sdg-hub 0.2.1__py3-none-any.whl → 0.2.2__py3-none-any.whl

sdg_hub/core/flow/base.py

@@ -13,18 +13,19 @@ from rich.console import Console
 from rich.panel import Panel
 from rich.table import Table
 from rich.tree import Tree
+import datasets
 import yaml
 
 # Local
 from ..blocks.base import BaseBlock
 from ..blocks.registry import BlockRegistry
-from ..utils.datautils import safe_concatenate_with_validation
+from ..utils.datautils import safe_concatenate_with_validation, validate_no_duplicates
 from ..utils.error_handling import EmptyDatasetError, FlowValidationError
 from ..utils.logger_config import setup_logger
 from ..utils.path_resolution import resolve_path
 from ..utils.yaml_utils import save_flow_yaml
 from .checkpointer import FlowCheckpointer
-from .metadata import FlowMetadata, FlowParameter
+from .metadata import DatasetRequirements, FlowMetadata, FlowParameter
 from .migration import FlowMigration
 from .validation import FlowValidator
 
@@ -306,13 +307,11 @@ class Flow(BaseModel):
 
         # Get block class from registry
         try:
-            block_class = BlockRegistry.get(block_type_name)
+            block_class = BlockRegistry._get(block_type_name)
         except KeyError as exc:
             # Get all available blocks from all categories
-            all_blocks = BlockRegistry.all()
-            available_blocks = ", ".join(
-                [block for blocks in all_blocks.values() for block in blocks]
-            )
+            all_blocks = BlockRegistry.list_blocks()
+            available_blocks = ", ".join(all_blocks)
             raise FlowValidationError(
                 f"Block type '{block_type_name}' not found in registry. "
                 f"Available blocks: {available_blocks}"
@@ -357,6 +356,7 @@ class Flow(BaseModel):
         runtime_params: Optional[dict[str, dict[str, Any]]] = None,
         checkpoint_dir: Optional[str] = None,
         save_freq: Optional[int] = None,
+        max_concurrency: Optional[int] = None,
     ) -> Dataset:
         """Execute the flow blocks in sequence to generate data.
 
@@ -378,6 +378,9 @@ class Flow(BaseModel):
         save_freq : Optional[int], optional
             Number of completed samples after which to save a checkpoint.
             If None, only saves final results when checkpointing is enabled.
+        max_concurrency : Optional[int], optional
+            Maximum number of concurrent requests across all blocks.
+            Controls async request concurrency to prevent overwhelming servers.
 
         Returns
         -------
@@ -397,6 +400,20 @@ class Flow(BaseModel):
                 f"save_freq must be greater than 0, got {save_freq}"
             )
 
+        # Validate max_concurrency parameter
+        if max_concurrency is not None:
+            # Explicitly reject boolean values (bool is a subclass of int in Python)
+            if isinstance(max_concurrency, bool) or not isinstance(
+                max_concurrency, int
+            ):
+                raise FlowValidationError(
+                    f"max_concurrency must be an int, got {type(max_concurrency).__name__}"
+                )
+            if max_concurrency <= 0:
+                raise FlowValidationError(
+                    f"max_concurrency must be greater than 0, got {max_concurrency}"
+                )
+
         # Validate preconditions
         if not self.blocks:
             raise FlowValidationError("Cannot generate with empty flow")
@@ -404,6 +421,8 @@ class Flow(BaseModel):
         if len(dataset) == 0:
             raise EmptyDatasetError("Input dataset is empty")
 
+        validate_no_duplicates(dataset)
+
         # Check if model configuration has been set for flows with LLM blocks
         llm_blocks = self._detect_llm_blocks()
         if llm_blocks and not self._model_config_set:
@@ -420,6 +439,10 @@ class Flow(BaseModel):
                 "Dataset validation failed:\n" + "\n".join(dataset_errors)
             )
 
