Dist: ruff<1,>=0.14.10
-Requires-Dist: scipy<2,>=1.11.0
-Requires-Dist: sqlfluff<4,>=3.2.0
-Requires-Dist: tiktoken<1,>=0.8.0
 Requires-Dist: typer<1,>=0.12.0
 Description-Content-Type: text/markdown
 
@@ -104,26 +79,19 @@ export OPENROUTER_API_KEY="your-openrouter-api-key-here"
 
 ### 3. Start generating data!
 ```python
-from data_designer.essentials import (
-    CategorySamplerParams,
-    DataDesigner,
-    DataDesignerConfigBuilder,
-    LLMTextColumnConfig,
-    PersonSamplerParams,
-    SamplerColumnConfig,
-    SamplerType,
-)
+import data_designer.config as dd
+from data_designer.interface import DataDesigner
 
 # Initialize with default settings
 data_designer = DataDesigner()
-config_builder = DataDesignerConfigBuilder()
+config_builder = dd.DataDesignerConfigBuilder()
 
 # Add a product category
 config_builder.add_column(
-    SamplerColumnConfig(
+    dd.SamplerColumnConfig(
         name="product_category",
-        sampler_type=SamplerType.CATEGORY,
-        params=CategorySamplerParams(
+        sampler_type=dd.SamplerType.CATEGORY,
+        params=dd.CategorySamplerParams(
             values=["Electronics", "Clothing", "Home & Kitchen", "Books"],
         ),
     )
@@ -131,7 +99,7 @@ config_builder.add_column(
 
 # Generate personalized customer reviews
 config_builder.add_column(
-    LLMTextColumnConfig(
+    dd.LLMTextColumnConfig(
         name="review",
         model_alias="nvidia-text",
         prompt="Write a brief product review for a {{ product_category }} item you recently purchased.",

data_designer-0.4.0.dist-info/RECORD

@@ -0,0 +1,39 @@
+data_designer/cli/README.md,sha256=uPE3KdlF5Y3H8pQc8c6ZZ3h6YSFXNQW-iEXGQJuVnI4,9026
+data_designer/cli/__init__.py,sha256=--5yQzMciTX8-vroyXyFNBCqQ0HQd67GWCwnIoIHhJ4,251
+data_designer/cli/main.py,sha256=1klKdUKPZTgmUbduHSzEFueQHWkc-42Gcbri25cjiHo,1974
+data_designer/cli/ui.py,sha256=IgpV_Ht6qmLFrT3ybgOoADTQthoSGJxrwds38o1Zz10,17632
+data_designer/cli/utils.py,sha256=yyKZfr4ndcsngKgmpj5r4fN7fP6ouX-Nwx1Go5s6SdM,2151
+data_designer/cli/commands/__init__.py,sha256=ObZ6NUPeEvvpGTJ5WIGKUyIrIjaI747OM6ErweRtHxQ,137
+data_designer/cli/commands/download.py,sha256=bTynzORVj1rftrrQhmTj6se-ITi2_L7Z3qtio1mLvXU,1770
+data_designer/cli/commands/list.py,sha256=Lu02qFTkhEkLX2e7ak_rHmoO8_4Jjrgy4Yua-EAtyHo,4091
+data_designer/cli/commands/models.py,sha256=Ot4eWyEbCS7heG_bylBdWZ1qj4CILv_hTddm2VdY0Dc,428
+data_designer/cli/commands/providers.py,sha256=-zVNtE_0A0hifcUk6n3c_v_Olcd14mHt3N8_HahHTQ4,491
+data_designer/cli/commands/reset.py,sha256=iCNjkFNdGU6Y7rv-Fprl9ZW60riseL_R7CrYi6DrwR0,3514
+data_designer/cli/controllers/__init__.py,sha256=70il4GIKebdau43nCXyu4VcQj7IFNoxxjEo1Z3hm8_M,491
+data_designer/cli/controllers/download_controller.py,sha256=9lQo-njn890WJiewGazfd6SrBBA4Rj8LYFkXZG_phPI,8117
+data_designer/cli/controllers/model_controller.py,sha256=CZimP1npWwH8UrJXlfMIfbNEn9pcJKtg14CqgArbqQM,9020
+data_designer/cli/controllers/provider_controller.py,sha256=mSLHkc60lu9VsXJE2NNpFZ6zHkasz6UQLtoTBYoFtkA,12293
+data_designer/cli/forms/__init__.py,sha256=UpTr7s5q2GFFssNz3229Kb5JxvFOqtZ55XpifB9a15w,713
+data_designer/cli/forms/builder.py,sha256=Juem3wB2j1KXtZZY7wVP0-eWKK_tj_0-L8Zq9EAS0-k,1731
+data_designer/cli/forms/field.py,sha256=TYEQLqjMvYBS_ftf6Ms-D5J6TOIK9NNe-Ydvo5Nkq50,7543
+data_designer/cli/forms/form.py,sha256=wFdKS0WfuhfotRtwWZgJyN2HrTthI7Kx07NUoQV2DtM,2066
+data_designer/cli/forms/model_builder.py,sha256=DPggV2cl-XQPUiVhrrGO_4_d7jTn5_kBeBn9oTw-V1U,13354
