data-designer 0.3.6__py3-none-any.whl → 0.3.8__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 = '0.3.6'
-__version_tuple__ = version_tuple = (0, 3, 6)
+__version__ = version = '0.3.8'
+__version_tuple__ = version_tuple = (0, 3, 8)
 
 __commit_id__ = commit_id = None

data_designer/config/default_model_settings.py

@@ -71,12 +71,20 @@ def get_default_model_configs() -> list[ModelConfig]:
     return []
 
 
-def get_default_model_providers_missing_api_keys() -> list[str]:
-    missing_api_keys = []
-    for predefined_provider in PREDEFINED_PROVIDERS:
-        if os.environ.get(predefined_provider["api_key"]) is None:
-            missing_api_keys.append(predefined_provider["api_key"])
-    return missing_api_keys
+def get_providers_with_missing_api_keys(providers: list[ModelProvider]) -> list[ModelProvider]:
+    providers_with_missing_keys = []
+
+    for provider in providers:
+        if provider.api_key is None:
+            # No API key specified at all
+            providers_with_missing_keys.append(provider)
+        elif provider.api_key.isupper() and "_" in provider.api_key:
+            # Looks like an environment variable name, check if it's set
+            if os.environ.get(provider.api_key) is None:
+                providers_with_missing_keys.append(provider)
+        # else: It's an actual API key value (not an env var), so it's valid
+
+    return providers_with_missing_keys
 
 
 def get_default_providers() -> list[ModelProvider]:

data_designer/config/run_config.py

@@ -26,6 +26,8 @@ class RunConfig(ConfigBase):
         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.
+        non_inference_max_parallel_workers: Maximum number of worker threads used for non-inference
+            cell-by-cell generators. Must be >= 1. Default is 4.
         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
@@ -37,6 +39,7 @@ class RunConfig(ConfigBase):
     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)
+    non_inference_max_parallel_workers: int = Field(default=4, ge=1)
     max_conversation_restarts: int = Field(default=5, ge=0)
     max_conversation_correction_steps: int = Field(default=0, ge=0)
 

data_designer/config/utils/constants.py

@@ -353,9 +353,11 @@ PREDEFINED_PROVIDERS_MODEL_MAP = {
 NEMOTRON_PERSONAS_DATASET_SIZES = {
     "en_US": "1.24 GB",
     "en_IN": "2.39 GB",
+    "en_SG": "0.30 GB",
     "hi_Deva_IN": "4.14 GB",
     "hi_Latn_IN": "2.7 GB",
     "ja_JP": "1.69 GB",
+    "pt_BR": "2.33 GB",
 }
 
 LOCALES_WITH_MANAGED_DATASETS = list[str](NEMOTRON_PERSONAS_DATASET_SIZES.keys())

data_designer/engine/column_generators/generators/llm_completion.py

@@ -55,6 +55,9 @@ class ColumnGeneratorWithModelChatCompletion(ColumnGeneratorWithModel[TaskConfig
         )
 
     def generate(self, data: dict) -> dict:
+        # Deserialize input data from previous columns so Jinja2 templates can access nested fields
+        # Example: If prev column stored '{"key": "value"}', templates can use {{ prev_column.key }}
+        # Note: This creates a new dict and doesn't mutate the original `data` argument
         deserialized_record = deserialize_json_values(data)
 
         multi_modal_context = None
@@ -81,13 +84,18 @@ class ColumnGeneratorWithModelChatCompletion(ColumnGeneratorWithModel[TaskConfig
             purpose=f"running generation for column '{self.config.name}'",
         )
 
-        data[self.config.name] = deserialize_json_values(self.response_recipe.serialize_output(response))
+        serialized_output = self.response_recipe.serialize_output(response)
+        data[self.config.name] = self._process_serialized_output(serialized_output)
 
         if reasoning_trace:
             data[self.config.name + REASONING_TRACE_COLUMN_POSTFIX] = reasoning_trace
 
         return data
 
+    def _process_serialized_output(self, serialized_output: str) -> str | dict | list:
+        """Process the serialized output from the model. Subclasses can override to customize deserialization."""
+        return serialized_output
+
 
 class LLMTextCellGenerator(ColumnGeneratorWithModelChatCompletion[LLMTextColumnConfig]): ...
 
@@ -95,7 +103,11 @@ class LLMTextCellGenerator(ColumnGeneratorWithModelChatCompletion[LLMTextColumnC
 class LLMCodeCellGenerator(ColumnGeneratorWithModelChatCompletion[LLMCodeColumnConfig]): ...
 
