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

data_designer/config/_version.py

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

data_designer/config/column_configs.py

@@ -14,7 +14,7 @@ from data_designer.config.errors import InvalidConfigError
 from data_designer.config.models import ImageContext
 from data_designer.config.sampler_params import SamplerParamsT, SamplerType
 from data_designer.config.utils.code_lang import CodeLang
-from data_designer.config.utils.constants import TRACE_COLUMN_POSTFIX
+from data_designer.config.utils.constants import REASONING_TRACE_COLUMN_POSTFIX
 from data_designer.config.utils.misc import assert_valid_jinja2_template, extract_keywords_from_jinja2_template
 from data_designer.config.validator_params import ValidatorParamsT, ValidatorType
 
@@ -143,8 +143,8 @@ class LLMTextColumnConfig(SingleColumnConfig):
 
     LLM text columns generate free-form text content using language models via LiteLLM.
     Prompts support Jinja2 templating to reference values from other columns, enabling
-    context-aware generation. The generated text can optionally include message traces
-    capturing the full conversation history.
+    context-aware generation. The generated text can optionally include reasoning traces
+    when models support extended thinking.
 
     Attributes:
         prompt: Prompt template for text generation. Supports Jinja2 syntax to
@@ -159,10 +159,6 @@ class LLMTextColumnConfig(SingleColumnConfig):
             `LLMStructuredColumnConfig` for structured output, `LLMCodeColumnConfig` for code.
         multi_modal_context: Optional list of image contexts for multi-modal generation.
             Enables vision-capable models to generate text based on image inputs.
-        with_trace: If True, creates a `{column_name}__trace` column containing the full
-            ordered message history (system/user/assistant) for the generation.
-            Can be overridden globally via `RunConfig.debug_override_save_all_column_traces`.
-            Defaults to False.
         column_type: Discriminator field, always "llm-text" for this configuration type.
     """
 
@@ -170,7 +166,6 @@ class LLMTextColumnConfig(SingleColumnConfig):
     model_alias: str
     system_prompt: str | None = None
     multi_modal_context: list[ImageContext] | None = None
-    with_trace: bool = False
     column_type: Literal["llm-text"] = "llm-text"
 
     @staticmethod
@@ -191,15 +186,14 @@ class LLMTextColumnConfig(SingleColumnConfig):
 
     @property
     def side_effect_columns(self) -> list[str]:
-        """Returns the trace column, which may be generated alongside the main column.
+        """Returns the reasoning trace column, which may be generated alongside the main column.
 
-        Traces are generated when `with_trace=True` on the column config or
-        when `RunConfig.debug_override_save_all_column_traces=True` globally.
+        Reasoning traces are only returned if the served model parses and returns reasoning content.
 
         Returns:
-            List containing the trace column name.
+            List containing the reasoning trace column name.
         """
-        return [f"{self.name}{TRACE_COLUMN_POSTFIX}"]
+        return [f"{self.name}{REASONING_TRACE_COLUMN_POSTFIX}"]
 
     @model_validator(mode="after")
     def assert_prompt_valid_jinja(self) -> Self:

data_designer/config/models.py

@@ -3,7 +3,6 @@
 
 from __future__ import annotations
 
-import json
 import logging
 from abc import ABC, abstractmethod
 from enum import Enum
@@ -66,7 +65,7 @@ class ModalityContext(ABC, BaseModel):
     data_type: ModalityDataType
 
     @abstractmethod
-    def get_contexts(self, record: dict) -> list[dict[str, Any]]: ...
+    def get_context(self, record: dict) -> dict[str, Any]: ...
 
 
 class ImageContext(ModalityContext):
@@ -82,53 +81,25 @@ class ImageContext(ModalityContext):
     modality: Modality = Modality.IMAGE
     image_format: ImageFormat | None = None
 
-    def get_contexts(self, record: dict) -> list[dict[str, Any]]:
-        """Get the contexts for the image modality.
+    def get_context(self, record: dict) -> dict[str, Any]:
+        """Get the context for the image modality.
 
         Args:
-            record: The record containing the image data. The data can be:
-                - A JSON serialized list of strings
-                - A list of strings
-                - A single string
+            record: The record containing the image data.
 
