data-designer 0.3.3__py3-none-any.whl → 0.3.4__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 = '0.3.3'
-__version_tuple__ = version_tuple = (0, 3, 3)
+__version__ = version = '0.3.4'
+__version_tuple__ = version_tuple = (0, 3, 4)
 
 __commit_id__ = commit_id = None

data_designer/config/base.py

@@ -18,6 +18,7 @@ class ConfigBase(BaseModel):
         use_enum_values=True,
         arbitrary_types_allowed=True,
         extra="forbid",
+        json_schema_mode_override="validation",
     )
 
 

data_designer/config/dataset_metadata.py

@@ -0,0 +1,18 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+
+from pydantic import BaseModel
+
+
+class DatasetMetadata(BaseModel):
+    """Metadata about a generated dataset.
+
+    This object is created by the engine and passed to results objects for use
+    in visualization and other client-side utilities. It is designed to be
+    serializable so it can be sent over the wire in a client-server architecture.
+
+    Attributes:
+        seed_column_names: Names of columns from the seed dataset. Empty list if no seed dataset.
+    """
+
+    seed_column_names: list[str] = []

data_designer/config/preview_results.py

@@ -7,6 +7,7 @@ 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.dataset_metadata import DatasetMetadata
 from data_designer.config.utils.visualization import WithRecordSamplerMixin
 
 
@@ -15,6 +16,7 @@ class PreviewResults(WithRecordSamplerMixin):
         self,
         *,
         config_builder: DataDesignerConfigBuilder,
+        dataset_metadata: DatasetMetadata,
         dataset: pd.DataFrame | None = None,
         analysis: DatasetProfilerResults | None = None,
         processor_artifacts: dict[str, list[str] | str] | None = None,
@@ -23,6 +25,7 @@ class PreviewResults(WithRecordSamplerMixin):
 
         Args:
             config_builder: Data Designer configuration builder.
+            dataset_metadata: Metadata about the generated dataset (e.g., seed column names).
             dataset: Dataset of the preview run.
             analysis: Analysis of the preview run.
             processor_artifacts: Artifacts generated by the processors.
@@ -30,4 +33,5 @@ class PreviewResults(WithRecordSamplerMixin):
         self.dataset: pd.DataFrame | None = dataset
         self.analysis: DatasetProfilerResults | None = analysis
         self.processor_artifacts: dict[str, list[str] | str] | None = processor_artifacts
+        self.dataset_metadata = dataset_metadata
         self._config_builder = config_builder

data_designer/config/run_config.py

@@ -14,21 +14,33 @@ class RunConfig(ConfigBase):
     part of the dataset configuration itself.
 
     Attributes:
-        disable_early_shutdown: If True, disables early shutdown entirely. Generation
-            will continue regardless of error rate. Default is False.
-        shutdown_error_rate: Error rate threshold (0.0-1.0) that triggers early shutdown.
-            When early shutdown is disabled, this value is normalized to 1.0. Default is 0.5.
+        disable_early_shutdown: If True, disables the executor's early-shutdown behavior entirely.
+            Generation will continue regardless of error rate, and the early-shutdown exception
+            will never be raised. Error counts and summaries are still collected. Default is False.
+        shutdown_error_rate: Error rate threshold (0.0-1.0) that triggers early shutdown when
+            early shutdown is enabled. Default is 0.5.
         shutdown_error_window: Minimum number of completed tasks before error rate
             monitoring begins. Must be >= 0. Default is 10.
+        buffer_size: Number of records to process in each batch during dataset generation.
+            A batch is processed end-to-end (column generation, post-batch processors, and writing the batch
+            to artifact storage) before moving on to the next batch. Must be > 0. Default is 1000.
+        max_conversation_restarts: Maximum number of full conversation restarts permitted when
+            generation tasks call `ModelFacade.generate(...)`. Must be >= 0. Default is 5.
+        max_conversation_correction_steps: Maximum number of correction rounds permitted within a
+            single conversation when generation tasks call `ModelFacade.generate(...)`. Must be >= 0.
+            Default is 0.
     """
 
     disable_early_shutdown: bool = False
     shutdown_error_rate: float = Field(default=0.5, ge=0.0, le=1.0)
     shutdown_error_window: int = Field(default=10, ge=0)
+    buffer_size: int = Field(default=1000, gt=0)
+    max_conversation_restarts: int = Field(default=5, ge=0)
+    max_conversation_correction_steps: int = Field(default=0, ge=0)
 
     @model_validator(mode="after")
     def normalize_shutdown_settings(self) -> Self:
-        """Set shutdown_error_rate to 1.0 when early shutdown is disabled."""
+        """Normalize shutdown settings for compatibility."""
         if self.disable_early_shutdown:
             self.shutdown_error_rate = 1.0
         return self

data_designer/config/seed_source.py

@@ -6,6 +6,7 @@ from typing import Literal
 
 import pandas as pd
 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 (
@@ -68,7 +69,7 @@ class DataFrameSeedSource(SeedSource):
 
     model_config = ConfigDict(arbitrary_types_allowed=True)
 