 
-class LLMStructuredCellGenerator(ColumnGeneratorWithModelChatCompletion[LLMStructuredColumnConfig]): ...
+class LLMStructuredCellGenerator(ColumnGeneratorWithModelChatCompletion[LLMStructuredColumnConfig]):
+    def _process_serialized_output(self, serialized_output: str) -> dict | list:
+        return deserialize_json_values(serialized_output)
 
 
-class LLMJudgeCellGenerator(ColumnGeneratorWithModelChatCompletion[LLMJudgeColumnConfig]): ...
+class LLMJudgeCellGenerator(ColumnGeneratorWithModelChatCompletion[LLMJudgeColumnConfig]):
+    def _process_serialized_output(self, serialized_output: str) -> dict | list:
+        return deserialize_json_values(serialized_output)

data_designer/engine/compiler.py

@@ -5,9 +5,10 @@ from __future__ import annotations
 
 import logging
 
-from data_designer.config.column_configs import SeedDatasetColumnConfig
+from data_designer.config.column_configs import SamplerColumnConfig, SeedDatasetColumnConfig
 from data_designer.config.data_designer_config import DataDesignerConfig
 from data_designer.config.errors import InvalidConfigError
+from data_designer.config.sampler_params import UUIDSamplerParams
 from data_designer.engine.resources.resource_provider import ResourceProvider
 from data_designer.engine.resources.seed_reader import SeedReader
 from data_designer.engine.validation import ViolationLevel, rich_print_violations, validate_data_designer_config
@@ -17,6 +18,7 @@ logger = logging.getLogger(__name__)
 
 def compile_data_designer_config(config: DataDesignerConfig, resource_provider: ResourceProvider) -> DataDesignerConfig:
     _resolve_and_add_seed_columns(config, resource_provider.seed_reader)
+    _add_internal_row_id_column_if_needed(config)
     _validate(config)
     return config
 
@@ -41,6 +43,35 @@ def _resolve_and_add_seed_columns(config: DataDesignerConfig, seed_reader: SeedR
     config.columns.extend([SeedDatasetColumnConfig(name=col_name) for col_name in seed_col_names])
 
 
+def _add_internal_row_id_column_if_needed(config: DataDesignerConfig) -> None:
+    """Adds a UUID sampler column named '_internal_row_id' (set to drop) if needed to enable generation.
+
+    Generation requires either:
+    - At least one sampler column (which can generate data from scratch), OR
+    - A seed dataset (which provides initial data rows)
+
+    If neither exists, a UUID sampler column '_internal_row_id' is automatically added and marked for drop
+    to enable the generation process to start.
+
+    Args:
+        config: The DataDesigner configuration to potentially modify.
+    """
+    has_sampler_column = any(isinstance(col, SamplerColumnConfig) for col in config.columns)
+    has_seed_dataset_column = any(isinstance(col, SeedDatasetColumnConfig) for col in config.columns)
+
+    if not has_sampler_column and not has_seed_dataset_column:
+        logger.warning(
+            "🔔 No sampler column or seed dataset detected. Adding UUID column '_internal_row_id' (marked for drop) to enable generation."
+        )
+        id_column = SamplerColumnConfig(
+            name="_internal_row_id",
+            sampler_type="uuid",
+            params=UUIDSamplerParams(),
+            drop=True,
+        )
+        config.columns.insert(0, id_column)
+
+
 def _validate(config: DataDesignerConfig) -> None:
     allowed_references = _get_allowed_references(config)
     violations = validate_data_designer_config(

data_designer/engine/dataset_builders/column_wise_builder.py

@@ -31,10 +31,7 @@ from data_designer.engine.compiler import compile_data_designer_config
 from data_designer.engine.dataset_builders.artifact_storage import SDG_CONFIG_FILENAME, ArtifactStorage
 from data_designer.engine.dataset_builders.errors import DatasetGenerationError, DatasetProcessingError
 from data_designer.engine.dataset_builders.multi_column_configs import MultiColumnConfig
-from data_designer.engine.dataset_builders.utils.concurrency import (
-    MAX_CONCURRENCY_PER_NON_LLM_GENERATOR,
-    ConcurrentThreadExecutor,
-)
+from data_designer.engine.dataset_builders.utils.concurrency import ConcurrentThreadExecutor
 from data_designer.engine.dataset_builders.utils.config_compiler import compile_dataset_builder_column_configs
 from data_designer.engine.dataset_builders.utils.dataset_batch_manager import DatasetBatchManager
 from data_designer.engine.models.telemetry import InferenceEvent, NemoSourceEnum, TaskStatusEnum, TelemetryHandler
@@ -202,7 +199,7 @@ class ColumnWiseDatasetBuilder:
         self.batch_manager.add_records(df.to_dict(orient="records"))
 