+        # Log concurrency control if specified
+        if max_concurrency is not None:
+            logger.info(f"Using max_concurrency={max_concurrency} for LLM requests")
+
         # Initialize checkpointer if enabled
         checkpointer = None
         completed_dataset = None
@@ -445,6 +468,7 @@ class Flow(BaseModel):
         logger.info(
             f"Starting flow '{self.metadata.name}' v{self.metadata.version} "
             f"with {len(dataset)} samples across {len(self.blocks)} blocks"
+            + (f" (max_concurrency={max_concurrency})" if max_concurrency else "")
         )
 
         # Merge migrated runtime params with provided ones (provided ones take precedence)
@@ -468,7 +492,7 @@ class Flow(BaseModel):
 
                 # Execute all blocks on this chunk
                 processed_chunk = self._execute_blocks_on_dataset(
-                    chunk_dataset, runtime_params
+                    chunk_dataset, runtime_params, max_concurrency
                 )
                 all_processed.append(processed_chunk)
 
@@ -492,7 +516,9 @@ class Flow(BaseModel):
 
         else:
             # Process entire dataset at once
-            final_dataset = self._execute_blocks_on_dataset(dataset, runtime_params)
+            final_dataset = self._execute_blocks_on_dataset(
+                dataset, runtime_params, max_concurrency
+            )
 
             # Save final checkpoint if checkpointing enabled
             if checkpointer:
@@ -515,7 +541,10 @@ class Flow(BaseModel):
         return final_dataset
 
     def _execute_blocks_on_dataset(
-        self, dataset: Dataset, runtime_params: dict[str, dict[str, Any]]
+        self,
+        dataset: Dataset,
+        runtime_params: dict[str, dict[str, Any]],
+        max_concurrency: Optional[int] = None,
     ) -> Dataset:
         """Execute all blocks in sequence on the given dataset.
 
@@ -525,6 +554,8 @@ class Flow(BaseModel):
             Dataset to process through all blocks.
         runtime_params : Dict[str, Dict[str, Any]]
             Runtime parameters for block execution.
+        max_concurrency : Optional[int], optional
+            Maximum concurrency for LLM requests across blocks.
 
         Returns
         -------
@@ -543,6 +574,10 @@ class Flow(BaseModel):
             # Prepare block execution parameters
             block_kwargs = self._prepare_block_kwargs(block, runtime_params)
 
+            # Add max_concurrency to block kwargs if provided
+            if max_concurrency is not None:
+                block_kwargs["_flow_max_concurrency"] = max_concurrency
+
             try:
                 # Check if this is a deprecated block and skip validations
                 is_deprecated_block = (
@@ -899,6 +934,8 @@ class Flow(BaseModel):
         if len(dataset) == 0:
             raise EmptyDatasetError("Input dataset is empty")
 
+        validate_no_duplicates(dataset)
+
         # Use smaller sample size if dataset is smaller
         actual_sample_size = min(sample_size, len(dataset))
 
@@ -1066,6 +1103,90 @@ class Flow(BaseModel):
             "block_names": [block.block_name for block in self.blocks],
         }
 