-    df: pd.DataFrame = Field(
+    df: SkipJsonSchema[pd.DataFrame] = Field(
         ...,
         exclude=True,
         description=(

data_designer/config/utils/visualization.py

@@ -31,6 +31,7 @@ from data_designer.config.utils.errors import DatasetSampleDisplayError
 
 if TYPE_CHECKING:
     from data_designer.config.config_builder import DataDesignerConfigBuilder
+    from data_designer.config.dataset_metadata import DatasetMetadata
 
 
 console = Console()
@@ -57,6 +58,7 @@ class ColorPalette(str, Enum):
 
 class WithRecordSamplerMixin:
     _display_cycle_index: int = 0
+    dataset_metadata: DatasetMetadata
 
     @cached_property
     def _record_sampler_dataset(self) -> pd.DataFrame:
@@ -79,22 +81,22 @@ class WithRecordSamplerMixin:
         self,
         index: int | None = None,
         *,
-        hide_seed_columns: bool = False,
         syntax_highlighting_theme: str = "dracula",
         background_color: str | None = None,
         processors_to_display: list[str] | None = None,
+        hide_seed_columns: bool = False,
     ) -> None:
         """Display a sample record from the Data Designer dataset preview.
 
         Args:
             index: Index of the record to display. If None, the next record will be displayed.
                 This is useful for running the cell in a notebook multiple times.
-            hide_seed_columns: If True, the columns from the seed dataset (if any) will not be displayed.
             syntax_highlighting_theme: Theme to use for syntax highlighting. See the `Syntax`
                 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.
+            hide_seed_columns: If True, seed columns will not be displayed separately.
         """
         i = index or self._display_cycle_index
 
@@ -120,14 +122,16 @@ class WithRecordSamplerMixin:
                     else:
                         processor_data_to_display[processor] = self.processor_artifacts[processor]
 
+        seed_column_names = None if hide_seed_columns else self.dataset_metadata.seed_column_names
+
         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,
-            hide_seed_columns=hide_seed_columns,
             record_index=i,
+            seed_column_names=seed_column_names,
         )
         if index is None:
             self._display_cycle_index = (self._display_cycle_index + 1) % num_records
@@ -160,7 +164,7 @@ def display_sample_record(
     background_color: str | None = None,
     syntax_highlighting_theme: str = "dracula",
     record_index: int | None = None,
-    hide_seed_columns: bool = False,
+    seed_column_names: list[str] | None = None,
 ):
     if isinstance(record, (dict, pd.Series)):
         record = pd.DataFrame([record]).iloc[0]
@@ -179,14 +183,14 @@ def display_sample_record(
     render_list = []
     table_kws = dict(show_lines=True, expand=True)
 
-    seed_columns = config_builder.get_columns_of_type(DataDesignerColumnType.SEED_DATASET)
-    if not hide_seed_columns and len(seed_columns) > 0:
+    # Display seed columns if seed_column_names is provided and not empty
+    if seed_column_names:
         table = Table(title="Seed Columns", **table_kws)
         table.add_column("Name")
         table.add_column("Value")
-        for col in seed_columns:
-            if not col.drop:
-                table.add_row(col.name, convert_to_row_element(record[col.name]))
+        for col_name in seed_column_names:
+            if col_name in record.index:
+                table.add_row(col_name, convert_to_row_element(record[col_name]))
         render_list.append(pad_console_element(table))
 
     non_code_columns = (

data_designer/engine/column_generators/generators/llm_completion.py

@@ -28,10 +28,6 @@ from data_designer.engine.processing.utils import deserialize_json_values
 logger = logging.getLogger(__name__)
 
 
-DEFAULT_MAX_CONVERSATION_RESTARTS = 5
-DEFAULT_MAX_CONVERSATION_CORRECTION_STEPS = 0
-
-
 class ColumnGeneratorWithModelChatCompletion(ColumnGeneratorWithModel[TaskConfigT]):
     @functools.cached_property
     def response_recipe(self) -> ResponseRecipe:
@@ -39,11 +35,11 @@ class ColumnGeneratorWithModelChatCompletion(ColumnGeneratorWithModel[TaskConfig
 
     @property
     def max_conversation_correction_steps(self) -> int:
-        return DEFAULT_MAX_CONVERSATION_CORRECTION_STEPS
+        return self.resource_provider.run_config.max_conversation_correction_steps
 
     @property
     def max_conversation_restarts(self) -> int:
-        return DEFAULT_MAX_CONVERSATION_RESTARTS
+        return self.resource_provider.run_config.max_conversation_restarts
 
     @functools.cached_property
     def prompt_renderer(self) -> RecordBasedPromptRenderer:
@@ -129,7 +125,3 @@ class LLMJudgeCellGenerator(ColumnGeneratorWithModelChatCompletion[LLMJudgeColum
             description="Judge a new dataset cell based on a set of rubrics",
             generation_strategy=GenerationStrategy.CELL_BY_CELL,
         )
-
-    @property
-    def max_conversation_restarts(self) -> int:
-        return 2 * DEFAULT_MAX_CONVERSATION_RESTARTS

data_designer/engine/column_generators/generators/validation.py

@@ -132,6 +132,7 @@ class ValidationColumnGenerator(ColumnGenerator[ValidationColumnConfig]):
             error_callback=error_callback,
             shutdown_error_rate=settings.shutdown_error_rate,
             shutdown_error_window=settings.shutdown_error_window,
+            disable_early_shutdown=settings.disable_early_shutdown,
         ) as executor:
             for i, batch in enumerate(batched_records):
                 executor.submit(lambda batch: self._validate_batch(validator, batch), batch, context={"index": i})

data_designer/engine/dataset_builders/column_wise_builder.py

@@ -94,7 +94,6 @@ class ColumnWiseDatasetBuilder:
         self,
         *,
         num_records: int,
-        buffer_size: int,
         on_batch_complete: Callable[[Path], None] | None = None,
     ) -> Path:
         self._write_configs()
@@ -104,6 +103,7 @@ class ColumnWiseDatasetBuilder:
         start_time = time.perf_counter()
         group_id = uuid.uuid4().hex
 