     def _run_cell_by_cell_generator(self, generator: ColumnGenerator) -> None:
-        max_workers = MAX_CONCURRENCY_PER_NON_LLM_GENERATOR
+        max_workers = self._resource_provider.run_config.non_inference_max_parallel_workers
         if isinstance(generator, ColumnGeneratorWithModel):
             max_workers = generator.inference_parameters.max_parallel_requests
         self._fan_out_with_threads(generator, max_workers=max_workers)

data_designer/engine/dataset_builders/utils/concurrency.py

@@ -16,9 +16,6 @@ from data_designer.engine.errors import DataDesignerRuntimeError, ErrorTrap
 
 logger = logging.getLogger(__name__)
 
-# Constants
-MAX_CONCURRENCY_PER_NON_LLM_GENERATOR = 4
-
 
 class ExecutorResults(BaseModel):
     failure_threshold: float = 0.0  # Error rate threshold

data_designer/engine/models/litellm_overrides.py

@@ -1,36 +1,42 @@
 # SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 
+
+"""
+LiteLLM overrides and customizations.
+
+Note on imports: This module uses direct (eager) imports for litellm rather than lazy loading.
+This is intentional because:
+
+1. Class inheritance requires base classes to be resolved at class definition time,
+   making lazy imports incompatible with our ThreadSafeCache and CustomRouter classes.
+
+2. This module is already lazily loaded at the application level - it's only imported
+   by facade.py, which itself is imported inside the create_model_registry() factory
+   function. So litellm is only loaded when models are actually needed.
+
+3. Attempting to use lazy imports here causes intermittent ImportErrors.
+"""
+
 from __future__ import annotations
 
 import random
 import threading
-from typing import TYPE_CHECKING
 
-# Import specific litellm submodules needed for class inheritance
-# Note: Class inheritance requires base classes at definition time, so we import these directly.
-# Runtime litellm usage below still benefits from lazy loading via the litellm alias.
-import litellm.caching.in_memory_cache as _litellm_cache
-import litellm.router as _litellm_router
+import httpx
+import litellm
+from litellm import RetryPolicy
+from litellm.caching.in_memory_cache import InMemoryCache
+from litellm.litellm_core_utils.logging_callback_manager import LoggingCallbackManager
+from litellm.router import Router
 from pydantic import BaseModel, Field
 from typing_extensions import override
 
-# Use lazy loading for runtime litellm usage (RetryPolicy, utils, etc.)
-from data_designer.lazy_heavy_imports import httpx, litellm
 from data_designer.logging import quiet_noisy_logger
 
-if TYPE_CHECKING:
-    import httpx
-    import litellm
-
 DEFAULT_MAX_CALLBACKS = 1000
 
 
-def _get_logging_callback_manager():
-    """Lazy accessor for LoggingCallbackManager to avoid loading litellm at import time."""
-    return litellm.litellm_core_utils.logging_callback_manager.LoggingCallbackManager
-
-
 class LiteLLMRouterDefaultKwargs(BaseModel):
     ## Number of seconds to wait initially after a connection
     ## failure.
@@ -46,15 +52,15 @@ class LiteLLMRouterDefaultKwargs(BaseModel):
 
     ## Sets the default retry policy, including the number
     ## of retries to use in particular scenarios.
-    retry_policy: litellm.RetryPolicy = Field(
-        default_factory=lambda: litellm.RetryPolicy(
+    retry_policy: RetryPolicy = Field(
+        default_factory=lambda: RetryPolicy(
             RateLimitErrorRetries=3,
             TimeoutErrorRetries=3,
         )
     )
 
 
-class ThreadSafeCache(_litellm_cache.InMemoryCache):
+class ThreadSafeCache(InMemoryCache):
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
 
@@ -89,7 +95,7 @@ class ThreadSafeCache(_litellm_cache.InMemoryCache):
             super().flush_cache()
 
 
-class CustomRouter(_litellm_router.Router):
+class CustomRouter(Router):
     def __init__(
         self,
         *args,
@@ -166,7 +172,7 @@ def apply_litellm_patches():
     litellm.in_memory_llm_clients_cache = ThreadSafeCache()
 
     # Workaround for the litellm issue described in https://github.com/BerriAI/litellm/issues/9792
-    _get_logging_callback_manager().MAX_CALLBACKS = DEFAULT_MAX_CALLBACKS
+    LoggingCallbackManager.MAX_CALLBACKS = DEFAULT_MAX_CALLBACKS
 
     quiet_noisy_logger("httpx")
     quiet_noisy_logger("LiteLLM")

data_designer/engine/processing/utils.py

@@ -4,6 +4,7 @@
 from __future__ import annotations
 
 import ast
+import copy
 import json
 import logging
 import re
@@ -50,6 +51,8 @@ def deserialize_json_values(data: T) -> T: ...
 def deserialize_json_values(data):
     """De-serialize JSON strings in various input formats.
 