         Returns:
-            A list of image contexts.
+            The context for the image modality.
         """
-        raw_value = record[self.column_name]
-
-        # Normalize to list of strings
-        if isinstance(raw_value, str):
-            # Try to parse as JSON first
-            try:
-                parsed_value = json.loads(raw_value)
-                if isinstance(parsed_value, list):
-                    context_values = parsed_value
-                else:
-                    context_values = [raw_value]
-            except (json.JSONDecodeError, TypeError):
-                context_values = [raw_value]
-        elif isinstance(raw_value, list):
-            context_values = raw_value
-        elif hasattr(raw_value, "__iter__") and not isinstance(raw_value, (str, bytes, dict)):
-            # Handle array-like objects (numpy arrays, pandas Series, etc.)
-            context_values = list(raw_value)
+        context = dict(type="image_url")
+        context_value = record[self.column_name]
+        if self.data_type == ModalityDataType.URL:
+            context["image_url"] = context_value
         else:
-            context_values = [raw_value]
-
-        # Build context list
-        contexts = []
-        for context_value in context_values:
-            context = dict(type="image_url")
-            if self.data_type == ModalityDataType.URL:
-                context["image_url"] = context_value
-            else:
-                context["image_url"] = {
-                    "url": f"data:image/{self.image_format.value};base64,{context_value}",
-                    "format": self.image_format.value,
-                }
-            contexts.append(context)
-
-        return contexts
+            context["image_url"] = {
+                "url": f"data:image/{self.image_format.value};base64,{context_value}",
+                "format": self.image_format.value,
+            }
+        return context
 
     @model_validator(mode="after")
     def _validate_image_format(self) -> Self:
@@ -428,14 +399,12 @@ class ModelConfig(ConfigBase):
         inference_parameters: Inference parameters for the model (temperature, top_p, max_tokens, etc.).
             The generation_type is determined by the type of inference_parameters.
         provider: Optional model provider name if using custom providers.
-        skip_health_check: Whether to skip the health check for this model. Defaults to False.
     """
 
     alias: str
     model: str
     inference_parameters: InferenceParamsT = Field(default_factory=ChatCompletionInferenceParams)
     provider: str | None = None
-    skip_health_check: bool = False
 
     @property
     def generation_type(self) -> GenerationType:

data_designer/config/run_config.py

@@ -33,10 +33,6 @@ class RunConfig(ConfigBase):
         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.
-        debug_override_save_all_column_traces: If True, overrides per-column `with_trace` settings
-            and includes `__trace` columns for ALL LLM generations, containing the full ordered
-            message history (system/user/assistant) for the final generation attempt.
-            Useful for debugging. Default is False.
     """
 
     disable_early_shutdown: bool = False
@@ -46,7 +42,6 @@ class RunConfig(ConfigBase):
     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)
-    debug_override_save_all_column_traces: bool = False
 
     @model_validator(mode="after")
     def normalize_shutdown_settings(self) -> Self:

data_designer/config/utils/code_lang.py

@@ -7,14 +7,9 @@ from enum import Enum
 
 
 class CodeLang(str, Enum):
-    BASH = "bash"
-    C = "c"
-    COBOL = "cobol"
-    CPP = "cpp"
-    CSHARP = "csharp"
     GO = "go"
-    JAVA = "java"
     JAVASCRIPT = "javascript"
+    JAVA = "java"
     KOTLIN = "kotlin"
     PYTHON = "python"
     RUBY = "ruby"
@@ -68,21 +63,15 @@ def code_lang_to_syntax_lexer(code_lang: CodeLang | str) -> str:
     Reference: https://pygments.org/docs/lexers/
     """
     code_lang_to_lexer = {
-        CodeLang.BASH: "bash",
-        CodeLang.C: "c",
-        CodeLang.COBOL: "cobol",
-        CodeLang.CPP: "cpp",
-        CodeLang.CSHARP: "csharp",
         CodeLang.GO: "golang",
-        CodeLang.JAVA: "java",
         CodeLang.JAVASCRIPT: "javascript",
+        CodeLang.JAVA: "java",
         CodeLang.KOTLIN: "kotlin",
         CodeLang.PYTHON: "python",
         CodeLang.RUBY: "ruby",
         CodeLang.RUST: "rust",
         CodeLang.SCALA: "scala",
         CodeLang.SWIFT: "swift",
-        CodeLang.TYPESCRIPT: "typescript",
         CodeLang.SQL_SQLITE: "sql",
         CodeLang.SQL_ANSI: "sql",
         CodeLang.SQL_TSQL: "tsql",