+        buffer_size = self._resource_provider.run_config.buffer_size
         self.batch_manager.start(num_records=num_records, buffer_size=buffer_size)
         for batch_idx in range(self.batch_manager.num_batches):
             logger.info(f"⏳ Processing batch {batch_idx + 1} of {self.batch_manager.num_batches}")
@@ -228,6 +228,7 @@ class ColumnWiseDatasetBuilder:
             error_callback=self._worker_error_callback,
             shutdown_error_rate=settings.shutdown_error_rate,
             shutdown_error_window=settings.shutdown_error_window,
+            disable_early_shutdown=settings.disable_early_shutdown,
         ) as executor:
             for i, record in self.batch_manager.iter_current_batch():
                 executor.submit(lambda record: generator.generate(record), record, context={"index": i})

data_designer/engine/dataset_builders/utils/concurrency.py

@@ -96,6 +96,7 @@ class ConcurrentThreadExecutor:
         error_callback: ErrorCallbackWithContext | None = None,
         shutdown_error_rate: float = 0.50,
         shutdown_error_window: int = 10,
+        disable_early_shutdown: bool = False,
     ):
         self._executor = None
         self._column_name = column_name
@@ -106,6 +107,7 @@ class ConcurrentThreadExecutor:
         self._error_callback = error_callback
         self._shutdown_error_rate = shutdown_error_rate
         self._shutdown_window_size = shutdown_error_window
+        self._disable_early_shutdown = disable_early_shutdown
         self._results = ExecutorResults(failure_threshold=shutdown_error_rate)
 
     @property
@@ -139,7 +141,7 @@ class ConcurrentThreadExecutor:
 
     def __exit__(self, exc_type, exc_value, traceback):
         self._shutdown_executor()
-        if self._results.early_shutdown is True:
+        if not self._disable_early_shutdown and self._results.early_shutdown is True:
             self._raise_task_error()
 
     def _shutdown_executor(self) -> None:
@@ -160,7 +162,7 @@ class ConcurrentThreadExecutor:
         if self._executor is None:
             raise RuntimeError("Executor is not initialized, this class should be used as a context manager.")
 
-        if self._results.early_shutdown:
+        if not self._disable_early_shutdown and self._results.early_shutdown:
             self._shutdown_executor()
             self._raise_task_error()
 
@@ -176,7 +178,9 @@ class ConcurrentThreadExecutor:
                 with self._lock:
                     self._results.completed_count += 1
                     self._results.error_trap.handle_error(err)
-                    if self._results.is_error_rate_exceeded(self._shutdown_window_size):
+                    if not self._disable_early_shutdown and self._results.is_error_rate_exceeded(
+                        self._shutdown_window_size
+                    ):
                         # Signal to shutdown early on the next submission (if received).
                         # We cannot trigger shutdown from within this thread as it can
                         # cause a deadlock.
@@ -196,7 +200,12 @@ class ConcurrentThreadExecutor:
             # We'll re-raise a custom error that can be handled at the call-site and the summary
             # can also be inspected.
             self._semaphore.release()
-            if not isinstance(err, RuntimeError) and "after shutdown" not in str(err):
+            is_shutdown_error = isinstance(err, RuntimeError) and (
+                "after shutdown" in str(err) or "Pool shutdown" in str(err)
+            )
+            if not is_shutdown_error:
+                raise err
+            if self._disable_early_shutdown:
                 raise err
             self._raise_task_error()
 

data_designer/engine/dataset_builders/utils/dataset_batch_manager.py

@@ -69,7 +69,7 @@ class DatasetBatchManager:
     def drop_records(self, index: Container[int]) -> None:
         self._buffer = [record for i, record in enumerate(self._buffer) if i not in index]
 
-    def finish_batch(self, on_complete: Callable[[Path], None] | None = None) -> Path:
+    def finish_batch(self, on_complete: Callable[[Path], None] | None = None) -> Path | None:
         """Finish the batch by moving the results from the partial results path to the final parquet folder.
 
         Returns:
@@ -78,29 +78,36 @@ class DatasetBatchManager:
         if self._current_batch_number >= self.num_batches:
             raise DatasetBatchManagementError("🛑 All batches have been processed.")
 