+    This function creates a deep copy of the input data and does not mutate the original.
+
     Args:
         data: Input data in one of four formats:
             - Single string (JSON string to deserialize)
@@ -63,18 +66,22 @@ def deserialize_json_values(data):
             - List of dictionaries (when input is a list of strings)
             - Dictionary (when input is a dictionary, with nested JSON strings deserialized)
             - The original object (if there is no deserialization to perform)
+
     """
+    # Create a deep copy to avoid mutating the original data
+    data_copy = copy.deepcopy(data)
+
     # Case 1: Single string input
-    if isinstance(data, str):
+    if isinstance(data_copy, str):
         try:
-            return json.loads(data)
+            return json.loads(data_copy)
         except json.JSONDecodeError:
-            return data
+            return data_copy
 
     # Case 2: List of strings input
-    elif isinstance(data, list):
+    elif isinstance(data_copy, list):
         result = []
-        for item in data:
+        for item in data_copy:
             if isinstance(item, str):
                 try:
                     result.append(json.loads(item))
@@ -86,9 +93,9 @@ def deserialize_json_values(data):
         return result
 
     # Case 3: Dictionary input with potential nested JSON strings
-    elif isinstance(data, dict):
+    elif isinstance(data_copy, dict):
         result = {}
-        for key, value in data.items():
+        for key, value in data_copy.items():
             if isinstance(value, str):
                 try:
                     result[key] = json.loads(value)
@@ -103,7 +110,7 @@ def deserialize_json_values(data):
 
     # Fallback for other data types
     else:
-        return data
+        return data_copy
 
 
 def parse_list_string(text: str) -> list[str]:

data_designer/engine/sampling_gen/entities/dataset_based_person_fields.py

@@ -40,13 +40,16 @@ PII_FIELDS = [
     "state",
     "email_address",
     "phone_number",
+    # Brazil-specific fields
+    "race",
     # Japan-specific fields
     "area",
     "prefecture",
     "zone",
+    # Brazil and India shared fields
+    "religion",
     # India-specific fields
     "district",
-    "religion",
     "education_degree",
     "first_language",
     "second_language",
@@ -78,9 +81,10 @@ PERSONA_FIELDS = [
     # Japan-specific persona fields
     "aspects",
     "digital_skills",
+    # Brazil and India shared persona fields
+    "religious_persona",
+    "religious_background",
     # India-specific persona fields
     "linguistic_persona",
-    "religious_persona",
     "linguistic_background",
-    "religious_background",
 ]

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
@@ -317,7 +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
+                early shutdown behavior, batch sizing via `buffer_size`, and non-inference worker
+                concurrency via `non_inference_max_parallel_workers`. Import RunConfig from
                 data_designer.essentials.
 
         Example:
@@ -334,8 +334,11 @@ 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-0.3.6.dist-info → data_designer-0.3.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-designer
-Version: 0.3.6
+Version: 0.3.8
 Summary: General framework for synthetic data generation
 License-Expression: Apache-2.0
 License-File: LICENSE

