sdg-hub 0.4.2__py3-none-any.whl → 0.5.0__py3-none-any.whl

sdg_hub/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.4.2'
-__version_tuple__ = version_tuple = (0, 4, 2)
+__version__ = version = '0.5.0'
+__version_tuple__ = version_tuple = (0, 5, 0)
 
 __commit_id__ = commit_id = None

sdg_hub/core/blocks/__init__.py

@@ -5,17 +5,6 @@ This package provides various block implementations for data generation, process
 
 # Local
 from .base import BaseBlock
-from .deprecated_blocks import (
-    CombineColumnsBlock,
-    DuplicateColumns,
-    FilterByValueBlock,
-    FlattenColumnsBlock,
-    LLMBlock,
-    RenameColumns,
-    SamplePopulatorBlock,
-    SelectorBlock,
-    SetToMajorityValue,
-)
 from .filtering import ColumnValueFilterBlock
 from .llm import LLMChatBlock, LLMParserBlock, PromptBuilderBlock, TextParserBlock
 from .registry import BlockRegistry
@@ -28,8 +17,6 @@ from .transform import (
     UniformColumnValueSetter,
 )
 
-# All blocks moved to deprecated_blocks or transform modules
-
 __all__ = [
     "BaseBlock",
     "BlockRegistry",
@@ -40,15 +27,6 @@ __all__ = [
     "RenameColumnsBlock",
     "TextConcatBlock",
     "UniformColumnValueSetter",
-    "CombineColumnsBlock",  # Deprecated
-    "DuplicateColumns",  # Deprecated
-    "FilterByValueBlock",  # Deprecated
-    "FlattenColumnsBlock",  # Deprecated
-    "RenameColumns",  # Deprecated
-    "SamplePopulatorBlock",  # Deprecated
-    "SelectorBlock",  # Deprecated
-    "SetToMajorityValue",  # Deprecated
-    "LLMBlock",  # Deprecated
     "LLMChatBlock",
     "LLMParserBlock",
     "TextParserBlock",

sdg_hub/core/blocks/transform/rename_columns.py

@@ -64,6 +64,25 @@ class RenameColumnsBlock(BaseBlock):
         -------
         Dataset
             Dataset with renamed columns.
+
+        Raises
+        ------
+        ValueError
+            If attempting to rename to a column name that already exists.
         """
+        # Check for column name collisions
+        # Strict validation: no target column name can be an existing column name
+        # This prevents chained/circular renames which can be confusing
+        existing_cols = set(samples.column_names)
+        target_cols = set(self.input_cols.values())
+
+        collision = target_cols & existing_cols
+        if collision:
+            raise ValueError(
+                f"Cannot rename to existing column names: {sorted(collision)}. "
+                "Target column names must not already exist in the dataset. "
+                "Chained renames are not supported."
+            )
+
         # Rename columns using HuggingFace datasets method
         return samples.rename_columns(self.input_cols)

sdg_hub/core/flow/base.py

@@ -41,7 +41,6 @@ from ..utils.time_estimator import estimate_execution_time
 from ..utils.yaml_utils import save_flow_yaml
 from .checkpointer import FlowCheckpointer
 from .metadata import DatasetRequirements, FlowMetadata
-from .migration import FlowMigration
 from .validation import FlowValidator
 
 logger = setup_logger(__name__)
@@ -73,8 +72,6 @@ class Flow(BaseModel):
     model_config = ConfigDict(extra="forbid", arbitrary_types_allowed=True)
 
     # Private attributes (not serialized)
-    _migrated_runtime_params: dict[str, dict[str, Any]] = {}
-    _llm_client: Any = None  # Only used for backward compatibility with old YAMLs
     _model_config_set: bool = False  # Track if model configuration has been set
     _block_metrics: list[dict[str, Any]] = PrivateAttr(
         default_factory=list
@@ -113,16 +110,13 @@ class Flow(BaseModel):
         return self
 
     @classmethod
-    def from_yaml(cls, yaml_path: str, client: Any = None) -> "Flow":
+    def from_yaml(cls, yaml_path: str) -> "Flow":
         """Load flow from YAML configuration file.
 