-        if not self.write():
-            raise DatasetBatchManagementError("🛑 Batch finished without any results to write.")
-
-        final_file_path = self.artifact_storage.move_partial_result_to_final_file_path(self._current_batch_number)
-
-        self.artifact_storage.write_metadata(
-            {
-                "target_num_records": sum(self.num_records_list),
-                "total_num_batches": self.num_batches,
-                "buffer_size": self._buffer_size,
-                "schema": {field.name: str(field.type) for field in pq.read_schema(final_file_path)},
-                "file_paths": [str(f) for f in sorted(self.artifact_storage.final_dataset_path.glob("*.parquet"))],
-                "num_records": self.num_records_list[: self._current_batch_number + 1],
-                "num_completed_batches": self._current_batch_number + 1,
-                "dataset_name": self.artifact_storage.dataset_name,
-            }
-        )
+        if self.write() is not None:
+            final_file_path = self.artifact_storage.move_partial_result_to_final_file_path(self._current_batch_number)
+
+            self.artifact_storage.write_metadata(
+                {
+                    "target_num_records": sum(self.num_records_list),
+                    "total_num_batches": self.num_batches,
+                    "buffer_size": self._buffer_size,
+                    "schema": {field.name: str(field.type) for field in pq.read_schema(final_file_path)},
+                    "file_paths": [str(f) for f in sorted(self.artifact_storage.final_dataset_path.glob("*.parquet"))],
+                    "num_records": self.num_records_list[: self._current_batch_number + 1],
+                    "num_completed_batches": self._current_batch_number + 1,
+                    "dataset_name": self.artifact_storage.dataset_name,
+                }
+            )
+
+            if on_complete:
+                on_complete(final_file_path)
+        else:
+            final_file_path = None
+
+            logger.warning(
+                f"⚠️ Batch {self._current_batch_number + 1} finished without any results to write. "
+                "A partial dataset containing the currently available columns has been written to the partial results "
+                f"directory: {self.artifact_storage.partial_results_path}"
+            )
+
         self._current_batch_number += 1
         self._buffer: list[dict] = []
 
-        if on_complete:
-            on_complete(final_file_path)
-
         return final_file_path
 
     def finish(self) -> None:

data_designer/engine/resources/resource_provider.py

@@ -2,6 +2,7 @@
 # SPDX-License-Identifier: Apache-2.0
 
 from data_designer.config.base import ConfigBase
+from data_designer.config.dataset_metadata import DatasetMetadata
 from data_designer.config.models import ModelConfig
 from data_designer.config.run_config import RunConfig
 from data_designer.config.seed_source import SeedSource
@@ -27,6 +28,17 @@ class ResourceProvider(ConfigBase):
     run_config: RunConfig = RunConfig()
     seed_reader: SeedReader | None = None
 
+    def get_dataset_metadata(self) -> DatasetMetadata:
+        """Get metadata about the dataset being generated.
+
+        Returns:
+            DatasetMetadata with seed column names and other metadata.
+        """
+        seed_column_names = []
+        if self.seed_reader is not None:
+            seed_column_names = self.seed_reader.get_column_names()
+        return DatasetMetadata(seed_column_names=seed_column_names)
+
 
 def create_resource_provider(
     *,

data_designer/interface/data_designer.py

@@ -56,15 +56,12 @@ from data_designer.engine.secret_resolver import (
 from data_designer.interface.errors import (
     DataDesignerGenerationError,
     DataDesignerProfilingError,
-    InvalidBufferValueError,
 )
 from data_designer.interface.results import DatasetCreationResults
 from data_designer.logging import RandomEmoji
 from data_designer.plugins.plugin import PluginType
 from data_designer.plugins.registry import PluginRegistry
 
-DEFAULT_BUFFER_SIZE = 1000
-
 DEFAULT_SECRET_RESOLVER = CompositeResolver([EnvironmentResolver(), PlaintextResolver()])
 
 DEFAULT_SEED_READERS = [
@@ -112,7 +109,6 @@ class DataDesigner(DataDesignerInterface[DatasetCreationResults]):
     ):
         self._secret_resolver = secret_resolver or DEFAULT_SECRET_RESOLVER
         self._artifact_path = Path(artifact_path) if artifact_path is not None else Path.cwd() / "artifacts"
-        self._buffer_size = DEFAULT_BUFFER_SIZE
         self._run_config = RunConfig()
         self._managed_assets_path = Path(managed_assets_path or MANAGED_ASSETS_PATH)
         self._model_providers = self._resolve_model_providers(model_providers)
@@ -169,7 +165,7 @@ class DataDesigner(DataDesignerInterface[DatasetCreationResults]):
         builder = self._create_dataset_builder(config_builder, resource_provider)
 
         try:
-            builder.build(num_records=num_records, buffer_size=self._buffer_size)
+            builder.build(num_records=num_records)
         except Exception as e:
             raise DataDesignerGenerationError(f"🛑 Error generating dataset: {e}")
 
@@ -182,10 +178,13 @@ class DataDesigner(DataDesignerInterface[DatasetCreationResults]):
         except Exception as e:
             raise DataDesignerProfilingError(f"🛑 Error profiling dataset: {e}")
 
+        dataset_metadata = resource_provider.get_dataset_metadata()
+
         return DatasetCreationResults(
             artifact_storage=builder.artifact_storage,
             analysis=analysis,
             config_builder=config_builder,
+            dataset_metadata=dataset_metadata,
         )
 
     def preview(
@@ -249,11 +248,15 @@ class DataDesigner(DataDesignerInterface[DatasetCreationResults]):
         ):
             logger.info(f"{RandomEmoji.success()} Preview complete!")
 
