data-designer 0.1.4__py3-none-any.whl → 0.1.5__py3-none-any.whl

data_designer/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.1.4'
-__version_tuple__ = version_tuple = (0, 1, 4)
+__version__ = version = '0.1.5'
+__version_tuple__ = version_tuple = (0, 1, 5)
 
 __commit_id__ = commit_id = None

data_designer/config/exports.py

@@ -32,7 +32,11 @@ from data_designer.config.models import (
     UniformDistribution,
     UniformDistributionParams,
 )
-from data_designer.config.processors import DropColumnsProcessorConfig, ProcessorType
+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,
@@ -69,6 +73,7 @@ from data_designer.config.validator_params import (
 
 def get_config_exports() -> list[str]:
     return [
+        SchemaTransformProcessorConfig.__name__,
         BernoulliMixtureSamplerParams.__name__,
         BernoulliSamplerParams.__name__,
         BinomialSamplerParams.__name__,

data_designer/config/preview_results.py

@@ -3,7 +3,7 @@
 
 from __future__ import annotations
 
-from typing import Optional
+from typing import Optional, Union
 
 import pandas as pd
 
@@ -19,6 +19,7 @@ class PreviewResults(WithRecordSamplerMixin):
         config_builder: DataDesignerConfigBuilder,
         dataset: Optional[pd.DataFrame] = None,
         analysis: Optional[DatasetProfilerResults] = None,
+        processor_artifacts: Optional[dict[str, Union[list[str], str]]] = None,
     ):
         """Creates a new instance with results from a Data Designer preview run.
 
@@ -26,7 +27,9 @@ class PreviewResults(WithRecordSamplerMixin):
             config_builder: Data Designer configuration builder.
             dataset: Dataset of the preview run.
             analysis: Analysis of the preview run.
+            processor_artifacts: Artifacts generated by the processors.
         """
-        self.dataset: pd.DataFrame | None = dataset
-        self.analysis: DatasetProfilerResults | None = analysis
+        self.dataset: Optional[pd.DataFrame] = dataset
+        self.analysis: Optional[DatasetProfilerResults] = analysis
+        self.processor_artifacts: Optional[dict[str, Union[list[str], str]]] = processor_artifacts
         self._config_builder = config_builder

data_designer/config/processors.py

@@ -1,25 +1,32 @@
 # SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 
+import json
 from abc import ABC
 from enum import Enum
-from typing import Literal
+from typing import Any, Literal
 
 from pydantic import Field, field_validator
 
 from data_designer.config.base import ConfigBase
 from data_designer.config.dataset_builders import BuildStage
+from data_designer.config.errors import InvalidConfigError
 
 SUPPORTED_STAGES = [BuildStage.POST_BATCH]
 
 
 class ProcessorType(str, Enum):
     DROP_COLUMNS = "drop_columns"
+    SCHEMA_TRANSFORM = "schema_transform"
 
 
 class ProcessorConfig(ConfigBase, ABC):
+    name: str = Field(
+        description="The name of the processor, used to identify the processor in the results and to write the artifacts to disk.",
+    )
     build_stage: BuildStage = Field(
-        ..., description=f"The stage at which the processor will run. Supported stages: {', '.join(SUPPORTED_STAGES)}"
+        default=BuildStage.POST_BATCH,
+        description=f"The stage at which the processor will run. Supported stages: {', '.join(SUPPORTED_STAGES)}",
     )
 
     @field_validator("build_stage")
@@ -34,8 +41,45 @@ class ProcessorConfig(ConfigBase, ABC):
 def get_processor_config_from_kwargs(processor_type: ProcessorType, **kwargs) -> ProcessorConfig:
     if processor_type == ProcessorType.DROP_COLUMNS:
         return DropColumnsProcessorConfig(**kwargs)
+    elif processor_type == ProcessorType.SCHEMA_TRANSFORM:
+        return SchemaTransformProcessorConfig(**kwargs)
 
 
 class DropColumnsProcessorConfig(ProcessorConfig):
     column_names: list[str]
     processor_type: Literal[ProcessorType.DROP_COLUMNS] = ProcessorType.DROP_COLUMNS
+
+
+class SchemaTransformProcessorConfig(ProcessorConfig):
+    template: dict[str, Any] = Field(
+        ...,
+        description="""
+        Dictionary specifying columns and templates to use in the new dataset with transformed schema.
+
+        Each key is a new column name, and each value is an object containing Jinja2 templates - for instance, a string or a list of strings.
+        Values must be JSON-serializable.
+
+        Example:
+
+        ```python
+        template = {
+            "list_of_strings": ["{{ col1 }}", "{{ col2 }}"],
+            "uppercase_string": "{{ col1 | upper }}",
+            "lowercase_string": "{{ col2 | lower }}",
+        }
+        ```
+
+        The above templates will create an new dataset with three columns: "list_of_strings", "uppercase_string", and "lowercase_string".
+        References to columns "col1" and "col2" in the templates will be replaced with the actual values of the columns in the dataset.
+        """,
+    )
+    processor_type: Literal[ProcessorType.SCHEMA_TRANSFORM] = ProcessorType.SCHEMA_TRANSFORM
+
+    @field_validator("template")
+    def validate_template(cls, v: dict[str, Any]) -> dict[str, Any]:
+        try:
+            json.dumps(v)
+        except TypeError as e:
+            if "not JSON serializable" in str(e):
+                raise InvalidConfigError("Template must be JSON serializable")
+        return v