         Parameters
         ----------
         yaml_path : str
             Path to the YAML flow configuration file.
-        client : Any, optional
-            LLM client instance. Required for backward compatibility with old format YAMLs
-            that use deprecated LLMBlocks. Ignored for new format YAMLs.
 
         Returns
         -------
@@ -153,21 +147,6 @@ class Flow(BaseModel):
         except yaml.YAMLError as exc:
             raise FlowValidationError(f"Invalid YAML in {yaml_path}: {exc}") from exc
 
-        # Check if this is an old format flow and migrate if necessary
-        migrated_runtime_params = None
-        is_old_format = FlowMigration.is_old_format(flow_config)
-        if is_old_format:
-            logger.info(f"Detected old format flow, migrating: {yaml_path}")
-            if client is None:
-                logger.warning(
-                    "Old format YAML detected but no client provided. LLMBlocks may fail."
-                )
-            flow_config, migrated_runtime_params = FlowMigration.migrate_to_new_format(
-                flow_config, yaml_path
-            )
-            # Save migrated config back to YAML to persist id
-            save_flow_yaml(yaml_path, flow_config, "migrated to new format")
-
         # Validate YAML structure
         validator = FlowValidator()
         validation_errors = validator.validate_yaml_structure(flow_config)
@@ -194,19 +173,6 @@ class Flow(BaseModel):
 
         for i, block_config in enumerate(block_configs):
             try:
-                # Inject client for deprecated LLMBlocks if this is an old format flow
-                if (
-                    is_old_format
-                    and block_config.get("block_type") == "LLMBlock"
-                    and client is not None
-                ):
-                    if "block_config" not in block_config:
-                        block_config["block_config"] = {}
-                    block_config["block_config"]["client"] = client
-                    logger.debug(
-                        f"Injected client for deprecated LLMBlock: {block_config['block_config'].get('block_name')}"
-                    )
-
                 block = cls._create_block_from_config(block_config, yaml_dir)
                 blocks.append(block)
             except Exception as exc:
@@ -228,12 +194,6 @@ class Flow(BaseModel):
                 )
             else:
                 logger.debug(f"Flow already had id: {flow.metadata.id}")
-            # Store migrated runtime params and client for backward compatibility
-            if migrated_runtime_params:
-                flow._migrated_runtime_params = migrated_runtime_params
-            if is_old_format and client is not None:
-                flow._llm_client = client
-
             # Check if this is a flow without LLM blocks
             llm_blocks = flow._detect_llm_blocks()
             if not llm_blocks:
@@ -484,12 +444,6 @@ class Flow(BaseModel):
         self._block_metrics = []
         run_start = time.perf_counter()
 
-        # Merge migrated runtime params with provided ones (provided ones take precedence)
-        merged_runtime_params = self._migrated_runtime_params.copy()
-        if runtime_params:
-            merged_runtime_params.update(runtime_params)
-        runtime_params = merged_runtime_params
-
         # Execute flow with metrics capture, ensuring metrics are always displayed/saved
         final_dataset = None
         execution_successful = False
@@ -647,22 +601,8 @@ class Flow(BaseModel):
             input_cols = set(current_dataset.column_names)
 
             try:
-                # Check if this is a deprecated block and skip validations
-                is_deprecated_block = (
-                    hasattr(block, "__class__")
-                    and hasattr(block.__class__, "__module__")
-                    and "deprecated_blocks" in block.__class__.__module__
-                )
-
-                if is_deprecated_block:
-                    exec_logger.debug(
-                        f"Skipping validations for deprecated block: {block.block_name}"
-                    )
-                    # Call generate() directly to skip validations, but keep the runtime params
-                    current_dataset = block.generate(current_dataset, **block_kwargs)
-                else:
-                    # Execute block with validation and logging
-                    current_dataset = block(current_dataset, **block_kwargs)
+                # Execute block with validation and logging
+                current_dataset = block(current_dataset, **block_kwargs)
 