+data_designer/cli/forms/provider_builder.py,sha256=YA6IoLwV39Sh6w0lZYoF25m-ryhnqBqysXLUo4V5X-w,2936
+data_designer/cli/repositories/__init__.py,sha256=ukHlLpOimH9CCJsdW5U9tooV_oFWQ4iLGK5GNi5YXtM,475
+data_designer/cli/repositories/base.py,sha256=ofOAHeAYAL6Bm4EJjSOFaNPD-odm2PlrW6quRkQQzaw,1095
+data_designer/cli/repositories/model_repository.py,sha256=oaa5ISP8Y-BRzXOdzAhDHf0FqmWngSEJ8RGOYWeXi4M,1487
+data_designer/cli/repositories/persona_repository.py,sha256=3ZRarD6BYAKVYFs_r9hDkh2nfkKW7BA8KJyfcYP0RRc,2683
+data_designer/cli/repositories/provider_repository.py,sha256=hG6tYbjR3gT8DmXL7usRvMrc6ILws4ECyTZ5imENpuQ,1556
+data_designer/cli/services/__init__.py,sha256=2ycyikXx-8gbYZm-xl6IMyKXLwR4REU5heg6BkUW6qo,455
+data_designer/cli/services/download_service.py,sha256=m_wtDfxAA80tZdIf9kUS3ye8fzKG-3DjfDnm5u0-mJE,3519
+data_designer/cli/services/model_service.py,sha256=cFiP9ZQIprPdrVibUC6uwL-NuCYRgx8XVIjxDV-TznU,3926
+data_designer/cli/services/provider_service.py,sha256=5cou_EWU0RwE9p2PWpRBM9HcPqdENLpkHUuGzQ-l9J4,3957
+data_designer/interface/__init__.py,sha256=2LbGosKhVhNXSUj-MX00b6UJRW-qeyiQ7PdEwtJxwso,718
+data_designer/interface/_version.py,sha256=2_0GUP7yBCXRus-qiJKxQD62z172WSs1sQ6DVpPsbmM,704
+data_designer/interface/data_designer.py,sha256=0LBAUL7W75EmMwz-f4Lr0my9BXg1OTR2hKpgNsWnqLk,17275
+data_designer/interface/errors.py,sha256=Ft9GMeIrOHJv_PC_1rU6hWcNyq1GHdsFYZSc9HnUrxU,606
+data_designer/interface/results.py,sha256=3fGwlhif4ufqUGh-EgsGccrob4S6a7WZ6BgFiszTo_A,3871
+data_designer-0.4.0.dist-info/METADATA,sha256=yKQ114sG3AInb2Hqi5d0Totv_0xt7RUwjd7VpXFQ__w,7152
+data_designer-0.4.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+data_designer-0.4.0.dist-info/entry_points.txt,sha256=NWWWidyDxN6CYX6y664PhBYMhbaYTQTyprqfYAgkyCg,57
+data_designer-0.4.0.dist-info/RECORD,,

data_designer/__init__.py

@@ -1,17 +0,0 @@
-# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
-# SPDX-License-Identifier: Apache-2.0
-
-from __future__ import annotations
-
-try:
-    from data_designer._version import __version__
-except ImportError:
-    # Fallback for editable installs without build
-    try:
-        from importlib.metadata import version
-
-        __version__ = version("data-designer")
-    except Exception:
-        __version__ = "0.0.0.dev0+unknown"
-
-__all__ = ["__version__"]

data_designer/config/__init__.py

@@ -1,2 +0,0 @@
-# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
-# SPDX-License-Identifier: Apache-2.0

data_designer/config/analysis/__init__.py

@@ -1,2 +0,0 @@
-# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
-# SPDX-License-Identifier: Apache-2.0

data_designer/config/analysis/column_profilers.py

@@ -1,159 +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
-from enum import Enum
-
-from pydantic import BaseModel, Field
-from rich.panel import Panel
-from rich.table import Column, Table
-from typing_extensions import TypeAlias
-
-from data_designer.config.analysis.column_statistics import (
-    CategoricalDistribution,
-    CategoricalHistogramData,
-    ColumnDistributionType,
-    MissingValue,
-    NumericalDistribution,
-)
-from data_designer.config.analysis.utils.reporting import TITLE_STYLE, create_judge_score_summary_table
-from data_designer.config.base import ConfigBase
-from data_designer.config.utils.visualization import ColorPalette
-
-
-class ColumnProfilerType(str, Enum):
-    JUDGE_SCORE = "judge-score"
-
-
-class ColumnProfilerResults(BaseModel, ABC):
-    """Abstract base class for column profiler results.