data_designer/config/utils/validation.py

@@ -18,7 +18,10 @@ from rich.panel import Panel
 from data_designer.config.column_types import ColumnConfigT, DataDesignerColumnType, column_type_is_llm_generated
 from data_designer.config.processors import ProcessorConfig, ProcessorType
 from data_designer.config.utils.constants import RICH_CONSOLE_THEME
-from data_designer.config.utils.misc import can_run_data_designer_locally
+from data_designer.config.utils.misc import (
+    can_run_data_designer_locally,
+    get_prompt_template_keywords,
+)
 from data_designer.config.validator_params import ValidatorType
 
 
@@ -63,6 +66,7 @@ def validate_data_designer_config(
     violations.extend(validate_expression_references(columns=columns, allowed_references=allowed_references))
     violations.extend(validate_columns_not_all_dropped(columns=columns))
     violations.extend(validate_drop_columns_processor(columns=columns, processor_configs=processor_configs))
+    violations.extend(validate_schema_transform_processor(columns=columns, processor_configs=processor_configs))
     if not can_run_data_designer_locally():
         violations.extend(validate_local_only_columns(columns=columns))
     return violations
@@ -271,7 +275,7 @@ def validate_drop_columns_processor(
     columns: list[ColumnConfigT],
     processor_configs: list[ProcessorConfig],
 ) -> list[Violation]:
-    all_column_names = set([c.name for c in columns])
+    all_column_names = {c.name for c in columns}
     for processor_config in processor_configs:
         if processor_config.processor_type == ProcessorType.DROP_COLUMNS:
             invalid_columns = set(processor_config.column_names) - all_column_names
@@ -288,6 +292,33 @@ def validate_drop_columns_processor(
     return []
 
 
+def validate_schema_transform_processor(
+    columns: list[ColumnConfigT],
+    processor_configs: list[ProcessorConfig],
+) -> list[Violation]:
+    violations = []
+
+    all_column_names = {c.name for c in columns}
+    for processor_config in processor_configs:
+        if processor_config.processor_type == ProcessorType.SCHEMA_TRANSFORM:
+            for col, template in processor_config.template.items():
+                template_keywords = get_prompt_template_keywords(template)
+                invalid_keywords = set(template_keywords) - all_column_names
+                if len(invalid_keywords) > 0:
+                    invalid_keywords = ", ".join([f"'{k}'" for k in invalid_keywords])
+                    message = f"Ancillary dataset processor attempts to reference columns {invalid_keywords} in the template for '{col}', but the columns are not defined in the dataset."
+                    violations.append(
+                        Violation(
+                            column=None,
+                            type=ViolationType.INVALID_REFERENCE,
+                            message=message,
+                            level=ViolationLevel.ERROR,
+                        )
+                    )
+
+    return violations
+
+
 def validate_expression_references(
     columns: list[ColumnConfigT],
     allowed_references: list[str],

data_designer/config/utils/visualization.py

@@ -72,6 +72,9 @@ class WithRecordSamplerMixin:
         else:
             raise DatasetSampleDisplayError("No valid dataset found in results object.")
 
+    def _has_processor_artifacts(self) -> bool:
+        return hasattr(self, "processor_artifacts") and self.processor_artifacts is not None
+
     def display_sample_record(
         self,
         index: Optional[int] = None,
@@ -79,6 +82,7 @@ class WithRecordSamplerMixin:
         hide_seed_columns: bool = False,
         syntax_highlighting_theme: str = "dracula",
         background_color: Optional[str] = None,
+        processors_to_display: Optional[list[str]] = None,
     ) -> None:
         """Display a sample record from the Data Designer dataset preview.
 
@@ -90,6 +94,7 @@ class WithRecordSamplerMixin:
                 documentation from `rich` for information about available themes.
             background_color: Background color to use for the record. See the `Syntax`
                 documentation from `rich` for information about available background colors.
+            processors_to_display: List of processors to display the artifacts for. If None, all processors will be displayed.
         """
         i = index or self._display_cycle_index
 
@@ -99,8 +104,25 @@ class WithRecordSamplerMixin:
         except IndexError:
             raise DatasetSampleDisplayError(f"Index {i} is out of bounds for dataset of length {num_records}.")
 