                 # Validate output
                 if len(current_dataset) == 0:
@@ -724,9 +664,11 @@ class Flow(BaseModel):
         return current_dataset
 
     def _prepare_block_kwargs(
-        self, block: BaseBlock, runtime_params: dict[str, dict[str, Any]]
+        self, block: BaseBlock, runtime_params: Optional[dict[str, dict[str, Any]]]
     ) -> dict[str, Any]:
         """Prepare execution parameters for a block."""
+        if runtime_params is None:
+            return {}
         return runtime_params.get(block.block_name, {})
 
     def set_model_config(
@@ -1114,22 +1056,8 @@ class Flow(BaseModel):
                 if max_concurrency is not None:
                     block_kwargs["_flow_max_concurrency"] = max_concurrency
 
-                # Check if this is a deprecated block and skip validations
-                is_deprecated_block = (
-                    hasattr(block, "__class__")
-                    and hasattr(block.__class__, "__module__")
-                    and "deprecated_blocks" in block.__class__.__module__
-                )
-
-                if is_deprecated_block:
-                    logger.debug(
-                        f"Dry run: Skipping validations for deprecated block: {block.block_name}"
-                    )
-                    # Call generate() directly to skip validations, but keep the runtime params
-                    current_dataset = block.generate(current_dataset, **block_kwargs)
-                else:
-                    # Execute block with validation and logging
-                    current_dataset = block(current_dataset, **block_kwargs)
+                # Execute block with validation and logging
+                current_dataset = block(current_dataset, **block_kwargs)
 
                 block_execution_time = (
                     time.perf_counter() - block_start_time

sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/detailed_summary/flow.yaml

@@ -77,9 +77,13 @@ blocks:
     - ''
 - block_type: RenameColumnsBlock
   block_config:
-    block_name: rename_to_document_column
+    block_name: rename_to_raw_document_column
     input_cols:
       document: raw_document
+- block_type: RenameColumnsBlock
+  block_config:
+    block_name: rename_to_document_column
+    input_cols:
       summary: document
 - block_type: PromptBuilderBlock
   block_config:

sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/extractive_summary/flow.yaml

@@ -79,9 +79,13 @@ blocks:
     - ''
 - block_type: RenameColumnsBlock
   block_config:
-    block_name: rename_to_document_column
+    block_name: rename_to_raw_document_column
     input_cols:
       document: raw_document
+- block_type: RenameColumnsBlock
+  block_config:
+    block_name: rename_to_document_column
+    input_cols:
       summary: document
 - block_type: PromptBuilderBlock
   block_config:

sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/key_facts/flow.yaml

@@ -72,9 +72,13 @@ blocks:
     parsing_pattern: '(?:^|\n)\s*\d+\.\s+(.*?)(?=\n\s*\d+\.\s+|\Z)'
 - block_type: RenameColumnsBlock
   block_config:
-    block_name: rename_to_document_column
+    block_name: rename_to_raw_document_column
     input_cols:
       document: raw_document
+- block_type: RenameColumnsBlock
+  block_config:
+    block_name: rename_to_document_column
+    input_cols:
       atomic_facts: document
 - block_type: PromptBuilderBlock
   block_config:

sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/instructlab/flow.yaml

@@ -134,10 +134,15 @@ blocks:
       input_cols: [summary_detailed, summary_extractive, summary_atomic_facts, base_document]
       output_cols: [summary, dataset_type]
 
+  - block_type: RenameColumnsBlock
+    block_config:
+      block_name: rename_to_raw_document_column
+      input_cols: {document: raw_document}
+
   - block_type: RenameColumnsBlock
     block_config:
       block_name: rename_to_document_column
-      input_cols: {document: raw_document, summary: document}
+      input_cols: {summary: document}
 
   - block_type: PromptBuilderBlock
     block_config:

sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/multilingual/japanese/flow.yaml

@@ -135,10 +135,14 @@ blocks:
       input_cols: [summary_detailed, summary_extractive, summary_atomic_facts, base_document]
       output_cols: [summary, dataset_type]
 
+  - block_type: RenameColumnsBlock
+    block_config:
+      block_name: rename_to_raw_document_column
+      input_cols: {document: raw_document}
   - block_type: RenameColumnsBlock
     block_config:
       block_name: rename_to_document_column
-      input_cols: {document: raw_document, summary: document}
+      input_cols: {summary: document}
 