-
-    Stores results from column profiling operations. Subclasses hold profiler-specific
-    analysis results and provide methods for generating formatted report sections for display.
-    """
-
-    def create_report_section(self) -> Panel:
-        """Creates a Rich Panel containing the formatted profiler results for display.
-
-        Returns:
-            A Rich Panel containing the formatted profiler results. Default implementation
-            returns a "Not Implemented" message; subclasses should override to provide
-            specific formatting.
-        """
-        return Panel(
-            f"Report section generation not implemented for '{self.__class__.__name__}'.",
-            title="Not Implemented",
-            border_style=f"bold {ColorPalette.YELLOW.value}",
-            padding=(1, 2),
-        )
-
-
-class JudgeScoreProfilerConfig(ConfigBase):
-    """Configuration for the LLM-as-a-judge score profiler.
-
-    Attributes:
-        model_alias: Alias of the LLM model to use for generating score distribution summaries.
-            Must match a model alias defined in the Data Designer configuration.
-        summary_score_sample_size: Number of score samples to include when prompting the LLM
-            to generate summaries. Larger sample sizes provide more context but increase
-            token usage. Must be at least 1. Defaults to 20.
-    """
-
-    model_alias: str
-    summary_score_sample_size: int | None = Field(default=20, ge=1)
-
-
-class JudgeScoreSample(BaseModel):
-    """Container for a single judge score and its associated reasoning.
-
-    Stores a paired score-reasoning sample extracted from an LLM-as-a-judge column.
-    Used when generating summaries to provide the LLM with examples of scoring patterns.
-
-    Attributes:
-        score: The score value assigned by the judge. Can be numeric (int) or categorical (str).
-        reasoning: The reasoning or explanation provided by the judge for this score.
-    """
-
-    score: int | str
-    reasoning: str
-
-
-class JudgeScoreDistributions(BaseModel):
-    """Container for computed distributions across all judge score dimensions.
-
-    Stores the complete distribution analysis for all score dimensions in an LLM-as-a-judge
-    column. Each score dimension (e.g., "relevance", "fluency") has its own distribution
-    computed from the generated data.
-
-    Attributes:
-        scores: Mapping of each score dimension name to its list of score values.
-        reasoning: Mapping of each score dimension name to its list of reasoning texts.
-        distribution_types: Mapping of each score dimension name to its classification.
-        distributions: Mapping of each score dimension name to its computed distribution statistics.
-        histograms: Mapping of each score dimension name to its histogram data.
-    """
-
-    scores: dict[str, list[int | str]]
-    reasoning: dict[str, list[str]]
-    distribution_types: dict[str, ColumnDistributionType]
-    distributions: dict[str, CategoricalDistribution | NumericalDistribution | MissingValue]
-    histograms: dict[str, CategoricalHistogramData | MissingValue]
-
-
-class JudgeScoreSummary(BaseModel):
-    """Container for an LLM-generated summary of a judge score dimension.
-
-    Stores the natural language summary and sample data for a single score dimension
-    generated by the judge score profiler. The summary is created by an LLM analyzing
-    the distribution and patterns in the score-reasoning pairs.
-
-    Attributes:
-        score_name: Name of the score dimension being summarized (e.g., "relevance", "fluency").
-        summary: LLM-generated natural language summary describing the scoring patterns,
-            distribution characteristics, and notable trends for this score dimension.
-        score_samples: List of score-reasoning pairs that were used to generate the summary.
-            These are the examples of the scoring behavior that were used to generate the summary.
-    """
-
-    score_name: str
-    summary: str
-    score_samples: list[JudgeScoreSample]
-
-
-class JudgeScoreProfilerResults(ColumnProfilerResults):
-    """Container for complete judge score profiler analysis results.
-
-    Attributes:
-        column_name: Name of the judge column that was profiled.
-        summaries: Mapping of each score dimension name to its LLM-generated summary.
-        score_distributions: Complete distribution analysis across all score dimensions.
-    """
-
-    column_name: str
-    summaries: dict[str, JudgeScoreSummary]
-    score_distributions: JudgeScoreDistributions | MissingValue
-
-    def create_report_section(self) -> Panel:
-        layout = Table.grid(Column(), expand=True, padding=(2, 0))
-
-        for score_name in self.summaries.keys():
-            layout.add_row(
-                create_judge_score_summary_table(
-                    score_name=score_name,
-                    histogram=self.score_distributions.histograms[score_name],
-                    summary=self.summaries[score_name].summary,
-                )
-            )
-
-        return Panel(
-            layout,
-            title=f"[{TITLE_STYLE}]LLM-as-a-Judge Score Profile: '{self.column_name}'[/{TITLE_STYLE}]",
-            padding=(1, 2),
-        )
-
-
-ColumnProfilerConfigT: TypeAlias = JudgeScoreProfilerConfig
-
-ColumnProfilerResultsT: TypeAlias = JudgeScoreProfilerResults