+    def get_dataset_requirements(self) -> Optional[DatasetRequirements]:
+        """Get the dataset requirements for this flow.
+
+        Returns
+        -------
+        Optional[DatasetRequirements]
+            Dataset requirements object or None if not defined.
+
+        Examples
+        --------
+        >>> flow = Flow.from_yaml("path/to/flow.yaml")
+        >>> requirements = flow.get_dataset_requirements()
+        >>> if requirements:
+        ...     print(f"Required columns: {requirements.required_columns}")
+        """
+        return self.metadata.dataset_requirements
+
+    def get_dataset_schema(self) -> Dataset:
+        """Get an empty dataset with the correct schema for this flow.
+
+        Returns
+        -------
+        Dataset
+            Empty HuggingFace Dataset with the correct schema/features for this flow.
+            Users can add data to this dataset or use it to validate their own dataset schema.
+
+        Examples
+        --------
+        >>> flow = Flow.from_yaml("path/to/flow.yaml")
+        >>> schema_dataset = flow.get_dataset_schema()
+        >>>
+        >>> # Add your data
+        >>> schema_dataset = schema_dataset.add_item({
+        ...     "document": "Your document text",
+        ...     "domain": "Computer Science",
+        ...     "icl_document": "Example document"
+        ... })
+        >>>
+        >>> # Or validate your existing dataset schema
+        >>> my_dataset = Dataset.from_dict(my_data)
+        >>> if my_dataset.features == schema_dataset.features:
+        ...     print("Schema matches!")
+        """
+
+        requirements = self.get_dataset_requirements()
+
+        if requirements is None:
+            # Return empty dataset with no schema requirements
+            return Dataset.from_dict({})
+
+        # Build schema features
+        schema_features = {}
+
+        # Process required columns
+        for col_name in requirements.required_columns:
+            col_type = requirements.column_types.get(col_name, "string")
+            schema_features[col_name] = self._map_column_type_to_feature(col_type)
+
+        # Process optional columns
+        for col_name in requirements.optional_columns:
+            col_type = requirements.column_types.get(col_name, "string")
+            schema_features[col_name] = self._map_column_type_to_feature(col_type)
+
+        # Create empty dataset with the correct features
+        features = datasets.Features(schema_features)
+        empty_data = {col_name: [] for col_name in schema_features.keys()}
+
+        return Dataset.from_dict(empty_data, features=features)
+
+    def _map_column_type_to_feature(self, col_type: str):
+        """Map column type string to HuggingFace feature type."""
+        # Map common type names to HuggingFace types
+        if col_type in ["str", "string", "text"]:
+            return datasets.Value("string")
+        elif col_type in ["int", "integer"]:
+            return datasets.Value("int64")
+        elif col_type in ["float", "number"]:
+            return datasets.Value("float64")
+        elif col_type in ["bool", "boolean"]:
+            return datasets.Value("bool")
+        else:
+            # Default to string for unknown types
+            return datasets.Value("string")
+
     def print_info(self) -> None:
         """
         Print an interactive summary of the Flow in the console.

sdg_hub/core/utils/datautils.py

@@ -15,6 +15,35 @@ def safe_concatenate_datasets(datasets: list):
     return concatenate_datasets(filtered_datasets)
 
 
+def validate_no_duplicates(dataset: Dataset) -> None:
+    """
+    Validate that the input dataset contains only unique rows.
+
+    Uses pandas `.duplicated()` for efficient duplicate detection.
+    Raises FlowValidationError if duplicates are found, including a count
+    of the duplicate rows detected.
+
+    Parameters
+    ----------
+    dataset : Dataset
+        Input dataset to validate.
+
+    Raises
+    ------
+    FlowValidationError
+        If duplicate rows are detected in the dataset.
+    """
+    df = dataset.to_pandas()
+    duplicate_count = int(df.duplicated(keep="first").sum())
+
+    if duplicate_count > 0:
+        raise FlowValidationError(
+            f"Input dataset contains {duplicate_count} duplicate rows. "
+            f"SDG Hub operations require unique input rows. "
+            f"Please deduplicate your dataset before processing."
+        )
+
+
 def safe_concatenate_with_validation(
     datasets: list, context: str = "datasets"
 ) -> Dataset:

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

@@ -46,7 +46,6 @@ blocks:
       input_cols: [document, document_outline]
       output_cols: summary_prompt
       prompt_config_path: detailed_summary.yaml
-      format_as_messages: true
 
   - block_type: LLMChatBlock
     block_config:
@@ -70,7 +69,6 @@ blocks:
       input_cols: [document, document_outline, domain]
       output_cols: atomic_facts_prompt
       prompt_config_path: atomic_facts.yaml
-      format_as_messages: true
 
   - block_type: LLMChatBlock
     block_config:
@@ -94,7 +92,6 @@ blocks:
       input_cols: [document, document_outline]
       output_cols: extractive_summary_prompt
       prompt_config_path: extractive_summary.yaml
-      format_as_messages: true
 