   - block_type: PromptBuilderBlock
     block_config:

{sdg_hub-0.4.2.dist-info → sdg_hub-0.5.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sdg_hub
-Version: 0.4.2
+Version: 0.5.0
 Summary: Synthetic Data Generation
 Author-email: Red Hat AI Innovation <abhandwa@redhat.com>
 License: Apache-2.0
@@ -23,7 +23,7 @@ Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: click<9.0.0,>=8.1.7
-Requires-Dist: datasets<4.0.0,>=2.18.0
+Requires-Dist: datasets>=4.0.0
 Requires-Dist: httpx<1.0.0,>=0.25.0
 Requires-Dist: jinja2
 Requires-Dist: litellm<1.75.0,>=1.73.0

{sdg_hub-0.4.2.dist-info → sdg_hub-0.5.0.dist-info}/RECORD

@@ -1,20 +1,10 @@
 sdg_hub/__init__.py,sha256=TlkZT40-70urdcWLqv3kupaJj8s-SVgd2QyvlSFwb4A,510
-sdg_hub/_version.py,sha256=A45grTqzrHuDn1CT9K5GVUbY4_Q3OSTcXAl3zdHzcEI,704
+sdg_hub/_version.py,sha256=fvHpBU3KZKRinkriKdtAt3crenOyysELF-M9y3ozg3U,704
 sdg_hub/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sdg_hub/core/__init__.py,sha256=e3BoejbqjYhasf9t__L4qE52lkD9EBjx4o--2kqKdro,460
-sdg_hub/core/blocks/__init__.py,sha256=5FsbkcO-dmBv6MqO96TPn9FKKPTQZQCv20j4wR7UvQw,1502
+sdg_hub/core/blocks/__init__.py,sha256=8Rn1SglH8V3jGmTD_cG-h7qk9ktAab2eaBdyk7RN_hY,865
 sdg_hub/core/blocks/base.py,sha256=-SOdBpJwtRTMsrmCEuLjUBQMRCo_PLYlHEBRrz8sF9g,13031
 sdg_hub/core/blocks/registry.py,sha256=FuEN_pnq-nSH1LguY3_oCubT6Kz3SuJjk3TcUpLT-lw,10695
-sdg_hub/core/blocks/deprecated_blocks/__init__.py,sha256=RDu3MWFStDQko-TKkx8tGoB1UTatP_RSldZK43zHDvY,889
-sdg_hub/core/blocks/deprecated_blocks/combine_columns.py,sha256=HCvpaYsAwgx1Dm0vIshcWsKoVsRT0KrmKp9j4oqtByc,2757
-sdg_hub/core/blocks/deprecated_blocks/duplicate_columns.py,sha256=maCaaEs0EMMzt7L1xm7fAH3ylaFMHEkeC_dtOw3FrjU,2694
-sdg_hub/core/blocks/deprecated_blocks/filter_by_value.py,sha256=-fuuMKj2g2MrijMBTd0PWtYBbf9anQ2UkYXHigCxxJI,3328
-sdg_hub/core/blocks/deprecated_blocks/flatten_columns.py,sha256=IenCskrPEv09h2uT6aZKCQzaxgA_3kAzOeJSd-R_-EA,2839
-sdg_hub/core/blocks/deprecated_blocks/llmblock.py,sha256=34lzC43BODpMk5AwlWA1ctdYPmN7cA6WL5vMXaI0P0Y,20385
-sdg_hub/core/blocks/deprecated_blocks/rename_columns.py,sha256=thp-mHtkRmUw_nYKpldy_mLWR2AvC5YUhbqDETM6-T0,2620
-sdg_hub/core/blocks/deprecated_blocks/sample_populator.py,sha256=UdueMApxOmPWaxxMrw7b1v74fKJBfqqRATEBqgmVtNw,1737
-sdg_hub/core/blocks/deprecated_blocks/selector.py,sha256=nWecsVsW8DvBcqAF_LOqXmW-5MQ28uN3d1y6wkSy38c,2960
-sdg_hub/core/blocks/deprecated_blocks/set_to_majority_value.py,sha256=44TQu-rK5isia-otMVB1zHd8D-wWmu3C8CI1NLtfY5s,2729
 sdg_hub/core/blocks/filtering/__init__.py,sha256=isxSVSvDqkMjG8dQSl3Q2M4g5c1t9fTjBSA21icf-yA,275
 sdg_hub/core/blocks/filtering/column_value_filter.py,sha256=2Z9j_CiiTn5mHZ9gfXU-itLXDmeXSh0UI0x1x7j-LQ0,6001
 sdg_hub/core/blocks/llm/__init__.py,sha256=AyS0dd3pkPPXH5a9aj4mT5HsKjX2vjXfkmQc6rkFV4A,795
@@ -29,14 +19,13 @@ sdg_hub/core/blocks/transform/duplicate_columns.py,sha256=SaP7rIF4ZFEFFa50aU2xGN
 sdg_hub/core/blocks/transform/index_based_mapper.py,sha256=XC_a7Skbd3mu7f4ra8fGWPxMwqUMSjJkQ7Ag7vflwJA,8235
 sdg_hub/core/blocks/transform/json_structure_block.py,sha256=hm-0M0NAyUREgJRPyV1u-laorgX6MZ1o17E9rNBhN78,5010
 sdg_hub/core/blocks/transform/melt_columns.py,sha256=vaYa5Taq6GhNZYWFL4uPK3-SfN2BsKEm-wvjd2EYYoI,4382
-sdg_hub/core/blocks/transform/rename_columns.py,sha256=qeB5L2utqDQnutUetH1VKZSqDiJSH_yUp5EFCV-XCVI,1998