data_designer/config/utils/constants.py

@@ -166,7 +166,7 @@ MIN_TEMPERATURE = 0.0
 MAX_TOP_P = 1.0
 MIN_TOP_P = 0.0
 MIN_MAX_TOKENS = 1
-TRACE_COLUMN_POSTFIX = "__trace"
+REASONING_TRACE_COLUMN_POSTFIX = "__reasoning_trace"
 
 AVAILABLE_LOCALES = [
     "ar_AA",

data_designer/logging.py

@@ -50,14 +50,6 @@ class LoggingConfig:
 class RandomEmoji:
     """A generator for various themed emoji collections."""
 
-    def __init__(self) -> None:
-        self._progress_style = random.choice(_PROGRESS_STYLES)
-
-    def progress(self, percent: float) -> str:
-        """Get a progress emoji based on completion percentage (0-100)."""
-        phase_idx = min(int(percent / 25), len(self._progress_style) - 1)
-        return self._progress_style[phase_idx]
-
     @staticmethod
     def cooking() -> str:
         """Get a random cooking or food preparation emoji."""
@@ -171,10 +163,3 @@ def _make_stream_formatter() -> logging.Formatter:
 
 
 _DEFAULT_NOISY_LOGGERS = ["httpx", "matplotlib"]
-
-
-_PROGRESS_STYLES: list[list[str]] = [
-    ["🌑", "🌘", "🌗", "🌖", "🌕"],  # Moon phases
-    ["🌧️", "🌦️", "⛅", "🌤️", "☀️"],  # Weather (storm to sun)
-    ["🥚", "🐣", "🐥", "🐤", "🐔"],  # Hatching (egg to chicken)
-]

{data_designer_config-0.4.0.dist-info → data_designer_config-0.4.0rc1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-designer-config
-Version: 0.4.0
+Version: 0.4.0rc1
 Summary: Configuration layer for DataDesigner synthetic data generation
 License-Expression: Apache-2.0
 Classifier: Development Status :: 4 - Beta

{data_designer_config-0.4.0.dist-info → data_designer_config-0.4.0rc1.dist-info}/RECORD