{data_designer-0.3.6.dist-info → data_designer-0.3.8.dist-info}/RECORD

@@ -1,5 +1,5 @@
 data_designer/__init__.py,sha256=iLr6FpW41-DFbGexuXCJ6gN1xBMNUZ2jfj9XxySmQhk,502
-data_designer/_version.py,sha256=DPG4bRRG7SLMPQyCzFx7koj75iQndn-UI-ENmNbYVCQ,704
+data_designer/_version.py,sha256=iWEYFk8Ve-UDYmpiH5KfwfwhQTYtkxZlaGPwKE2xDy0,704
 data_designer/errors.py,sha256=r1pBvmvRBAsPmb7oF_veubhkxZ2uPo9cGEDwykLziX4,220
 data_designer/lazy_heavy_imports.py,sha256=wULSEPQRUOZXvOnb0tdf6wNbRBpaaczYfAjY-pstCBM,1512
 data_designer/logging.py,sha256=gRi9BOqm95UC1-u4pn6n-G4EySy9HhwKVyKLRO4aqm4,5382
@@ -42,14 +42,14 @@ data_designer/config/config_builder.py,sha256=vuPibkodbJxbCXdaI1tt1Uyo1SVCnAOfLB
 data_designer/config/data_designer_config.py,sha256=qOojviug05vHR2S4800sjd4OmxhSVi6kB8SAFXLlPog,1891
 data_designer/config/dataset_builders.py,sha256=jdCujJYFlKAiSkPNX2Qeyrs683GrRcCDv_m8ZZhtg64,368
 data_designer/config/dataset_metadata.py,sha256=UTlEgnHWgjwPuc7bP95T7gaKmcr7pIhFMy9vvbUwMV4,647
-data_designer/config/default_model_settings.py,sha256=d9ZuTDGMtS1rZpIDqoSQjCiD5tcHrUOr22X0-mGQspc,4497
+data_designer/config/default_model_settings.py,sha256=c-llH2otfG0tMCMsxoz3ZcS1nFxIQQPfRedFXAydDbc,4868
 data_designer/config/errors.py,sha256=JhvUYecfLmP0gZjQzqA3OmfaSs9TRlC5E-ubnV_-3gs,560
 data_designer/config/exports.py,sha256=lNwteK4djETKXrMKh5PPeHeZvPAZ5RpnJt2otpoaUz0,4756
 data_designer/config/interface.py,sha256=ikmpm_KwencTpM-yg0auo7XMgcmMSa67S75IqdpFLfk,1676
 data_designer/config/models.py,sha256=OekrXEVnI9WdHzEVk-8fO0NtxLZtjKVtCL03RY8qwYs,15457
 data_designer/config/preview_results.py,sha256=WnPlDcHElIHNfjV_P-nLu_Dpul8D3Eyb5qyi3E173Gs,1744
 data_designer/config/processors.py,sha256=lnyUZA1EhO9NWjjVFFioYxSgeYpoAaM1J7UzwOYkvms,6028
-data_designer/config/run_config.py,sha256=5TA1PSmZ3Ca5V0GA1KTds3xrEwGPFZY9C35Vf_1cAs0,2429
+data_designer/config/run_config.py,sha256=oJ163DpHXu9PzST5Hn9px-bIP9DYjIkCO7UGB93J7bI,2663
 data_designer/config/sampler_constraints.py,sha256=tQI1XLF5bS4TnyKMLo0nArvefnXI8dWCzov38r4qNCQ,1197
 data_designer/config/sampler_params.py,sha256=Gio-53vjSYOdPhF2CEq4HSWCXCaZMy4WpGPbuFVcWOM,27965
 data_designer/config/seed.py,sha256=eShSqOcSUzfCEZBnqY-rB0qZpRGxjeOE3fSaJAwacec,4668
@@ -63,7 +63,7 @@ data_designer/config/analysis/dataset_profiler.py,sha256=-5eX55IXivwUBMg2pI-d_3e
 data_designer/config/analysis/utils/errors.py,sha256=pvmdQ_YuIlWW4NFw-cX_rOoQf-GG8y_FiQzNctB__DQ,331
 data_designer/config/analysis/utils/reporting.py,sha256=teTzd1OHtpI4vbIinGOGsKXyNldO3F5eqbNdAztF0_s,7066
 data_designer/config/utils/code_lang.py,sha256=EqMJh1GL5ysUZIoyqx_6vmqenUKHm4J-RQtKXiA4EPg,2354
-data_designer/config/utils/constants.py,sha256=KU4ZCIe18gXdBp2N_BgZlRW90FIqjFPYmJtqgVY3Ink,8925
+data_designer/config/utils/constants.py,sha256=eqDQ57b8B0v5qRSO0He45LEjSxtfxlsPtHRvBu1xkw0,8973
 data_designer/config/utils/errors.py,sha256=HCjer0YrF0bMn5j8gmgWaLb0395LAr_hxMD1ftOsOc8,520