+sdg_hub/core/blocks/transform/rename_columns.py,sha256=W2hcDSJY6L73ZpElUhOML2sGLM9Y-v0gSo3xEF1LXDc,2749
 sdg_hub/core/blocks/transform/text_concat.py,sha256=_-B__Hob1WwgwkILPIZvTnsDzuwtoX1hKviyzHlnnes,3149
 sdg_hub/core/blocks/transform/uniform_col_val_setter.py,sha256=XnjiT29z3PzIPy8M-mmE2w-Miab6Ed5ahy32SaxTCTE,3263
 sdg_hub/core/flow/__init__.py,sha256=0_m_htuZfPxk8xQ9IKfp0Pz-JRE4O7lYMUFrKyLNoLA,409
-sdg_hub/core/flow/base.py,sha256=4kR-dKXAlLFSwm3YWdT8EoedCIGJT56agcot3tQb6VY,59508
+sdg_hub/core/flow/base.py,sha256=64YJJujNRaSIbT1YKn9nAxij_hdJ9xRVH_uiUY1IUcI,55788
 sdg_hub/core/flow/checkpointer.py,sha256=stm5ZtjjEiLk9ZkAAnoQQn5Y8Yl_d7qCsQLZTrCXR48,11867
 sdg_hub/core/flow/metadata.py,sha256=cFrpJjWOaK87aCuRFyC3Pdf83oYU93mrmZEMdUnhsN8,10540
-sdg_hub/core/flow/migration.py,sha256=6and-RBqV0t2gRipr1GiOOVnyBJdtyyjw1kO08Z--d4,7558
 sdg_hub/core/flow/registry.py,sha256=N6KfX-L7QRkooznIFxDuhRZYuDA5g3N5zC-KRm2jVhk,12109
 sdg_hub/core/flow/validation.py,sha256=pUJvgaUjLpKNwvW6djcqVOF-HShOjegEmGOnUnoX4BA,9722
 sdg_hub/core/utils/__init__.py,sha256=KcT56JhobC5sBg0MKEMn5hc4OyKa9_Vnn45Mt_kS4jQ,610
@@ -55,14 +44,14 @@ sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/gener
 sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/generate_question_list.yaml,sha256=qHOgUNrQz2vjUjJiEHNGWxDDXwjJlP1kofTxeGgLyPI,1461
 sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/detailed_summary/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/detailed_summary/detailed_summary.yaml,sha256=Ik6gAml0O-jPq8jpXBAkURzYkQuFOnDZb4LDwjmfAiE,381
-sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/detailed_summary/flow.yaml,sha256=fUdzY9dtU69o99Uq8FIPycgVWdLD-1kbY97Bh-Vo2A0,5538
+sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/detailed_summary/flow.yaml,sha256=cxNpPh60mcvzxfczMH8hw66Ql3S8O-cWCCDeauO736c,5649
 sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/doc_direct_qa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/doc_direct_qa/flow.yaml,sha256=smPWVUZRCt58EagWDmJVmTBQj8qMcjpzh-Q3GSuFrz0,4413
 sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/extractive_summary/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/extractive_summary/extractive_summary.yaml,sha256=SeapWoOx3fhN5SvWYuHss_9prLE8xSkOic7JkbDHSR0,4081
-sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/extractive_summary/flow.yaml,sha256=iNNIfofFE7awK7iivtIFWxjfjy8QviMugOPPnOTySKA,5706
+sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/extractive_summary/flow.yaml,sha256=7dVc0_g7Ex5SfdX57pqtk9gmH_lC6Cdm3HC-lg8OiXQ,5817
 sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/key_facts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/key_facts/flow.yaml,sha256=CIUZNYhvszT-jpz1Hvh6nS2y5W34P529ZOMp8thEQ9k,3219
+sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/key_facts/flow.yaml,sha256=7X4N19TcyHUo7pNo3C6Zv3w6br7hjzEfgv06XUVDaQo,3330
 sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/key_facts/key_facts_summary.yaml,sha256=YKMX_CuvcThG_bdNCAIXdVBkMvB72I89RGq2ltSSgc8,3298
 sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/instructlab/README.md,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/instructlab/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -72,14 +61,14 @@ sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/instructlab/ev
 sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/instructlab/evaluate_question.yaml,sha256=zwzklXup6khRkR88avgrJTcjaMcV1wnbeYaML5oPuNs,1767
 sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/instructlab/evaluate_relevancy.yaml,sha256=cA8igo7jMrRXaWW6k0of6KOp7YnxLtPj0fP4DbrmZNQ,3647
 sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/instructlab/extractive_summary.yaml,sha256=fcMV7LaCFZo4D29nwhGJXqFFuZMYVLo9XYjv8zcU6zs,364
-sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/instructlab/flow.yaml,sha256=HR8sf7RUZKr8UqKztBj-nlvyrve1UMUu8x8qgYM6O14,9055
+sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/instructlab/flow.yaml,sha256=km0ggcmFsZJGc2TfyYLkzPTrHGmcOB-jBAHInqySisk,9176
 sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/instructlab/generate_questions_responses.yaml,sha256=yX8aLY8dJSDML9ZJhnj9RzPbN8tH2xfcM4Gc6xZuwqQ,2596
 sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/multilingual/japanese/README.md,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/multilingual/japanese/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/multilingual/japanese/atomic_facts_ja.yaml,sha256=OjPZaSCOSLxEWgW3pmNwF7mmLhGhFGTmKL_3rKdqeW4,2488
 sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/multilingual/japanese/detailed_summary_ja.yaml,sha256=nEy_RcotHGiiENrmUANpKkbIFsrARAeSwECrBeHi2so,391
 sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/multilingual/japanese/extractive_summary_ja.yaml,sha256=V90W0IeJQZTFThA8v0UOs3DtZbtU3BI9jkpChw1BULo,402
-sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/multilingual/japanese/flow.yaml,sha256=jumjKmKshSd8hoTYpyBJ0nMOADeQmxBmNPY7yfa_xQ8,9171
+sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/multilingual/japanese/flow.yaml,sha256=Q6RusV-_HHMr5jlFNOP6UVuEf8d6btHENMOP3MnB3u0,9291
 sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/multilingual/japanese/generate_questions_responses_ja.yaml,sha256=96SQqXG7fmb-50SdX85sgVtrFcQ-oNKe_0BoQdZmY5g,2638
 sdg_hub/flows/text_analysis/__init__.py,sha256=WStks4eM_KHNTVsHglcj8vFghmI0PH9P1hUrijBLbwc,125
 sdg_hub/flows/text_analysis/structured_insights/__init__.py,sha256=_DT4NR05JD9CZoSWROPr2lC6se0VjSqQPZJJlEV79mk,274
@@ -88,8 +77,8 @@ sdg_hub/flows/text_analysis/structured_insights/extract_entities.yaml,sha256=Q_S
 sdg_hub/flows/text_analysis/structured_insights/extract_keywords.yaml,sha256=_nPPMdHnxag_lYbhYUjGJGo-CvRwWvwdGX7cQhdZ1S0,847
 sdg_hub/flows/text_analysis/structured_insights/flow.yaml,sha256=BBV18SdvuVTAESjwkJ7V1jbb-cSTBvNl3SCycd0oEQ4,4934
 sdg_hub/flows/text_analysis/structured_insights/summarize.yaml,sha256=WXwQak1pF8e1OwnOoI1EHu8QB6iUNW89rfkTdi1Oq54,687
-sdg_hub-0.4.2.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-sdg_hub-0.4.2.dist-info/METADATA,sha256=5qbw9_DoVmfntmQlvz4VPdQXdUXoLO8Zhrxbc1uY7b0,9783
-sdg_hub-0.4.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-sdg_hub-0.4.2.dist-info/top_level.txt,sha256=TqI7d-HE1n6zkXFkU0nF3A1Ct0P0pBaqI675uFokhx4,8
-sdg_hub-0.4.2.dist-info/RECORD,,
+sdg_hub-0.5.0.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+sdg_hub-0.5.0.dist-info/METADATA,sha256=z4tCCtWlTBzu5DF1K44RtWjIs7ZNL6__2Aae7I0EfxQ,9775
+sdg_hub-0.5.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+sdg_hub-0.5.0.dist-info/top_level.txt,sha256=TqI7d-HE1n6zkXFkU0nF3A1Ct0P0pBaqI675uFokhx4,8
+sdg_hub-0.5.0.dist-info/RECORD,,