   - block_type: LLMChatBlock
     block_config:
@@ -129,7 +126,6 @@ blocks:
       input_cols: [domain, document, document_outline, icl_document, icl_query_1, icl_response_1, icl_query_2, icl_response_2, icl_query_3, icl_response_3]
       output_cols: knowledge_generation_prompt
       prompt_config_path: generate_questions_responses.yaml
-      format_as_messages: true
 
   - block_type: LLMChatBlock
     block_config:
@@ -157,7 +153,6 @@ blocks:
       filter_value: "YES"
       operation: eq
       async_mode: true
-      format_as_messages: true
       start_tags: ["[Start of Explanation]", "[Start of Answer]"]
       end_tags: ["[End of Explanation]", "[End of Answer]"]
 
@@ -172,7 +167,6 @@ blocks:
       convert_dtype: float
       max_tokens: 2048
       async_mode: true
-      format_as_messages: true
       start_tags: ["[Start of Feedback]", "[Start of Score]"]
       end_tags: ["[End of Feedback]", "[End of Score]"]
 
@@ -187,6 +181,5 @@ blocks:
       convert_dtype: float
       max_tokens: 2048
       async_mode: true
-      format_as_messages: true
       start_tags: ["[Start of Explanation]", "[Start of Rating]"]
       end_tags: ["[End of Explanation]", "[End of Rating]"]

{sdg_hub-0.2.1.dist-info → sdg_hub-0.2.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sdg_hub
-Version: 0.2.1
+Version: 0.2.2
 Summary: Synthetic Data Generation
 Author-email: Red Hat AI Innovation <abhandwa@redhat.com>
 License: Apache-2.0
@@ -27,7 +27,6 @@ Requires-Dist: datasets<4.0.0,>=2.18.0
 Requires-Dist: httpx<1.0.0,>=0.25.0
 Requires-Dist: jinja2
 Requires-Dist: litellm<1.75.0,>=1.73.0
-Requires-Dist: openai<2.0.0,>=1.13.3
 Requires-Dist: rich
 Requires-Dist: pydantic<3.0.0,>=2.0.0
 Requires-Dist: python-dotenv<2.0.0,>=1.0.0
@@ -92,6 +91,8 @@ A modular Python framework for building synthetic data generation pipelines usin
 
 **📊 Rich Monitoring** - Detailed logging with progress bars and execution summaries.
 
+**📋 Dataset Schema Discovery** - Instantly discover required data formats. Get empty datasets with correct schema for easy validation and data preparation.
+
 **🧩 Easily Extensible** - Create custom blocks with simple inheritance. Rich logging and monitoring built-in.
 
 
@@ -176,22 +177,46 @@ flow.set_model_config(
     api_key="your_key",
 )
 ```
-#### Load your dataset and run the flow
+#### Discover dataset requirements and create your dataset
 ```python
-# Create your dataset with required columns
-dataset = Dataset.from_dict({
-    'document': ['Your document text here...'],
-    'document_outline': ['1. Topic A; 2. Topic B; 3. Topic C'],
-    'domain': ['Computer Science'],
-    'icl_document': ['Example document for in-context learning...'],
-    'icl_query_1': ['Example question 1?'],
-    'icl_response_1': ['Example answer 1'],
-    'icl_query_2': ['Example question 2?'], 
-    'icl_response_2': ['Example answer 2'],
-    'icl_query_3': ['Example question 3?'],
-    'icl_response_3': ['Example answer 3']
+# First, discover what data the flow needs
+# Get an empty dataset with the exact schema needed
+schema_dataset = flow.get_dataset_schema()  # Get empty dataset with correct schema
+print(f"Required columns: {schema_dataset.column_names}")
+print(f"Schema: {schema_dataset.features}")
+
+# Option 1: Add data directly to the schema dataset
+dataset = schema_dataset.add_item({
+    'document': 'Your document text here...',
+    'document_outline': '1. Topic A; 2. Topic B; 3. Topic C',
+    'domain': 'Computer Science',
+    'icl_document': 'Example document for in-context learning...',
+    'icl_query_1': 'Example question 1?',
+    'icl_response_1': 'Example answer 1',
+    'icl_query_2': 'Example question 2?', 
+    'icl_response_2': 'Example answer 2',
+    'icl_query_3': 'Example question 3?',
+    'icl_response_3': 'Example answer 3'
 })
 