+        # Create dataset metadata from the resource provider
+        dataset_metadata = resource_provider.get_dataset_metadata()
+
         return PreviewResults(
             dataset=processed_dataset,
             analysis=analysis,
             processor_artifacts=processor_artifacts,
             config_builder=config_builder,
+            dataset_metadata=dataset_metadata,
         )
 
     def validate(self, config_builder: DataDesignerConfigBuilder) -> None:
@@ -300,34 +303,22 @@ class DataDesigner(DataDesignerInterface[DatasetCreationResults]):
         """
         return self._secret_resolver
 
-    def set_buffer_size(self, buffer_size: int) -> None:
-        """Set the buffer size for dataset generation.
-
-        The buffer size controls how many records are processed in memory at once
-        during dataset generation using the `create` method. The default value is
-        set to the constant `DEFAULT_BUFFER_SIZE` defined in the data_designer module.
-
-        Args:
-            buffer_size: Number of records to process in each buffer.
-
-        Raises:
-            InvalidBufferValueError: If buffer size is less than or equal to 0.
-        """
-        if buffer_size <= 0:
-            raise InvalidBufferValueError("Buffer size must be greater than 0.")
-        self._buffer_size = buffer_size
-
     def set_run_config(self, run_config: RunConfig) -> None:
         """Set the runtime configuration for dataset generation.
 
         Args:
             run_config: A RunConfig instance containing runtime settings such as
-                early shutdown behavior. Import RunConfig from data_designer.essentials.
+                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))
+
+        Notes:
+            When `disable_early_shutdown=True`, DataDesigner will never terminate generation early
+            due to error-rate thresholds. Errors are still tracked for reporting.
         """
         self._run_config = run_config
 

data_designer/interface/results.py

@@ -9,6 +9,7 @@ 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.dataset_metadata import DatasetMetadata
 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
@@ -28,6 +29,7 @@ class DatasetCreationResults(WithRecordSamplerMixin):
         artifact_storage: ArtifactStorage,
         analysis: DatasetProfilerResults,
         config_builder: DataDesignerConfigBuilder,
+        dataset_metadata: DatasetMetadata,
     ):
         """Creates a new instance with results based on a dataset creation run.
 
@@ -35,10 +37,12 @@ class DatasetCreationResults(WithRecordSamplerMixin):
             artifact_storage: Storage manager for accessing generated artifacts.
             analysis: Profiling results for the generated dataset.
             config_builder: Configuration builder used to create the dataset.
+            dataset_metadata: Metadata about the generated dataset (e.g., seed column names).
         """
         self.artifact_storage = artifact_storage
         self._analysis = analysis
         self._config_builder = config_builder
+        self.dataset_metadata = dataset_metadata
 
     def load_analysis(self) -> DatasetProfilerResults:
         """Load the profiling analysis results for the generated dataset.

{data_designer-0.3.3.dist-info → data_designer-0.3.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-designer
-Version: 0.3.3
+Version: 0.3.4
 Summary: General framework for synthetic data generation
 License-Expression: Apache-2.0
 License-File: LICENSE
@@ -193,6 +193,14 @@ The value `openai/gpt-oss-20b` would be collected.
 
 To disable telemetry capture, set `NEMO_TELEMETRY_ENABLED=false`.
 
+### Top Models
+
+This chart represents the breakdown of models used for Data Designer across all synthetic data generation jobs from 12/18/2025 to 1/14/2026. 
+
+![Top models used for synthetic data generation](docs/images/top-models.png)
+
+_Last updated on 1/14/2026_
+
 ---
 