sdg_hub/core/blocks/deprecated_blocks/__init__.py

@@ -1,29 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-"""Deprecated blocks for backwards compatibility.
-
-This module contains deprecated block implementations that are maintained
-for backwards compatibility. These blocks should not be used in new code.
-"""
-
-# Local
-from .combine_columns import CombineColumnsBlock
-from .duplicate_columns import DuplicateColumns
-from .filter_by_value import FilterByValueBlock
-from .flatten_columns import FlattenColumnsBlock
-from .llmblock import LLMBlock
-from .rename_columns import RenameColumns
-from .sample_populator import SamplePopulatorBlock
-from .selector import SelectorBlock
-from .set_to_majority_value import SetToMajorityValue
-
-__all__ = [
-    "CombineColumnsBlock",
-    "DuplicateColumns",
-    "FilterByValueBlock",
-    "FlattenColumnsBlock",
-    "LLMBlock",
-    "RenameColumns",
-    "SamplePopulatorBlock",
-    "SelectorBlock",
-    "SetToMajorityValue",
-]

sdg_hub/core/blocks/deprecated_blocks/combine_columns.py

@@ -1,93 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-"""DEPRECATED: CombineColumnsBlock for backward compatibility.
-
-This module provides a deprecated wrapper for the old CombineColumnsBlock interface.
-Use transform.CombineColumnsBlock instead.
-"""
-
-# Standard
-from typing import Any
-import warnings
-
-# Third Party
-from datasets import Dataset
-
-# Local
-from ...utils.logger_config import setup_logger
-from ..base import BaseBlock
-from ..registry import BlockRegistry
-from ..transform.text_concat import TextConcatBlock
-
-logger = setup_logger(__name__)
-
-
-@BlockRegistry.register(
-    "CombineColumnsBlock",
-    "deprecated",
-    "DEPRECATED: Use TextConcatBlock instead. Combines multiple columns into a single column using a separator",
-)
-class CombineColumnsBlock(BaseBlock):
-    r"""DEPRECATED: Combine multiple columns into a single column using a separator.
-
-    .. deprecated::
-        Use `sdg_hub.blocks.transform.CombineColumnsBlock` instead.
-        This class will be removed in a future version.
-
-    This block concatenates values from multiple columns into a single output column,
-    using a specified separator between values.
-
-    Parameters
-    ----------
-    block_name : str
-        Name of the block.
-    columns : List[str]
-        List of column names to combine.
-    output_col : str
-        Name of the column to store combined values.
-    separator : str, optional
-        String to use as separator between combined values, by default "\\n\\n".
-    **batch_kwargs : Dict[str, Any]
-        Additional keyword arguments for batch processing.
-    """
-
-    def __init__(
-        self,
-        block_name: str,
-        columns: list[str],
-        output_col: str,
-        separator: str = "\n\n",
-        **batch_kwargs: dict[str, Any],
-    ) -> None:
-        warnings.warn(
-            "CombineColumnsBlock is deprecated. Use sdg_hub.blocks.transform.TextConcatBlock instead.",
-            DeprecationWarning,
-            stacklevel=2,
-        )
-
-        # Initialize with dummy values for BaseBlock validation
-        super().__init__(
-            block_name=block_name, input_cols=columns, output_cols=[output_col]
-        )
-
-        # Create the new implementation
-        self._impl = TextConcatBlock(
-            block_name=block_name,