+        processor_data_to_display = None
+        if self._has_processor_artifacts() and len(self.processor_artifacts) > 0:
+            if processors_to_display is None:
+                processors_to_display = list(self.processor_artifacts.keys())
+
+            if len(processors_to_display) > 0:
+                processor_data_to_display = {}
+                for processor in processors_to_display:
+                    if (
+                        isinstance(self.processor_artifacts[processor], list)
+                        and len(self.processor_artifacts[processor]) == num_records
+                    ):
+                        processor_data_to_display[processor] = self.processor_artifacts[processor][i]
+                    else:
+                        processor_data_to_display[processor] = self.processor_artifacts[processor]
+
         display_sample_record(
             record=record,
+            processor_data_to_display=processor_data_to_display,
             config_builder=self._config_builder,
             background_color=background_color,
             syntax_highlighting_theme=syntax_highlighting_theme,
@@ -134,6 +156,7 @@ def create_rich_histogram_table(
 def display_sample_record(
     record: Union[dict, pd.Series, pd.DataFrame],
     config_builder: DataDesignerConfigBuilder,
+    processor_data_to_display: Optional[dict[str, Union[list[str], str]]] = None,
     background_color: Optional[str] = None,
     syntax_highlighting_theme: str = "dracula",
     record_index: Optional[int] = None,
@@ -230,6 +253,15 @@ def display_sample_record(
             table.add_row(*row)
             render_list.append(pad_console_element(table, (1, 0, 1, 0)))
 
+    if processor_data_to_display and len(processor_data_to_display) > 0:
+        for processor_name, processor_data in processor_data_to_display.items():
+            table = Table(title=f"Processor Outputs: {processor_name}", **table_kws)
+            table.add_column("Name")
+            table.add_column("Value")
+            for col, value in processor_data.items():
+                table.add_row(col, convert_to_row_element(value))
+        render_list.append(pad_console_element(table, (1, 0, 1, 0)))
+
     if record_index is not None:
         index_label = Text(f"[index: {record_index}]", justify="center")
         render_list.append(index_label)

data_designer/engine/dataset_builders/artifact_storage.py

@@ -25,6 +25,7 @@ class BatchStage(StrEnum):
     PARTIAL_RESULT = "partial_results_path"
     FINAL_RESULT = "final_dataset_path"
     DROPPED_COLUMNS = "dropped_columns_dataset_path"
+    PROCESSORS_OUTPUTS = "processors_outputs_path"
 
 
 class ArtifactStorage(BaseModel):
@@ -33,6 +34,7 @@ class ArtifactStorage(BaseModel):
     final_dataset_folder_name: str = "parquet-files"
     partial_results_folder_name: str = "tmp-partial-parquet-files"
     dropped_columns_folder_name: str = "dropped-columns-parquet-files"
+    processors_outputs_folder_name: str = "processors-files"
 
     @property
     def artifact_path_exists(self) -> bool:
@@ -70,6 +72,10 @@ class ArtifactStorage(BaseModel):
     def partial_results_path(self) -> Path:
         return self.base_dataset_path / self.partial_results_folder_name
 
+    @property
+    def processors_outputs_path(self) -> Path:
+        return self.base_dataset_path / self.processors_outputs_folder_name
+
     @field_validator("artifact_path")
     def validate_artifact_path(cls, v: Union[Path, str]) -> Path:
         v = Path(v)
@@ -84,6 +90,7 @@ class ArtifactStorage(BaseModel):
             self.final_dataset_folder_name,
             self.partial_results_folder_name,
             self.dropped_columns_folder_name,
+            self.processors_outputs_folder_name,
         ]
 
         for name in folder_names:
@@ -169,9 +176,10 @@ class ArtifactStorage(BaseModel):
         batch_number: int,
         dataframe: pd.DataFrame,
         batch_stage: BatchStage,
+        subfolder: str | None = None,
     ) -> Path:
         file_path = self.create_batch_file_path(batch_number, batch_stage=batch_stage)
-        self.write_parquet_file(file_path.name, dataframe, batch_stage)
+        self.write_parquet_file(file_path.name, dataframe, batch_stage, subfolder=subfolder)
         return file_path
 
     def write_parquet_file(
@@ -179,9 +187,11 @@ class ArtifactStorage(BaseModel):
         parquet_file_name: str,
         dataframe: pd.DataFrame,
         batch_stage: BatchStage,
+        subfolder: str | None = None,
     ) -> Path:
-        self.mkdir_if_needed(self._get_stage_path(batch_stage))
-        file_path = self._get_stage_path(batch_stage) / parquet_file_name
+        subfolder = subfolder or ""
+        self.mkdir_if_needed(self._get_stage_path(batch_stage) / subfolder)
+        file_path = self._get_stage_path(batch_stage) / subfolder / parquet_file_name
         dataframe.to_parquet(file_path, index=False)
         return file_path
 