+# Option 2: Create your own dataset and validate the schema
+my_dataset = Dataset.from_dict(my_data_dict)
+if my_dataset.features == schema_dataset.features:
+    print("✅ Schema matches - ready to generate!")
+    dataset = my_dataset
+else:
+    print("❌ Schema mismatch - check your columns")
+
+# Option 3: Get raw requirements for detailed inspection
+requirements = flow.get_dataset_requirements()
+if requirements:
+    print(f"Required: {requirements.required_columns}")
+    print(f"Optional: {requirements.optional_columns}")
+    print(f"Min samples: {requirements.min_samples}")
+```
+
+#### Dry Run and Generate
+```python
 # Quick Testing with Dry Run
 dry_result = flow.dry_run(dataset, sample_size=1)
 print(f"Dry run completed in {dry_result['execution_time_seconds']:.2f}s")

{sdg_hub-0.2.1.dist-info → sdg_hub-0.2.2.dist-info}/RECORD

@@ -1,10 +1,10 @@
 sdg_hub/__init__.py,sha256=Tw-6R5a8_W1kJcTAsW3R9ltBDP1dy5-fe7Tvt3cSyCQ,550
-sdg_hub/_version.py,sha256=UoNvMtd4wCG76RwoSpNCUtaFyTwakGcZolfjXzNVSMY,511
+sdg_hub/_version.py,sha256=o3ZTescp-19Z9cvBGq9dQnbppljgzdUYUf98Nov0spY,704
 sdg_hub/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sdg_hub/core/__init__.py,sha256=NwqB4fwhC29W50VW7QXZssLxx122YvgO9LHDLdgAnrI,496
 sdg_hub/core/blocks/__init__.py,sha256=9sCkCvDQzJGSedaePVlEIpbNwrkBz_K500VW_6FLhuE,1601
 sdg_hub/core/blocks/base.py,sha256=TrzUAkG7Tiquk0Z3SOFsb5mRnHd1IbHH6gFPVH1P7T8,10424
-sdg_hub/core/blocks/registry.py,sha256=U__75QrxFpRaJlt36mOd26dgOqBeePs-ZX0Rnutp6r0,9782
+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
@@ -13,38 +13,38 @@ sdg_hub/core/blocks/deprecated_blocks/flatten_columns.py,sha256=IenCskrPEv09h2uT
 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=ABcXZrqEMsgKfdGAkSo2plMp4LsZSqPhEQugoDEYm1I,2950
+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/evaluation/__init__.py,sha256=kFXee-vsVVdU2XtLio9qHgPx_a0zoB_rQr509EKBGJc,357
-sdg_hub/core/blocks/evaluation/evaluate_faithfulness_block.py,sha256=ZuQ8jq2JwTdslUJtFi1E9NXebCWFZS8isXOafcJ_CMU,23026
-sdg_hub/core/blocks/evaluation/evaluate_relevancy_block.py,sha256=ieQRwl4bx5EQ3m7Wa2P3pHLUPQY7HuwNWjHUCo98u6g,22832
-sdg_hub/core/blocks/evaluation/verify_question_block.py,sha256=fSNbW1KpdfVE0fQsm4Y8QfVk6A3J5H3C0dtGn49t8tM,22853
+sdg_hub/core/blocks/evaluation/evaluate_faithfulness_block.py,sha256=vFi3YIxVPNnzgdenIeAl7yUb4OOUY_uUOXS-pWLsDmw,12223