 ## License

{data_designer-0.3.3.dist-info → data_designer-0.3.4.dist-info}/RECORD

@@ -1,5 +1,5 @@
 data_designer/__init__.py,sha256=xYZCBRleSswcNCARfHQzFy_Edag3Nmmwfa6A5C1d5B8,466
-data_designer/_version.py,sha256=lemL_4Kl75FgrO6lVuFrrtw6-Dcf9wtXBalKkXuzkO4,704
+data_designer/_version.py,sha256=3nDaC5e0d_scBB1bUEKPlItbvbY0PmXNNyyOTNFNWNI,704
 data_designer/errors.py,sha256=BjnxDxwtTGscY3lZbi1RQ666j5PseoxNJRobeMXAJiI,184
 data_designer/logging.py,sha256=2ToJzPPb6zF-QR-yQnrLVcBiBGL_QVNsnCHSQC0nPpQ,5346
 data_designer/plugin_manager.py,sha256=C2ZkZiXlcMRiaxfrrho5Shz6DKdExVeBha7ch-d4CnU,2695
@@ -34,24 +34,25 @@ data_designer/cli/services/download_service.py,sha256=9ocQdHZW6VYHqM3nyHn_7dP1z1
 data_designer/cli/services/model_service.py,sha256=rcsozdIRXMElskUHtmWGj6pZbVFf2JzHHv8rTnXv8xw,3890
 data_designer/cli/services/provider_service.py,sha256=ru0-AJVZLr8wk5kOV2z2FgPpF-iK8vWQs0qtrMKp-dg,3921
 data_designer/config/__init__.py,sha256=XLO09Ei8g0lU7hYlzKCvhvQhLFBe5CBwE4v2PqK9xWY,142
-data_designer/config/base.py,sha256=DtsUGIwTny57ASN3ffIfvhjrWt1PGhGuRDoqRmRx8Qo,2401
+data_designer/config/base.py,sha256=IGj6sy_GnKzC94uu2rdxe12EqR_AmGJ6O3rl2MxOv6g,2449
 data_designer/config/column_configs.py,sha256=Z3V8BKMkgse91MGlEcyJBa-lV25_j81SZ-vZNOoUKXc,18966
 data_designer/config/column_types.py,sha256=qsy04QslsnPEOoStN3sJIoSBeSSTxpNg5VLVmew_YLQ,5753
 data_designer/config/config_builder.py,sha256=vuPibkodbJxbCXdaI1tt1Uyo1SVCnAOfLBAW1AmhajI,24707
 data_designer/config/data_designer_config.py,sha256=qOojviug05vHR2S4800sjd4OmxhSVi6kB8SAFXLlPog,1891
 data_designer/config/dataset_builders.py,sha256=4NSEEqXzgSK8IDXoUSVRSUTcEe-ocKS-iEzyzKkNSJ0,332
+data_designer/config/dataset_metadata.py,sha256=UTlEgnHWgjwPuc7bP95T7gaKmcr7pIhFMy9vvbUwMV4,647
 data_designer/config/default_model_settings.py,sha256=3iUr10JvSTMDHwlEdSbLE_y90czbGOs_21La3V9fXoM,4462
 data_designer/config/errors.py,sha256=g64yn9l7lTbcXI3DPdC_3utvm994IXGDhoQRiNON6T0,524
 data_designer/config/exports.py,sha256=y23KqhwAf4DIarfvqgiuqyK2Fs1zv9cTDcuQ9SBX54o,4720
 data_designer/config/interface.py,sha256=RRC5JHl6wQ9Icg1IQWOM6t8VkBk6c1BREkka3cEAi8c,1624
 data_designer/config/models.py,sha256=A8D0qj6L9ndYvScvNWGuoOLe0zjYtoAm0JkwaG3qjRg,15335
-data_designer/config/preview_results.py,sha256=fhmxRLbSifdMO_pLrvmGaDJHtNIupX8X3HvXhjHr3hM,1350
+data_designer/config/preview_results.py,sha256=y-zEnRxZt_72XuAFs_e_peK4bVJ_fDSi9b-jLxsQ-S0,1602
 data_designer/config/processors.py,sha256=CoLUN1AuEBUPigmDT8vCWotvOcFgnC8CFk8VLvNSjxw,5992
-data_designer/config/run_config.py,sha256=M6m3oc3e1CTgStfkkgHyIt78JYrrMKdGSJUR07elmp0,1418
+data_designer/config/run_config.py,sha256=yakCcWyT78kLXGZnFVK35pdrkPpWT7AVEp_sHyq67fg,2393
 data_designer/config/sampler_constraints.py,sha256=XBPxm81J0u2q3WVsRaP2CoIE_0ssY14xc4Nt5r0oyuM,1161
 data_designer/config/sampler_params.py,sha256=FSMvmdj-9Hiyap1_n-AM_ZDT-sTovox7LK4TO4L2UUc,27843
 data_designer/config/seed.py,sha256=iUFByadE6GTG9HCcp0nEWm7wTDNaAOuYtGm2Ov0tiaE,4632
-data_designer/config/seed_source.py,sha256=zOnLAOyJ_nfFA5sI6DNzDf5IGWiYEjDgHYOzo_5O5Zw,2449
+data_designer/config/seed_source.py,sha256=GYgK9f0_a0FuOtvXlrLEw0MmAELucTB1Qrc_sGGoziw,2513
 data_designer/config/seed_source_types.py,sha256=4EJ4IsYkfkicYqh0CuEvyI3H541XbtV_ffClJV2-zCQ,679
 data_designer/config/validator_params.py,sha256=9w9M7Z1rcZOpw-BUBhjaVfA8ykNP5iPvdyJOHmdugEg,3911
 data_designer/config/analysis/__init__.py,sha256=XLO09Ei8g0lU7hYlzKCvhvQhLFBe5CBwE4v2PqK9xWY,142
@@ -68,7 +69,7 @@ data_designer/config/utils/io_helpers.py,sha256=_14cfoMUIFqiUPBTu5u-BomarqmP6_VB
 data_designer/config/utils/misc.py,sha256=cRofbhUulLKjV7j_7M5aNNNyIewyyhXLkj00GaZf9uo,2472