-            input_cols=columns,
-            output_cols=[output_col],
-            separator=separator,
-        )
-
-    def generate(self, samples: Dataset, **kwargs: Any) -> Dataset:
-        """Generate a dataset with combined columns.
-
-        Parameters
-        ----------
-        samples : Dataset
-            Input dataset to process.
-
-        Returns
-        -------
-        Dataset
-            Dataset with combined values stored in output column.
-        """
-        return self._impl.generate(samples)

sdg_hub/core/blocks/deprecated_blocks/duplicate_columns.py

@@ -1,88 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-"""Deprecated DuplicateColumns for backwards compatibility.
-
-This module provides a deprecated wrapper around DuplicateColumnsBlock
-to maintain backwards compatibility with existing code and configurations.
-"""
-
-# Standard
-from typing import Any
-import warnings
-
-# Third Party
-from datasets import Dataset
-
-# Local
-from ...utils.logger_config import setup_logger
-from ..base import BaseBlock
-from ..registry import BlockRegistry
-from ..transform import DuplicateColumnsBlock
-
-logger = setup_logger(__name__)
-
-
-@BlockRegistry.register(
-    "DuplicateColumns",
-    "deprecated",
-    "DEPRECATED: Use DuplicateColumnsBlock instead. Duplicates existing columns with new names according to a mapping dictionary",
-)
-class DuplicateColumns(BaseBlock):
-    """DEPRECATED: Block for duplicating existing columns with new names.
-
-    This block is deprecated and maintained only for backwards compatibility.
-    Please use DuplicateColumnsBlock instead.
-
-    This block creates copies of existing columns with new names as specified
-    in the columns mapping dictionary.
-    """
-
-    def __init__(
-        self,
-        block_name: str,
-        columns_map: dict[str, str],
-    ) -> None:
-        """Initialize the deprecated DuplicateColumns.
-
-        Parameters
-        ----------
-        block_name : str
-            Name of the block.
-        columns_map : Dict[str, str]
-            Dictionary mapping existing column names to new column names.
-            Keys are existing column names, values are new column names.
-        """
-        # Issue deprecation warning
-        warnings.warn(
-            "DuplicateColumns is deprecated and will be removed in a future version. "
-            "Please use DuplicateColumnsBlock instead.",
-            DeprecationWarning,
-            stacklevel=2,
-        )
-
-        # Map old signature to new signature
-        super().__init__(
-            block_name=block_name,
-            input_cols=columns_map,
-            output_cols=list(columns_map.values()),
-        )
-
-        # Create the new block instance with mapped parameters
-        self._new_block = DuplicateColumnsBlock(
-            block_name=block_name,
-            input_cols=columns_map,
-        )
-
-    def generate(self, samples: Dataset, **kwargs: Any) -> Dataset:
-        """Generate dataset with duplicated columns using the new DuplicateColumnsBlock.
-
-        Parameters
-        ----------
-        samples : Dataset
-            The input dataset to duplicate columns from.
-
-        Returns
-        -------
-        Dataset
-            The dataset with additional duplicated columns.
-        """
-        return self._new_block.generate(samples, **kwargs)