data_designer/engine/dataset_builders/column_wise_builder.py

@@ -171,6 +171,8 @@ class ColumnWiseDatasetBuilder:
         max_workers = MAX_CONCURRENCY_PER_NON_LLM_GENERATOR
         if isinstance(generator, WithLLMGeneration):
             max_workers = generator.inference_parameters.max_parallel_requests
+        elif hasattr(generator.config, "max_parallel_requests"):
+            max_workers = generator.config.max_parallel_requests
         self._fan_out_with_threads(generator, max_workers=max_workers)
 
     def _run_full_column_generator(self, generator: ColumnGenerator) -> None:
@@ -244,6 +246,7 @@ class ColumnWiseDatasetBuilder:
             processors[BuildStage.POST_BATCH].append(  # as post-batch by default
                 DropColumnsProcessor(
                     config=DropColumnsProcessorConfig(
+                        name="default_drop_columns_processor",
                         column_names=columns_to_drop,
                         build_stage=BuildStage.POST_BATCH,
                     ),

data_designer/engine/processing/processors/drop_columns.py

@@ -17,7 +17,7 @@ class DropColumnsProcessor(Processor[DropColumnsProcessorConfig]):
     @staticmethod
     def metadata() -> ConfigurableTaskMetadata:
         return ConfigurableTaskMetadata(
-            name="drop_columns",
+            name="drop_columns_processor",
             description="Drop columns from the input dataset.",
             required_resources=None,
         )

data_designer/engine/processing/processors/registry.py

@@ -5,9 +5,11 @@ from data_designer.config.base import ConfigBase
 from data_designer.config.processors import (
     DropColumnsProcessorConfig,
     ProcessorType,
+    SchemaTransformProcessorConfig,
 )
 from data_designer.engine.processing.processors.base import Processor
 from data_designer.engine.processing.processors.drop_columns import DropColumnsProcessor
+from data_designer.engine.processing.processors.schema_transform import SchemaTransformProcessor
 from data_designer.engine.registry.base import TaskRegistry
 
 
@@ -16,5 +18,6 @@ class ProcessorRegistry(TaskRegistry[str, Processor, ConfigBase]): ...
 
 def create_default_processor_registry() -> ProcessorRegistry:
     registry = ProcessorRegistry()
+    registry.register(ProcessorType.SCHEMA_TRANSFORM, SchemaTransformProcessor, SchemaTransformProcessorConfig, False)
     registry.register(ProcessorType.DROP_COLUMNS, DropColumnsProcessor, DropColumnsProcessorConfig, False)
     return registry

data_designer/engine/processing/processors/schema_transform.py

@@ -0,0 +1,53 @@
+# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+
+import json
+import logging
+
+import pandas as pd
+
+from data_designer.config.processors import SchemaTransformProcessorConfig
+from data_designer.engine.configurable_task import ConfigurableTaskMetadata
+from data_designer.engine.dataset_builders.artifact_storage import BatchStage
+from data_designer.engine.processing.ginja.environment import WithJinja2UserTemplateRendering
+from data_designer.engine.processing.processors.base import Processor
+from data_designer.engine.processing.utils import deserialize_json_values
+
+logger = logging.getLogger(__name__)
+
+
+class SchemaTransformProcessor(WithJinja2UserTemplateRendering, Processor[SchemaTransformProcessorConfig]):
+    @staticmethod
+    def metadata() -> ConfigurableTaskMetadata:
+        return ConfigurableTaskMetadata(
+            name="schema_transform_processor",
+            description="Generate dataset with transformed schema using a Jinja2 template.",
+            required_resources=None,
+        )
+
+    @property
+    def template_as_str(self) -> str:
+        return json.dumps(self.config.template)
+
+    def process(self, data: pd.DataFrame, *, current_batch_number: int | None = None) -> pd.DataFrame:
+        self.prepare_jinja2_template_renderer(self.template_as_str, data.columns.to_list())
+        formatted_records = [
+            json.loads(self.render_template(deserialize_json_values(record)).replace("\n", "\\n"))
+            for record in data.to_dict(orient="records")
+        ]
+        formatted_data = pd.DataFrame(formatted_records)
+        if current_batch_number is not None:
+            self.artifact_storage.write_batch_to_parquet_file(
+                batch_number=current_batch_number,
+                dataframe=formatted_data,
+                batch_stage=BatchStage.PROCESSORS_OUTPUTS,
+                subfolder=self.config.name,
+            )
+        else:
+            self.artifact_storage.write_parquet_file(
+                parquet_file_name=f"{self.config.name}.parquet",
+                dataframe=formatted_data,
+                batch_stage=BatchStage.PROCESSORS_OUTPUTS,
+            )
+
+        return data

data_designer/interface/data_designer.py

@@ -249,6 +249,17 @@ class DataDesigner(DataDesignerInterface[DatasetCreationResults]):
         except Exception as e:
             raise DataDesignerProfilingError(f"🛑 Error profiling preview dataset: {e}")
 