@@ -1,11 +1,11 @@
 data_designer/errors.py,sha256=r1pBvmvRBAsPmb7oF_veubhkxZ2uPo9cGEDwykLziX4,220
 data_designer/lazy_heavy_imports.py,sha256=5X04vUj9TYbKgfDmY2qvhzRf5-IZWKOanIpi3_u7fmM,1662
-data_designer/logging.py,sha256=Xq2cRwxmDJ-r8_s9NWnk15efLRsrKm5iVScHy6HkjiE,6044
+data_designer/logging.py,sha256=_x-tDj34ClrgSnU57Dh0mZdDxrnA73vgs09KooUvbEA,5444
 data_designer/plugin_manager.py,sha256=C2ZkZiXlcMRiaxfrrho5Shz6DKdExVeBha7ch-d4CnU,2695
 data_designer/config/__init__.py,sha256=MWzRZhXA41sTpc0sL_xq2baA3kSlV37alT6g8RlP8dU,4919
-data_designer/config/_version.py,sha256=2_0GUP7yBCXRus-qiJKxQD62z172WSs1sQ6DVpPsbmM,704
+data_designer/config/_version.py,sha256=yib4WPM_pEWXdpIHBdFnf29aurTH5f4xrnwVlv7cijo,714
 data_designer/config/base.py,sha256=IGj6sy_GnKzC94uu2rdxe12EqR_AmGJ6O3rl2MxOv6g,2449
-data_designer/config/column_configs.py,sha256=QEHXbxljbGEfOEnzNsiR3_CRpaCukQsayBbHQyhMhbc,20720
+data_designer/config/column_configs.py,sha256=JBYIeqmIiwdZzA-NXTw4qghs2Y30RZPQ_-koqPVcQ9g,20384
 data_designer/config/column_types.py,sha256=xGXuu0EBy3Y5Jd74f2VM6x5jHq72GmK9leA6qOnAz8c,5423
 data_designer/config/config_builder.py,sha256=vuPibkodbJxbCXdaI1tt1Uyo1SVCnAOfLBAW1AmhajI,24707
 data_designer/config/data_designer_config.py,sha256=qOojviug05vHR2S4800sjd4OmxhSVi6kB8SAFXLlPog,1891
@@ -14,10 +14,10 @@ data_designer/config/dataset_metadata.py,sha256=UTlEgnHWgjwPuc7bP95T7gaKmcr7pIhF
 data_designer/config/default_model_settings.py,sha256=c-llH2otfG0tMCMsxoz3ZcS1nFxIQQPfRedFXAydDbc,4868
 data_designer/config/errors.py,sha256=JhvUYecfLmP0gZjQzqA3OmfaSs9TRlC5E-ubnV_-3gs,560
 data_designer/config/interface.py,sha256=ikmpm_KwencTpM-yg0auo7XMgcmMSa67S75IqdpFLfk,1676
-data_designer/config/models.py,sha256=_NctRk4brgBeb5q5V7r_hXE5OORlLh6SCVZP0eu2LGo,16721
+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=m_rrqEmNHR533AYJ_OR5yq0a9Pegy9vPGZgyfD4x9cI,3052
+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
@@ -32,8 +32,8 @@ data_designer/config/analysis/utils/errors.py,sha256=pvmdQ_YuIlWW4NFw-cX_rOoQf-G
 data_designer/config/analysis/utils/reporting.py,sha256=teTzd1OHtpI4vbIinGOGsKXyNldO3F5eqbNdAztF0_s,7066
 data_designer/config/testing/__init__.py,sha256=vxFrIOqDoDfOx-MWjC5lb_hvmB4kRKvh1QdTv--QYFM,222
 data_designer/config/testing/fixtures.py,sha256=J1bcWjerAIoVUIZBVPbUcuvEa2laj_kspVcLS7UZMbo,10876
-data_designer/config/utils/code_lang.py,sha256=nUeWjuzSYBVF5gwOiUE2-EsYCEDzRZaw31RIivt7GPI,2638
-data_designer/config/utils/constants.py,sha256=lprfeF_bIzGJ_oGrZBhvHEbLVgrGfFtVbCdWJHf_6B8,8953
+data_designer/config/utils/code_lang.py,sha256=EqMJh1GL5ysUZIoyqx_6vmqenUKHm4J-RQtKXiA4EPg,2354
+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
@@ -45,6 +45,6 @@ data_designer/plugins/__init__.py,sha256=qe1alcTEtnMSMdzknjb57vvjqKgFE5cEHXxBj8t
 data_designer/plugins/errors.py,sha256=d7FMed3ueQvZHwuhwyPLzF4E34bO1mdj3aBVEw6p34o,386
 data_designer/plugins/plugin.py,sha256=TVyyOaQBWAt0FQwUmtihTZ9MDJD85HwggrQ3L9CviPQ,5367
 data_designer/plugins/registry.py,sha256=Cnt33Q25o9bS2v2YDbV3QPM57VNrtIBKAb4ERQRE_dY,3053
-data_designer_config-0.4.0.dist-info/METADATA,sha256=l06rdZe6t1jKhqvgkH0ZYSTXX-UUVsjQ-ZIfwD_mwvA,2283
-data_designer_config-0.4.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-data_designer_config-0.4.0.dist-info/RECORD,,
+data_designer_config-0.4.0rc1.dist-info/METADATA,sha256=EvLUDu0U0oK7FuylbCr44meSR8H5Ty-bt-EdUIagmi4,2286
+data_designer_config-0.4.0rc1.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+data_designer_config-0.4.0rc1.dist-info/RECORD,,