 data_designer/config/utils/numerical_helpers.py,sha256=BadOPY1AR2ZVKFAKORpKT_Corc1SZR7W1of6FXYIMY4,802
 data_designer/config/utils/type_helpers.py,sha256=2WSGYWTDktOCa9FGNv2IPXIHQHJc7-fimAB1JqIJVx0,4023
-data_designer/config/utils/visualization.py,sha256=TbYgHAvxXEmJZH-QZYyOkf28E52rW80ZirpJT2PMeK8,18191
+data_designer/config/utils/visualization.py,sha256=2ZloKN1UimKvIXyKJBSHZ56-JItE5MzMXY31J9x4hbY,18366
 data_designer/engine/__init__.py,sha256=XLO09Ei8g0lU7hYlzKCvhvQhLFBe5CBwE4v2PqK9xWY,142
 data_designer/engine/compiler.py,sha256=tzZF5rk_AAid0yRwwsR86-xvW-5GdJskN1RPfvuFq-k,2853
 data_designer/engine/configurable_task.py,sha256=hdXyfekQ9dHSc_NQG6nZIxKCqWSWKnqA5nje7Uobf6k,2525
@@ -90,23 +91,23 @@ data_designer/engine/column_generators/generators/__init__.py,sha256=XLO09Ei8g0l
 data_designer/engine/column_generators/generators/base.py,sha256=T3ccXIyKXwYN4Kes6HcTBdELK-wOs9cFCoaTH3C3dyQ,3814
 data_designer/engine/column_generators/generators/embedding.py,sha256=pdRMzb95CKmBpOiTQrAEiKngBFvAlt5g8HwI8EwWBIY,1565
 data_designer/engine/column_generators/generators/expression.py,sha256=irBDhTsFyZaWU2EIqy5xOKRBxX-x8W8q5pQ69P7NKTs,2543
-data_designer/engine/column_generators/generators/llm_completion.py,sha256=Dp4F1wxZAMwUglRqQHE5lPXDNyPALKWsMr1IJRIvbJI,5031
+data_designer/engine/column_generators/generators/llm_completion.py,sha256=fwL6Xbfg8d9SnZgv2-j3g_6S38xzuwnVY4R4UabvdIw,4881
 data_designer/engine/column_generators/generators/samplers.py,sha256=0bvJhVK2LfH9aRY1BxqWCjA7LJxy1B63gGmZuWK8auU,3486
 data_designer/engine/column_generators/generators/seed_dataset.py,sha256=IskfOQkRMRTfu8tiYb426LMchBYKNQs0uSo9E5y0bwg,6905
-data_designer/engine/column_generators/generators/validation.py,sha256=hDqE_xZfJ2XGVE89ifDUvsbtZfzQmiNGRBTY733dXgY,6776
+data_designer/engine/column_generators/generators/validation.py,sha256=0gw0Wzq4yVqejWewt2uznQ4UJI7_0MMEdvMenH-KwYc,6844
 data_designer/engine/column_generators/utils/errors.py,sha256=Nemo7fxg9BpTOf0kdlxxdtXZMfe_ksrRfzWg2E5sFX0,370
 data_designer/engine/column_generators/utils/generator_classification.py,sha256=1fvMX7lQzY3A1s-V3CtS-W6-zwmby553_Oe9K-tdZKE,1922
 data_designer/engine/column_generators/utils/judge_score_factory.py,sha256=8l0g-L_O6esmAEf1rJh7o2IASZnLqZ_KDlGaLCMYMK0,2105
 data_designer/engine/column_generators/utils/prompt_renderer.py,sha256=xXnzJiR60zTmMDorR_wfTleNMJsLKA5gbL4WOjQ-wYg,4765
 data_designer/engine/dataset_builders/artifact_storage.py,sha256=fYBC569tXVpn7UURcuXfHPhEvvwOHnMxAkA1iQAB-j4,8425
-data_designer/engine/dataset_builders/column_wise_builder.py,sha256=y068Eza-MabPviEStsFt14Kl4p8b9o1Exe4-kje4vEs,15197
+data_designer/engine/dataset_builders/column_wise_builder.py,sha256=DUAMEmy7xCSFDYy-WU-ZXflKzy5oJ6yqMESQSb7CoUc,15308
 data_designer/engine/dataset_builders/errors.py,sha256=ov9cTRvLtLieIFkUGZdk1n_iabdc904ZATwgT5u9uzY,364
 data_designer/engine/dataset_builders/multi_column_configs.py,sha256=bxRildX3SfzSFKv_rqwwsUeFn_RoyhfFneSj4qBi-Q4,1624
 data_designer/engine/dataset_builders/utils/__init__.py,sha256=XLO09Ei8g0lU7hYlzKCvhvQhLFBe5CBwE4v2PqK9xWY,142
-data_designer/engine/dataset_builders/utils/concurrency.py,sha256=SQlT9Tu3UgATllm_fwle4kkro09NQBVU_nLSZj7lBDQ,7893
+data_designer/engine/dataset_builders/utils/concurrency.py,sha256=Q0ro9UY-3-FFzfi3MZ29nMTSiDZgg1Um6y_HQFztDhk,8338
 data_designer/engine/dataset_builders/utils/config_compiler.py,sha256=iAbaLiDNBPyjZwSVK1a83KFKln9LACjKdVSpIiZRemw,2405
 data_designer/engine/dataset_builders/utils/dag.py,sha256=L3-sla2s8oqcy3V-WSxXAWZVakkmb3cvmTh5L6phC1M,2474
-data_designer/engine/dataset_builders/utils/dataset_batch_manager.py,sha256=c-6ER96oP-0oZ6CncN8sjXy1S1ZjzTreeYBr1oOX8Yg,7774
+data_designer/engine/dataset_builders/utils/dataset_batch_manager.py,sha256=DpEW_zrHv7CPiVFw07r_0Q9V6dFaTqOFJ1uWnuicxHo,8142