 data_designer/config/utils/info.py,sha256=yOa4U8kI_CY4OfCKZxCm2okU8klAiThvyjKM5tG-F0A,3469
 data_designer/config/utils/io_helpers.py,sha256=kzvOR7QgqijkqU-O2enIlpCWwHvzc3oRaEl4Lsjh1Do,8466
@@ -72,7 +72,7 @@ data_designer/config/utils/numerical_helpers.py,sha256=DIubKzc8q2_Bw7xRjyOGwxYul
 data_designer/config/utils/type_helpers.py,sha256=XyVup24F4Bl7uNze_yUW9oD6EzFbfsJWKhpeMN2901A,4059
 data_designer/config/utils/visualization.py,sha256=_0Mn-jva0Oz1tVTQH1mnWSARpqZ2kh1JSzJEuikyy9s,18491
 data_designer/engine/__init__.py,sha256=XLO09Ei8g0lU7hYlzKCvhvQhLFBe5CBwE4v2PqK9xWY,142
-data_designer/engine/compiler.py,sha256=4a6ayCQjpULrGU2CXaBMDs-RU0TszT2oEkMK-vn51zk,2757
+data_designer/engine/compiler.py,sha256=4QAeCJjINtH0afSXygdhiKMyq2KIfaDthK3ApZLgrQ0,4152
 data_designer/engine/configurable_task.py,sha256=6R4FPXPzIeK0lqNVSEXzRDtK14B3dFz38lplr-nkvRE,2539
 data_designer/engine/errors.py,sha256=YXI7ny83BQ16sOK43CpTm384hJTKuZkPTEAjlHlDIfA,1303
 data_designer/engine/model_provider.py,sha256=_uU5Bw7yrGlMROjHL4dN1mMTg1eN-LVW5JWcQxovhAA,2823
@@ -92,7 +92,7 @@ data_designer/engine/column_generators/generators/__init__.py,sha256=XLO09Ei8g0l
 data_designer/engine/column_generators/generators/base.py,sha256=QElk5KsaUQ3EYwlv40NcZgQsw3HIkX3YQV_0S3erl7Q,4209
 data_designer/engine/column_generators/generators/embedding.py,sha256=uB0jgHlCgctgIUf9ZfMqG1YThbJ0g-GCX3VdNbdDSko,1407
 data_designer/engine/column_generators/generators/expression.py,sha256=BiQcfVTinvQl3OI9nkdhB9B7FGBueWiHJwxTA8uNVuY,2330
-data_designer/engine/column_generators/generators/llm_completion.py,sha256=TGVCV0Sp2AI5KwJ7lG9Co7-zF6gVy-vmVg9eEKmiazE,3873
+data_designer/engine/column_generators/generators/llm_completion.py,sha256=3S3ikNLLLGnutUdcuswL5dUfcLgT_-he8DiRZ9K706U,4721
 data_designer/engine/column_generators/generators/samplers.py,sha256=gNzURmu9K8Zb5MHamKvZPIxmWlFgl2W4FIVgaFcy4f0,3371
 data_designer/engine/column_generators/generators/seed_dataset.py,sha256=CoQPbz4Ww7pBLaGw8-CYqIk1sjfkBaoRMKZQexdfgKY,6824
 data_designer/engine/column_generators/generators/validation.py,sha256=YfYbk-8_ZUye0No6_Q7hIqpZv_tunnEZ6HkLSMFXlDE,6659
@@ -101,11 +101,11 @@ data_designer/engine/column_generators/utils/generator_classification.py,sha256=
 data_designer/engine/column_generators/utils/judge_score_factory.py,sha256=gESiqMrQzbbcFpZas0sAAAkrH2DL0Z4Nq5ywBO-pQ6k,2141
 data_designer/engine/column_generators/utils/prompt_renderer.py,sha256=LATVAlDYwL7HyM7Nogd6n9XTTk-j9s64o4z0LpKHMhQ,4819
 data_designer/engine/dataset_builders/artifact_storage.py,sha256=CKpTBtJTde7OQvsFZQa1v1autVz5yUxlBHkIKeATFnE,10999
-data_designer/engine/dataset_builders/column_wise_builder.py,sha256=_3_JJJG-tA9qLhNiEKbHxl1EHYBbMVAGUtaAdqO_wsc,15736
+data_designer/engine/dataset_builders/column_wise_builder.py,sha256=lzCSk3dFmdZvKLPAVIRNp9oJQsiilthHRW7mB4dUUB4,15716
 data_designer/engine/dataset_builders/errors.py,sha256=gLXtPcGSMBG10PzQ85dOXskdA0mKbBQrHa_VtP9sbVY,400