+        if builder.artifact_storage.processors_outputs_path.exists():
+            processor_artifacts = {
+                processor_config.name: pd.read_parquet(
+                    builder.artifact_storage.processors_outputs_path / f"{processor_config.name}.parquet",
+                    dtype_backend="pyarrow",
+                ).to_dict(orient="records")
+                for processor_config in config_builder.get_processor_configs()
+            }
+        else:
+            processor_artifacts = {}
+
         if (
             len(processed_dataset) > 0
             and isinstance(analysis, DatasetProfilerResults)
@@ -259,6 +270,7 @@ class DataDesigner(DataDesignerInterface[DatasetCreationResults]):
         return PreviewResults(
             dataset=processed_dataset,
             analysis=analysis,
+            processor_artifacts=processor_artifacts,
             config_builder=config_builder,
         )
 

data_designer/interface/results.py

@@ -3,12 +3,15 @@
 
 from __future__ import annotations
 
+from pathlib import Path
+
 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.utils.visualization import WithRecordSamplerMixin
 from data_designer.engine.dataset_builders.artifact_storage import ArtifactStorage
+from data_designer.engine.dataset_builders.errors import ArtifactStorageError
 
 
 class DatasetCreationResults(WithRecordSamplerMixin):
@@ -53,3 +56,36 @@ class DatasetCreationResults(WithRecordSamplerMixin):
             A pandas DataFrame containing the full generated dataset.
         """
         return self.artifact_storage.load_dataset()
+
+    def load_processor_dataset(self, processor_name: str) -> pd.DataFrame:
+        """Load the dataset generated by a processor.
+
+        This only works for processors that write their artifacts in Parquet format.
+
+        Args:
+            processor_name: The name of the processor to load the dataset from.
+
+        Returns:
+            A pandas DataFrame containing the dataset generated by the processor.
+        """
+        try:
+            dataset = self.artifact_storage.read_parquet_files(
+                self.artifact_storage.processors_outputs_path / processor_name
+            )
+        except Exception as e:
+            raise ArtifactStorageError(f"Failed to load dataset for processor {processor_name}: {e}")
+
+        return dataset
+
+    def get_path_to_processor_artifacts(self, processor_name: str) -> Path:
+        """Get the path to the artifacts generated by a processor.
+
+        Args:
+            processor_name: The name of the processor to load the artifact from.
+
+        Returns:
+            The path to the artifacts.
+        """
+        if not self.artifact_storage.processors_outputs_path.exists():
+            raise ArtifactStorageError(f"Processor {processor_name} has no artifacts.")
+        return self.artifact_storage.processors_outputs_path / processor_name

{data_designer-0.1.4.dist-info → data_designer-0.1.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-designer
-Version: 0.1.4
+Version: 0.1.5
 Summary: General framework for synthetic data generation
 License-Expression: Apache-2.0
 License-File: LICENSE
@@ -144,12 +144,12 @@ preview.display_sample_record()
 
 ### 📚 Learn more
 
-- **[Quick Start Guide](https://nvidia-nemo.github.io/DataDesigner/quick-start/)** – Detailed walkthrough with more examples
-- **[Tutorial Notebooks](https://nvidia-nemo.github.io/DataDesigner/notebooks/)** – Step-by-step interactive tutorials
-- **[Column Types](https://nvidia-nemo.github.io/DataDesigner/concepts/columns/)** – Explore samplers, LLM columns, validators, and more
-- **[Validators](https://nvidia-nemo.github.io/DataDesigner/concepts/validators/)** – Learn how to validate generated data with Python, SQL, and remote validators
-- **[Model Configuration](https://nvidia-nemo.github.io/DataDesigner/concepts/models/model-configs/)** – Configure custom models and providers
-- **[Person Sampling](https://nvidia-nemo.github.io/DataDesigner/concepts/person_sampling/)** – Learn how to sample realistic person data with demographic attributes
+- **[Quick Start Guide](https://nvidia-nemo.github.io/DataDesigner/latest/quick-start/)** – Detailed walkthrough with more examples
+- **[Tutorial Notebooks](https://nvidia-nemo.github.io/DataDesigner/latest/notebooks/)** – Step-by-step interactive tutorials
+- **[Column Types](https://nvidia-nemo.github.io/DataDesigner/latest/concepts/columns/)** – Explore samplers, LLM columns, validators, and more
+- **[Validators](https://nvidia-nemo.github.io/DataDesigner/latest/concepts/validators/)** – Learn how to validate generated data with Python, SQL, and remote validators
+- **[Model Configuration](https://nvidia-nemo.github.io/DataDesigner/latest/concepts/models/model-configs/)** – Configure custom models and providers
+- **[Person Sampling](https://nvidia-nemo.github.io/DataDesigner/latest/concepts/person_sampling/)** – Learn how to sample realistic person data with demographic attributes
 