 data_designer/engine/dataset_builders/utils/errors.py,sha256=6hstnyjYZ8pU69qK3OrUvlyeifqRJC2m399GNVcih3I,375
 data_designer/engine/models/__init__.py,sha256=XLO09Ei8g0lU7hYlzKCvhvQhLFBe5CBwE4v2PqK9xWY,142
 data_designer/engine/models/errors.py,sha256=HjPF3ERKU7veS7s189_0VBBMpePl6pSmOqaYhOO8xv4,12179
@@ -145,7 +146,7 @@ data_designer/engine/registry/errors.py,sha256=PNWsfU2baNmzshcHah1-P7YT9OqxfxYf1
 data_designer/engine/resources/managed_dataset_generator.py,sha256=mJAR-dc0vEfiw3xN7ABIOalxGIbQmfZ7P23U-vUut40,1374
 data_designer/engine/resources/managed_dataset_repository.py,sha256=zxxP9SDdu0PrP28ozJmIwdlbHHuGkcPRmb1Ua5VOsG0,7552
 data_designer/engine/resources/managed_storage.py,sha256=nTfp14o-BbtDP6XUxD3564g0cXB6B1og-1rZI9dx1H0,2084
-data_designer/engine/resources/resource_provider.py,sha256=9IwJ5qQPvoQwXe_wIkp0enNpgKRRu691BQfxsnZic5w,2323
+data_designer/engine/resources/resource_provider.py,sha256=pMh0_j8JCZ54x4zCPtPIb9s5AGwSBswQsYFddxsgM_U,2813
 data_designer/engine/resources/seed_reader.py,sha256=Gh524gMWh6Lz43bielQG3nmMz5MrZy1BTGs792AhMpc,5591
 data_designer/engine/sampling_gen/column.py,sha256=lqdMrUebIFJ_C_Laye0TuIkEd_fVVPP5b-zoNGez25Q,3951
 data_designer/engine/sampling_gen/constraints.py,sha256=HtLxW_VYXlo_A8IMlZkgTb1fBwyrRHuB3LZnF3AgV-I,3009
@@ -176,9 +177,9 @@ data_designer/engine/validators/remote.py,sha256=Qviad8vF7SBtHRvNqKxZyiLJuGJp0rm
 data_designer/engine/validators/sql.py,sha256=Y2FkM_JmcWzW98qjZruq73vt8RgjkLXuTbyLPGrA2l8,2255
 data_designer/essentials/__init__.py,sha256=wt84P4qu1-OdIfrZmdOtRtiBoGcVSdTEdkIiUaztPWs,1099
 data_designer/interface/__init__.py,sha256=XLO09Ei8g0lU7hYlzKCvhvQhLFBe5CBwE4v2PqK9xWY,142
-data_designer/interface/data_designer.py,sha256=AJ-1ntSeAkDcmuyI0-erq8xrxdu6C5m47h0k8p2IxFQ,17409
+data_designer/interface/data_designer.py,sha256=OpjWdfjwhp1wzeArdicpCzmaaVCZydSGarQDpvh3egU,17105
 data_designer/interface/errors.py,sha256=CoH-6V95RDNHNONxKs8MWina-cD6NtaerMW_cyH8WRU,570
-data_designer/interface/results.py,sha256=x6bzKaG9ZaDU_UmImNgjULn131jTektMzWX5B3VZXpE,3516
+data_designer/interface/results.py,sha256=aiRWSK2QVAKTGboqn_Fods7dc5lbG5cmDs6O_INbH-0,3768
 data_designer/plugins/__init__.py,sha256=GmeQ6bzFMNkLthrmLKQ5bcUMPw_W2K4d6oWKvYA8eNw,239
 data_designer/plugins/errors.py,sha256=EzKPo0rEiTe872sIAvF0_cDjFfl_P2MyDtESZL1P3ug,350
 data_designer/plugins/plugin.py,sha256=TmdllvWXOKZZNwJTW_rUMD1M68pAh_IEIILZei7fHqU,5468
@@ -186,8 +187,8 @@ data_designer/plugins/registry.py,sha256=1vNlmDyFMCIY8D_z1RbnWMfKnHZ02g8sAvJg1nE
 data_designer/plugins/testing/__init__.py,sha256=lSuWzt1AVTJg4gV9wh6BUU1Az7IjQ-9FgADdUAtm_qQ,260
 data_designer/plugins/testing/stubs.py,sha256=E8bovwU4zpNaJM4b1i4biCDXyqvthe8vmsrZ9M0M9vM,4277
 data_designer/plugins/testing/utils.py,sha256=OLoQzW8-qbA-91wTUWtwNHrMDyGz1-ma0f6a-3NBUNI,937
-data_designer-0.3.3.dist-info/METADATA,sha256=zJ5wtn9YBRb9qEXBHT3_93rZxo7RT5P6JhSsAdILimQ,7648
-data_designer-0.3.3.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-data_designer-0.3.3.dist-info/entry_points.txt,sha256=NWWWidyDxN6CYX6y664PhBYMhbaYTQTyprqfYAgkyCg,57
-data_designer-0.3.3.dist-info/licenses/LICENSE,sha256=cSWJDwVqHyQgly8Zmt3pqXJ2eQbZVYwN9qd0NMssxXY,11336
-data_designer-0.3.3.dist-info/RECORD,,
+data_designer-0.3.4.dist-info/METADATA,sha256=10B6euF52J8L-MFg1_I_3lRQ3rK3Q5x_2V0iZ_vTtBQ,7914
+data_designer-0.3.4.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+data_designer-0.3.4.dist-info/entry_points.txt,sha256=NWWWidyDxN6CYX6y664PhBYMhbaYTQTyprqfYAgkyCg,57
+data_designer-0.3.4.dist-info/licenses/LICENSE,sha256=cSWJDwVqHyQgly8Zmt3pqXJ2eQbZVYwN9qd0NMssxXY,11336
+data_designer-0.3.4.dist-info/RECORD,,