 data_designer/engine/dataset_builders/multi_column_configs.py,sha256=U4Pg0ETCBq5phRhb2zt8IFa4fRx-aTMakomKOBnrs0U,1660
 data_designer/engine/dataset_builders/utils/__init__.py,sha256=XLO09Ei8g0lU7hYlzKCvhvQhLFBe5CBwE4v2PqK9xWY,142
-data_designer/engine/dataset_builders/utils/concurrency.py,sha256=Q0ro9UY-3-FFzfi3MZ29nMTSiDZgg1Um6y_HQFztDhk,8338
+data_designer/engine/dataset_builders/utils/concurrency.py,sha256=Lga_xd8i3ZAPqJlKCB4GHG7uxWxws1m-UGAz9UeqU_8,8283
 data_designer/engine/dataset_builders/utils/config_compiler.py,sha256=NGI6U0vgG88d5YKj7oW_SIJ4-_fhA6VFhPbjqGRHea4,2441
 data_designer/engine/dataset_builders/utils/dag.py,sha256=RIEI75OtiphkuDl1vfI_MQC1xMiiIg29s-0C_fNZkWQ,2613
 data_designer/engine/dataset_builders/utils/dataset_batch_manager.py,sha256=IfWd_HcfEzIPhgFp2dJaxNIKRlrPsHqYATFXauvCfaw,8133
@@ -114,7 +114,7 @@ data_designer/engine/models/__init__.py,sha256=XLO09Ei8g0lU7hYlzKCvhvQhLFBe5CBwE
 data_designer/engine/models/errors.py,sha256=k9oZnmk8DRD8U2SVKJJRLwrcdsCcVoJiOb_Q7ZyEdvg,12271
 data_designer/engine/models/facade.py,sha256=UBMpw_o2JcsWpJsPdpTPKfFZCh_i0eeG_oaWi1XeKds,12582
 data_designer/engine/models/factory.py,sha256=2NjI0iiGv8ayQ1c249lsJtha4pDmvmtSjdwvlvitRds,1581
-data_designer/engine/models/litellm_overrides.py,sha256=ECreuMCHo2qfLNmW1_53jdE74flbv3pwPa1NIiIQQx4,6145
+data_designer/engine/models/litellm_overrides.py,sha256=e9IZCFQ6BhNWlOTncm8ErL8w4rtE1_4USh2mtUYxCZI,6207
 data_designer/engine/models/registry.py,sha256=7hZ6TQwwZf259yRZmc3ZI20a4wAo3PCOozPi9Mc5KLo,6827
 data_designer/engine/models/telemetry.py,sha256=wmuekvPRZjNz7p7ImKx5H_hqDRhTv_dSB-u2S6Ze3uo,12502
 data_designer/engine/models/usage.py,sha256=A0LV9Ycuj_7snOsaqnirs4mlkAjozv2mzj2om2FpDoU,2410
@@ -127,7 +127,7 @@ data_designer/engine/models/parsers/tag_parsers.py,sha256=HNAIBfXW1Wjdkw4IX-P9sH
 data_designer/engine/models/parsers/types.py,sha256=wEt80al1FykbMplZVjJ5uXFtacMx-a9GE4_QoqDJ6Us,2631
 data_designer/engine/models/recipes/base.py,sha256=AQg3Ay_E0hBEVg-sqSNVVZNMJfJ3r1eT14-b9yqymnQ,2630
 data_designer/engine/models/recipes/response_recipes.py,sha256=UX9m-8RTDj3sXkzEdKpkSj5z7jO-fQhdca3MSByb_Js,10189
-data_designer/engine/processing/utils.py,sha256=iu7JJ4foI3Gfd29ppIBGn9c0syO64PTyvW9CiaLVAHE,5201
+data_designer/engine/processing/utils.py,sha256=g82KsdDR20g_isadpmgHnneQSX0W21aCVhkp5TIWEhw,5443
 data_designer/engine/processing/ginja/__init__.py,sha256=XLO09Ei8g0lU7hYlzKCvhvQhLFBe5CBwE4v2PqK9xWY,142
 data_designer/engine/processing/ginja/ast.py,sha256=w62yt434RDnJYrcfofIDThGv0C5H9XJE3VHOnxEzJVM,1964
 data_designer/engine/processing/ginja/environment.py,sha256=wJRbzPuUCQGvCi4zS4g8sYzihgu_6fn-tE_nYSL1AoU,18974
@@ -164,7 +164,7 @@ data_designer/engine/sampling_gen/data_sources/base.py,sha256=zUG5XTplD5pgHh4ytC
 data_designer/engine/sampling_gen/data_sources/errors.py,sha256=_9rbwUpaz0Pd2Ods4AVDQ7Uq4JvPyfHhTp51BdtJDto,367