 ### 🔧 Configure models via CLI
 
@@ -161,7 +161,7 @@ data-designer config list      # View current settings
 
 ### 🤝 Get involved
 
-- **[Contributing Guide](https://nvidia-nemo.github.io/DataDesigner/CONTRIBUTING)** – Help improve Data Designer
+- **[Contributing Guide](https://nvidia-nemo.github.io/DataDesigner/latest/CONTRIBUTING)** – Help improve Data Designer
 - **[GitHub Issues](https://github.com/NVIDIA-NeMo/DataDesigner/issues)** – Report bugs or make a feature request
 
 ---
@@ -178,7 +178,7 @@ If you use NeMo Data Designer in your research, please cite it using the followi
 
 ```bibtex
 @misc{nemo-data-designer,
-  author = {The NeMo Data Designer Team},
+  author = {The NeMo Data Designer Team, NVIDIA},
   title = {NeMo Data Designer: A framework for generating synthetic data from scratch or based on your own seed data},
   howpublished = {\url{https://github.com/NVIDIA-NeMo/DataDesigner}},
   year = {2025},

{data_designer-0.1.4.dist-info → data_designer-0.1.5.dist-info}/RECORD

@@ -1,5 +1,5 @@
 data_designer/__init__.py,sha256=iCeqRnb640RrL2QpA630GY5Ng7JiDt83Vq0DwLnNugU,461
-data_designer/_version.py,sha256=rLCrf4heo25FJtBY-2Ap7ZuWW-5FS7sqTjsolIUuI5c,704
+data_designer/_version.py,sha256=rdxBMYpwzYxiWk08QbPLHSAxHoDfeKWwyaJIAM0lSic,704
 data_designer/errors.py,sha256=Z4eN9XwzZvGRdBluSNoSqQYkPPzNQIDf0ET_OqWRZh8,179
 data_designer/logging.py,sha256=OqRGvWNlGA3ebRFts7e5k-5GFwoAPaGXYQS4oEzVG0o,5354
 data_designer/plugin_manager.py,sha256=eXtmmqyyoVHWO1zvlLvKQ-rTrONJxf9jhr4ZMzsXWSE,2610
@@ -39,11 +39,11 @@ data_designer/config/dataset_builders.py,sha256=1pNFy_pkQ5lJ6AVZ43AeTuSbz6yC_l7N
 data_designer/config/datastore.py,sha256=brMylPuBsT7uDKSy7G59M7Zdx91RTYWMOVcdRVe5Wjs,7632
 data_designer/config/default_model_settings.py,sha256=HAGyfYzT1fdWMpMSLeJuZZZQHKku2T9KJTOhpwS_5Ek,4577
 data_designer/config/errors.py,sha256=MNMnqh8G1XzXAMeJ5ju6zkBiIH2aVgyITnzYJbGEwFY,461
-data_designer/config/exports.py,sha256=FoyxvW7fckm_KYRU-sgtAJUM8GWWHaDakX8Zk3DAokE,4342
+data_designer/config/exports.py,sha256=vDokNLxoBlaII_-TBIS4w65t-g-MX8ADV85arpOPBRA,4440
 data_designer/config/interface.py,sha256=ery8a93pnCW1JPbgtiaRsMKSR8Q2o7rDmsZfVYbfkeE,1619
 data_designer/config/models.py,sha256=kB9Ut9Y00V6nG9zKK2c4xIVZewn3vPPIU6deug_Rttc,11362
-data_designer/config/preview_results.py,sha256=6SXdkq3oz15VxB7RGroSWikDP1EVPbbBn8GbMrRn2Wc,1147
-data_designer/config/processors.py,sha256=9JeXbGi79QSJanzjiFIDvCxRqriQDlaOtycDVYVUFI4,1368
+data_designer/config/preview_results.py,sha256=6FHBUJAxYEoLq8raCCkQYPUSJTQLvhXFMKciOBU_mVw,1411
+data_designer/config/processors.py,sha256=Q1fCRoL7YSWAnLwJ6sGERwQXdJNx4By8WVyHhjwtd_8,3172
 data_designer/config/sampler_constraints.py,sha256=Dxbjt5PNNmvm5CMp-Z5CYrfd6oeDeXOUnODR6FgvCDk,1187
 data_designer/config/sampler_params.py,sha256=50OEhC1AF3EPMoMlpJGGZ72kXej5wsqcZiyt7J7Kx08,26614