+sdg_hub/core/blocks/evaluation/evaluate_relevancy_block.py,sha256=NXT1lixR-JnOXNlBCbMjULcpu4kh2SthhwCWEobiBt0,12115
+sdg_hub/core/blocks/evaluation/verify_question_block.py,sha256=LKoIHdxUuTVO24n_M9cAliEj56uEe2kQAecKTRz65zI,12465
 sdg_hub/core/blocks/filtering/__init__.py,sha256=isxSVSvDqkMjG8dQSl3Q2M4g5c1t9fTjBSA21icf-yA,275
 sdg_hub/core/blocks/filtering/column_value_filter.py,sha256=H8Gif0q9Wc_d1TnVow8Zpsg7blJOFGN1EZmV6OPpkcg,5971
 sdg_hub/core/blocks/llm/__init__.py,sha256=N6-Prgd4X85oWbMQzhYMrq7OX-NTJm57cghowK-val0,844
-sdg_hub/core/blocks/llm/client_manager.py,sha256=vaoPoTITJ9IlooeVRfu6M4WBc08mp4aJZ5tvnl2fMv8,12309
-sdg_hub/core/blocks/llm/config.py,sha256=TmbfqxPHH3mShTK2EuCX2AGKtDvl0aSvihsaqgzABtM,11266
+sdg_hub/core/blocks/llm/client_manager.py,sha256=PDf07t2s68WQaoU-LTRke6nQUDWDKwiV4ptAT7Cbn18,14047
+sdg_hub/core/blocks/llm/config.py,sha256=gc4xp5D20MSlKMFEos0QAaKUwgbZpBtMGXmn6LsIk78,11289
 sdg_hub/core/blocks/llm/error_handler.py,sha256=7T-019ZFB9qgZoX1ybIiXyaLjPzrF96qcKmUu6vmO6g,12178
-sdg_hub/core/blocks/llm/llm_chat_block.py,sha256=3o2oV_ecWsEHFp5FWPIpBT-yJ1imJmeZy2b9GZL-T54,20121
-sdg_hub/core/blocks/llm/llm_chat_with_parsing_retry_block.py,sha256=mMmifTC-sRUhdxuLRRtAMhQC7r7NOyTAfBx-xTzLzTc,19669
+sdg_hub/core/blocks/llm/llm_chat_block.py,sha256=J-iDJTY-txuduFXx-NUhyohWpRnEaYIg4f0VsSgpjVw,22641
+sdg_hub/core/blocks/llm/llm_chat_with_parsing_retry_block.py,sha256=H7LqYpEiFO1g2cxncAl4vkLhQxAYgGpV6cUyQTSG03k,27628
 sdg_hub/core/blocks/llm/prompt_builder_block.py,sha256=fkJd718X1oYlMY1cjo_8WCO16Gl8Tm0bUPWR78E_uws,13935
-sdg_hub/core/blocks/llm/text_parser_block.py,sha256=vQgUaeYJI9HuxDPRjII-NIOsR01JA-sBBGl05623L8I,14391
+sdg_hub/core/blocks/llm/text_parser_block.py,sha256=uYcof6cy1tgMG_mHpFBW4xhVXg40rNhTerM5EqAvcEo,14187
 sdg_hub/core/blocks/transform/__init__.py,sha256=Y_3izPCtgnMbFK-gBMeLHZspSrNLgbGheAJXU57XfFw,746
 sdg_hub/core/blocks/transform/duplicate_columns.py,sha256=SaP7rIF4ZFEFFa50aU2xGNIuddXaEZrKxdWfHjzFpVI,2833
-sdg_hub/core/blocks/transform/index_based_mapper.py,sha256=mGup5agvDf9kAFSvXE5X6Puo6CQc9UOdFdbhdFWJjwk,8225
+sdg_hub/core/blocks/transform/index_based_mapper.py,sha256=XC_a7Skbd3mu7f4ra8fGWPxMwqUMSjJkQ7Ag7vflwJA,8235
 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/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=N2NZGngvd7qpT5FI_knKukUFM0IkD9K5jdTi-gDeUI4,475