 data_designer/engine/sampling_gen/data_sources/sources.py,sha256=53KVPp7REjNKA0rajGmT_tBkxwQqwrcIKhcijBGcfcs,13647
 data_designer/engine/sampling_gen/entities/__init__.py,sha256=XLO09Ei8g0lU7hYlzKCvhvQhLFBe5CBwE4v2PqK9xWY,142
-data_designer/engine/sampling_gen/entities/dataset_based_person_fields.py,sha256=0_eUTtrWFGxTfTfqlz9ig9bJEtYeckb50J7w5LhYTr8,1883
+data_designer/engine/sampling_gen/entities/dataset_based_person_fields.py,sha256=r8qXWe8EquJognihPNGzma4fFuSQAAZHlkYVsGmcX2w,2006
 data_designer/engine/sampling_gen/entities/email_address_utils.py,sha256=THfD7muq5tMHkRWOATN-N3iSFgkKjT4e8hKquDFMTlU,5272
 data_designer/engine/sampling_gen/entities/errors.py,sha256=SbtwwG6JgoY4k6pq2-y-lD60nX_pqjf5QftmwgXt0us,352
 data_designer/engine/sampling_gen/entities/national_id_utils.py,sha256=XUFB6RhfLGFQUNyy0B6BSgtrG9NdEnIjfSALBwJplho,2652
@@ -179,7 +179,7 @@ data_designer/engine/validators/remote.py,sha256=rythhIrH2GvqncMQeF3FiJa9Om0KZWe
 data_designer/engine/validators/sql.py,sha256=AMaEdA-gj9j0zwVp809x3ycKltd51wVEhI8mMYGyxd4,2408
 data_designer/essentials/__init__.py,sha256=dIGYH9s0_VQJ1lG8S-ElZiISz59LHo9v7Y5upizcA1M,1135
 data_designer/interface/__init__.py,sha256=XLO09Ei8g0lU7hYlzKCvhvQhLFBe5CBwE4v2PqK9xWY,142
-data_designer/interface/data_designer.py,sha256=aX3Etg1qGpjivQQdplQ0Oi3aB7_6jzClk_4yrpcE5fY,17322
+data_designer/interface/data_designer.py,sha256=nqsl2Et1wSF3TQzYx3gC1drJzrKlm4FtRE7QJYilbys,17544
 data_designer/interface/errors.py,sha256=Ft9GMeIrOHJv_PC_1rU6hWcNyq1GHdsFYZSc9HnUrxU,606
 data_designer/interface/results.py,sha256=3fGwlhif4ufqUGh-EgsGccrob4S6a7WZ6BgFiszTo_A,3871
 data_designer/plugins/__init__.py,sha256=qe1alcTEtnMSMdzknjb57vvjqKgFE5cEHXxBj8tPWMI,275
@@ -189,8 +189,8 @@ data_designer/plugins/registry.py,sha256=Cnt33Q25o9bS2v2YDbV3QPM57VNrtIBKAb4ERQR
 data_designer/plugins/testing/__init__.py,sha256=yyxrrH_i3q0Xb56QO9Ma35WtHlQ5PJF1b2pQoKa16xU,296
 data_designer/plugins/testing/stubs.py,sha256=9tUF209ayZR6f0Q1LsRDW4kEOTgPoIxV8jlq4QoWuW0,3498
 data_designer/plugins/testing/utils.py,sha256=a9LEgK827cnIzHEkgXOdgywrKDLBE36cyttrpG1ctT4,973
-data_designer-0.3.6.dist-info/METADATA,sha256=DRhL6EhZHVG81mZy-G6czvlm_r9F8sCiu0hIxAyU-q4,8119
-data_designer-0.3.6.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-data_designer-0.3.6.dist-info/entry_points.txt,sha256=NWWWidyDxN6CYX6y664PhBYMhbaYTQTyprqfYAgkyCg,57
-data_designer-0.3.6.dist-info/licenses/LICENSE,sha256=cSWJDwVqHyQgly8Zmt3pqXJ2eQbZVYwN9qd0NMssxXY,11336
-data_designer-0.3.6.dist-info/RECORD,,
+data_designer-0.3.8.dist-info/METADATA,sha256=n9jXs34c2_rOL-Tme5Y6xrb4fMo0-GNNEVHlCl5WfLY,8119
+data_designer-0.3.8.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+data_designer-0.3.8.dist-info/entry_points.txt,sha256=NWWWidyDxN6CYX6y664PhBYMhbaYTQTyprqfYAgkyCg,57
+data_designer-0.3.8.dist-info/licenses/LICENSE,sha256=cSWJDwVqHyQgly8Zmt3pqXJ2eQbZVYwN9qd0NMssxXY,11336
+data_designer-0.3.8.dist-info/RECORD,,