 data_designer/config/seed.py,sha256=tKzNUvHx-9JV8uPDUbQqx44tG88CAeCss_T8xFEPh5g,5547
@@ -61,8 +61,8 @@ data_designer/config/utils/io_helpers.py,sha256=Jl1ihaQM0K_SL86UfP0N1-y4KVph4z3S
 data_designer/config/utils/misc.py,sha256=HVRvrbpdO5c_oPI-e_3hrS7cBJA1SaG8iHMLtWKVv8A,2526
 data_designer/config/utils/numerical_helpers.py,sha256=tcm5x5qSURoZZHjN9Bm1-Jkct3G67QefXm10QQXDtlM,803
 data_designer/config/utils/type_helpers.py,sha256=RvhDk4rxQKDOMBLqJiMM4IJXdLoNUf3uzW52vB5cqrg,4024
-data_designer/config/utils/validation.py,sha256=wXXzdZXVAWraM6XbH21zMb-X2RvzQvzZSC290G8-iks,13079
-data_designer/config/utils/visualization.py,sha256=dk1TQRTg2Uo08mqEabSxui5wXOk4YgjC-Cd4Autilmc,15784
+data_designer/config/utils/validation.py,sha256=1MoVqrS_DofT0LDIrGpWTPi02chntZT1p2K0FIyUOzs,14463
+data_designer/config/utils/visualization.py,sha256=X0R-EDW-yzIaYtK1ttLsCXEp6a6ubejvm_9xpO2UrMg,17599
 data_designer/engine/__init__.py,sha256=9eG4WHKyrJcNoK4GEz6BCw_E0Ewo9elQoDN4TLMbAog,137
 data_designer/engine/configurable_task.py,sha256=GnaBG6xVBQ1ELpzumNctwKYZJvKKjh2LMKhws4W2GS4,3124
 data_designer/engine/errors.py,sha256=DUoKhQCSwIBoLSQGv7dstzO3DFGDRqW3MBoWnRPcm1I,1262
@@ -88,8 +88,8 @@ data_designer/engine/column_generators/generators/validation.py,sha256=MbDFXzief
 data_designer/engine/column_generators/utils/errors.py,sha256=ugNwaqnPdrPZI7YnKLbYwFjYUSm0WAzgaVu_u6i5Rc8,365
 data_designer/engine/column_generators/utils/judge_score_factory.py,sha256=JRoaZgRGK24dH0zx7MNGSccK196tQK_l0sbwNkurg7c,2132
 data_designer/engine/column_generators/utils/prompt_renderer.py,sha256=d4tbyPsgmFDikW3nxL5is9RNaajMkoPDCrfkQkxw7rc,4760
-data_designer/engine/dataset_builders/artifact_storage.py,sha256=r70ZoohD-givRxd0mQT7JBZiUp1hhQvu_zzH-g_lQbU,7995
-data_designer/engine/dataset_builders/column_wise_builder.py,sha256=OSpIAChevQpLjMehP9zFwJbIURaZN-sEF0Hhy8QTbGA,13074
+data_designer/engine/dataset_builders/artifact_storage.py,sha256=GCHuKuQ6Y_ePG515rsqc3NzQtN1v4pEV2L1I2H2_tx4,8451
+data_designer/engine/dataset_builders/column_wise_builder.py,sha256=ljf-2fAKdry1UCVubhkhRWhoVlKZfK77ytwgkjuQ5VY,13267
 data_designer/engine/dataset_builders/errors.py,sha256=1kChleChG4rASWIiL4Bel6Ox6aFZjQUrh5ogPt1CDWo,359
 data_designer/engine/dataset_builders/multi_column_configs.py,sha256=t28fhI-WRIBohFnAJ80l5EAETEDB5rJ5RSWInMiRfyE,1619
 data_designer/engine/dataset_builders/utils/__init__.py,sha256=9eG4WHKyrJcNoK4GEz6BCw_E0Ewo9elQoDN4TLMbAog,137
@@ -125,8 +125,9 @@ data_designer/engine/processing/gsonschema/schema_transformers.py,sha256=__-dfrC
 data_designer/engine/processing/gsonschema/types.py,sha256=-x_K2HrVnZ_Z7fzYl4T2Gd7QHf6B6ADvn7E7iYvw5Kc,313
 data_designer/engine/processing/gsonschema/validators.py,sha256=5Jh864KnA5gWBeLbpz1cE5Kk_GMxI6kPWvunAbLI3vI,4704
 data_designer/engine/processing/processors/base.py,sha256=WJl7_0dtiUppjfY-lrQ3lDiIgYqRDSEYUwSAQNN7nFE,548