-sdg_hub/core/flow/base.py,sha256=Jm90xQ1ns0ArEiqkceSME6phzBtkw6nthjSJNTU3IkQ,45530
+sdg_hub/core/flow/base.py,sha256=eneLS9GR21q9nK3M8qZzIyJ-OeFF2Lp6ZwzQjBVnbyk,50364
 sdg_hub/core/flow/checkpointer.py,sha256=stm5ZtjjEiLk9ZkAAnoQQn5Y8Yl_d7qCsQLZTrCXR48,11867
 sdg_hub/core/flow/metadata.py,sha256=h9jpvAzWsF5n4ztZMzwa9ZNgnzKTHmFWdn7YbyJLHCw,12977
 sdg_hub/core/flow/migration.py,sha256=6and-RBqV0t2gRipr1GiOOVnyBJdtyyjw1kO08Z--d4,7558
 sdg_hub/core/flow/registry.py,sha256=DzCqEEgwhvwnCBAGLogoMVdwXh4pCHrxOWqoxam7O8I,12162
 sdg_hub/core/flow/validation.py,sha256=pUJvgaUjLpKNwvW6djcqVOF-HShOjegEmGOnUnoX4BA,9722
 sdg_hub/core/utils/__init__.py,sha256=C2FzLn3dHprwGJDEgI4fyFS3aoCJR-9PhHsunxropJ8,351
-sdg_hub/core/utils/datautils.py,sha256=QnzMl7nOp0crNJEWgAqurOuuAyz0SnvAjLiKzvG0uds,1933
+sdg_hub/core/utils/datautils.py,sha256=vvZSNZ94vMQMh9Bs99X92UPwSNzyyYwO3V4w3O3QYoA,2801
 sdg_hub/core/utils/error_handling.py,sha256=yku8cGj_nKCyXDsnb-mHCpgukkkAMucJ4iAUrIzqysc,5510
 sdg_hub/core/utils/flow_id_words.yaml,sha256=5QHpQdP7zwahRuooyAlJIwBY7WcDR7vtbJXxVJqujbg,2317
 sdg_hub/core/utils/flow_identifier.py,sha256=aAHfK_G9AwEtMglLRMdMpi_AI1dciub5UqBGm4yb2HE,2841
@@ -59,10 +59,10 @@ 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=Rrl9eve9QsGLojAkflgKTHyUgUawKfvhEVAnAxBLZJ8,6307
+sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/instructlab/flow.yaml,sha256=oyrLRjEnmioMa_G_sd9yQK_nBt4arwWV5fvKgzYE2ds,6090
 sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/instructlab/generate_questions_responses.yaml,sha256=yX8aLY8dJSDML9ZJhnj9RzPbN8tH2xfcM4Gc6xZuwqQ,2596
-sdg_hub-0.2.1.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-sdg_hub-0.2.1.dist-info/METADATA,sha256=0Si2PZotpwtUI2Pg2cc3uSZIJtS12jF4VInJSTyBngA,8606
-sdg_hub-0.2.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-sdg_hub-0.2.1.dist-info/top_level.txt,sha256=TqI7d-HE1n6zkXFkU0nF3A1Ct0P0pBaqI675uFokhx4,8
-sdg_hub-0.2.1.dist-info/RECORD,,
+sdg_hub-0.2.2.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+sdg_hub-0.2.2.dist-info/METADATA,sha256=OHIiUh4AqSHVW-asGQdUp67TXL_dCRV7NVC0E14IwM0,9647
+sdg_hub-0.2.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+sdg_hub-0.2.2.dist-info/top_level.txt,sha256=TqI7d-HE1n6zkXFkU0nF3A1Ct0P0pBaqI675uFokhx4,8
+sdg_hub-0.2.2.dist-info/RECORD,,