-data_designer/engine/processing/processors/drop_columns.py,sha256=-ATddFz8efrM2jwiG6w7vgtj48VVy4ZoDvSbGY0aZfY,2050
-data_designer/engine/processing/processors/registry.py,sha256=2zr91IjEMy7duN43fkborPekXohA_X1J8BSKVc1rJKk,804
+data_designer/engine/processing/processors/drop_columns.py,sha256=MIb_CVrpoM3kyN5-8dHZrdFAAUiCCWgDEyQjAk8nZqE,2060
+data_designer/engine/processing/processors/registry.py,sha256=nhB1O4b0wSUkWQeleV9l1MykwZD-dSvY0ydqmSscEY8,1056
+data_designer/engine/processing/processors/schema_transform.py,sha256=amRIw69F5Mn6ZrJvov3ZCRXk-Vil1_adQ1_rC6VKELg,2233
 data_designer/engine/registry/base.py,sha256=8h5MRPccLGSGcss3qFoQ-i7XGzvn8gdiRR0tYr7mDgk,3544
 data_designer/engine/registry/data_designer_registry.py,sha256=0nO7JEezwc2wnnDRKAX5BZz6RhBI3-kNU3Eb1WAdCFI,1487
 data_designer/engine/registry/errors.py,sha256=nO794QVy4DovKGKWEjycVDN9cdDlH-skbZLTb354M3Y,309
@@ -164,15 +165,15 @@ data_designer/engine/validators/remote.py,sha256=jtDIvWzfHh17m2ac_Fp93p49Th8RlkB
 data_designer/engine/validators/sql.py,sha256=bxbyxPxDT9yuwjhABVEY40iR1pzWRFi65WU4tPgG2bE,2250
 data_designer/essentials/__init__.py,sha256=eHuZFJTmeRf_b6KQZ2vZeqy1afJ7y7RMTm7q4Jrg58s,1012
 data_designer/interface/__init__.py,sha256=9eG4WHKyrJcNoK4GEz6BCw_E0Ewo9elQoDN4TLMbAog,137
-data_designer/interface/data_designer.py,sha256=fnkKrhOW-uI6LDxpVHHbnySmCSEuEUfDh4mHgIpDm6c,16288
+data_designer/interface/data_designer.py,sha256=O6PehBIdL4_2d9rFW86J9b3jfJ_CJmFId8T2AviM2zM,16844
 data_designer/interface/errors.py,sha256=jagKT3tPUnYq4e3e6AkTnBkcayHyEfxjPMBzx-GEKe4,565
-data_designer/interface/results.py,sha256=qFxa8SuCXeADiRpaCMBwJcExkJBCfUPeGCdcJSTjoTc,2111
+data_designer/interface/results.py,sha256=zYVX589OUyFuB-8XLmjjdKk3hCDNKu189sH-gOOFreQ,3511
 data_designer/plugins/__init__.py,sha256=c_V7q4QhfVoNf_uc9UwmXCsWqwtyWogI7YoN_0PzzE4,234
 data_designer/plugins/errors.py,sha256=yPIHpSddEr-o9ZcNVibb2hI-73O15Kg_Od8SlmQlnRs,297
 data_designer/plugins/plugin.py,sha256=7ErdUyrTdOb5PCBE3msdhTOrvQpldjOQw90-Bu4Bosc,2522
 data_designer/plugins/registry.py,sha256=w0o7I3A5UpIaCiqSJIj3kv_dLlh7m_WHznP_O-X13-s,3018
-data_designer-0.1.4.dist-info/METADATA,sha256=Sf3MnCQkIfyO53T7lSqn20ckC_mFLx8tlOpd8izk-nc,6653
-data_designer-0.1.4.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-data_designer-0.1.4.dist-info/entry_points.txt,sha256=NWWWidyDxN6CYX6y664PhBYMhbaYTQTyprqfYAgkyCg,57
-data_designer-0.1.4.dist-info/licenses/LICENSE,sha256=cSWJDwVqHyQgly8Zmt3pqXJ2eQbZVYwN9qd0NMssxXY,11336
-data_designer-0.1.4.dist-info/RECORD,,
+data_designer-0.1.5.dist-info/METADATA,sha256=s4j9BlO8RDnExQPVbFCYZhY5FNI539DanL-sLEmwzGk,6710
+data_designer-0.1.5.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+data_designer-0.1.5.dist-info/entry_points.txt,sha256=NWWWidyDxN6CYX6y664PhBYMhbaYTQTyprqfYAgkyCg,57
+data_designer-0.1.5.dist-info/licenses/LICENSE,sha256=cSWJDwVqHyQgly8Zmt3pqXJ2eQbZVYwN9qd0NMssxXY,11336
+data_designer-0.1.5.dist-info/RECORD,,