sdg-hub 0.2.0__py3-none-any.whl → 0.2.2__py3-none-any.whl

sdg_hub/core/utils/flow_identifier.py

@@ -0,0 +1,94 @@
+# Standard
+from pathlib import Path
+from typing import Dict, List
+import hashlib
+import random
+
+# Third Party
+import yaml
+
+# Cache for loaded word lists to avoid repeated file I/O
+_WORD_CACHE: Dict[str, List[str]] = {}
+
+
+def _load_word_lists() -> Dict[str, List[str]]:
+    """Load word lists from YAML configuration file.
+
+    Returns:
+        Dictionary containing 'adjectives' and 'nouns' lists
+
+    Raises:
+        FileNotFoundError: If the word list file is not found
+        yaml.YAMLError: If the YAML file is malformed
+    """
+    global _WORD_CACHE
+
+    if _WORD_CACHE:
+        return _WORD_CACHE
+
+    # Get path to word list file relative to this module
+    current_dir = Path(__file__).parent
+    words_file = current_dir / "flow_id_words.yaml"
+
+    try:
+        with open(words_file, "r", encoding="utf-8") as f:
+            word_data = yaml.safe_load(f)
+
+        _WORD_CACHE = {
+            "adjectives": word_data["adjectives"],
+            "nouns": word_data["nouns"],
+        }
+
+        return _WORD_CACHE
+
+    except FileNotFoundError:
+        # Fallback to minimal word lists if configuration file is not found
+        _WORD_CACHE = {
+            "adjectives": ["bright", "calm", "fast", "smart", "quick"],
+            "nouns": ["river", "star", "cloud", "moon", "rock"],
+        }
+        return _WORD_CACHE
+    except yaml.YAMLError as e:
+        raise yaml.YAMLError(f"Error parsing word list YAML: {e}")
+    except KeyError as e:
+        raise KeyError(f"Missing required key in word list YAML: {e}")
+
+
+def get_flow_identifier(name: str) -> str:
+    """Generate a deterministic wandb-style flow identifier.
+
+    Creates a human-readable identifier in the format "adjective-noun-number"
+    that is deterministic based on the input name. Same name will always
+    produce the same identifier.
+
+    Args:
+        name: Flow name to generate identifier from
+
+    Returns:
+        A string in the format "adjective-noun-number" (e.g., "bright-river-123")
+
+    Examples:
+        >>> get_flow_identifier("My Document QA Flow")
+        "bright-river-123"
+        >>> get_flow_identifier("My Document QA Flow")  # Same input
+        "bright-river-123"  # Same output
+
+    Raises:
+        FileNotFoundError: If the word list configuration file is not found
+        yaml.YAMLError: If the word list YAML file is malformed
+    """
+    # Load word lists from YAML configuration
+    word_lists = _load_word_lists()
+    adjectives = word_lists["adjectives"]
+    nouns = word_lists["nouns"]
+
+    # Create deterministic seed from name
+    seed_value = int(hashlib.sha256(name.encode()).hexdigest()[:8], 16)
+    rng = random.Random(seed_value)
+
+    # Select words and number deterministically
+    adjective = rng.choice(adjectives)
+    noun = rng.choice(nouns)
+    number = rng.randint(1, 999)
+
+    return f"{adjective}-{noun}-{number}"

sdg_hub/core/utils/yaml_utils.py

@@ -0,0 +1,59 @@
+# SPDX-License-Identifier: Apache-2.0
+"""YAML utilities for flow configuration."""
+
+# Standard
+from pathlib import Path
+from typing import Any, Dict
+
+# Third Party
+import yaml
+
+# Local
+from .logger_config import setup_logger
+
+logger = setup_logger(__name__)
+
+
+def save_flow_yaml(
+    yaml_path: str,
+    flow_config: Dict[str, Any],
+    reason: str = "",
+    sort_keys: bool = False,
+    width: int = 240,
+    indent: int = 2,
+) -> None:
+    """
+    Save flow configuration to a YAML file.
+
+    This utility function saves flow configurations to YAML files,
+    ensuring consistent formatting and logging across the codebase.
+
+    Parameters
+    ----------
+    yaml_path : str
+        Path to the YAML file to write.
+    flow_config : Dict[str, Any]
+        Flow configuration to save.
+    reason : str, optional
+        Reason for saving, used in log message.
+    width : int, optional
+        Maximum line width for YAML output.
+    indent : int, optional
+        Indentation level for YAML output.
+    """
+    yaml_path = str(Path(yaml_path))  # Normalize path
+
+    with open(yaml_path, "w", encoding="utf-8") as f:
+        yaml.dump(
+            flow_config,
+            f,
+            default_flow_style=False,
+            sort_keys=sort_keys,
+            width=width,
+            indent=indent,
+        )
+
+    log_msg = f"Saved flow configuration to YAML: {yaml_path}"
+    if reason:
+        log_msg = f"{log_msg} ({reason})"
+    logger.debug(log_msg)

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

@@ -1,4 +1,5 @@
 metadata:
+  id: small-rock-799
   name: "Advanced Document Grounded Question-Answer Generation Flow for Knowledge Tuning"
   description: "A comprehensive flow that generates high-quality question-answer pairs from input documents using multiple LLM blocks for question generation, answer synthesis, and quality evaluation."
   version: "1.0.0"
@@ -45,7 +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:
@@ -69,7 +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:
@@ -93,7 +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:
@@ -128,7 +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:
@@ -156,7 +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]"]
 
@@ -171,7 +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]"]
 
@@ -186,6 +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-0.2.0.dist-info → sdg_hub-0.2.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sdg_hub
-Version: 0.2.0
+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.
 
 
@@ -121,7 +122,7 @@ uv pip install sdg-hub[examples]
 
 ## 🚀 Quick Start
 
-### 🧱 Core Concepts
+### Core Concepts
 
 **Blocks** are composable units that transform datasets - think of them as data processing Lego pieces. Each block performs a specific task: LLM chat, text parsing, evaluation, or transformation.
 
@@ -136,7 +137,7 @@ dataset → Block₁ → Block₂ → Block₃ → enriched_dataset
 
 #### Flow Discovery
 ```python
-from sdg_hub import FlowRegistry
+from sdg_hub import FlowRegistry, Flow
 
 # Auto-discover all available flows (no setup needed!)
 FlowRegistry.discover_flows()
@@ -150,16 +151,20 @@ qa_flows = FlowRegistry.search_flows(tag="question-generation")
 print(f"QA flows: {qa_flows}")
 ```
 
-#### Using Flows
+Each flow has a **unique, human-readable ID** automatically generated from its name. These IDs provide a convenient shorthand for referencing flows:
+
 ```python
-from sdg_hub import FlowRegistry, Flow
-from datasets import Dataset
+# Every flow gets a deterministic ID 
+# Same flow name always generates the same ID
+flow_id = "small-rock-799" 
 
-# Load the flow by name
-flow_name = "Advanced Document Grounded Question-Answer Generation Flow for Knowledge Tuning"
-flow_path = FlowRegistry.get_flow_path(flow_name)
+# Use ID to reference the flow
+flow_path = FlowRegistry.get_flow_path(flow_id)
 flow = Flow.from_yaml(flow_path)
+```
 
+#### Discovering Models and Configuring them
+```python
 # Discover recommended models
 default_model = flow.get_default_model()
 recommendations = flow.get_model_recommendations()
@@ -171,21 +176,52 @@ flow.set_model_config(
     api_base="http://localhost:8000/v1",
     api_key="your_key",
 )
-
-# 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']
+```
+#### Discover dataset requirements and create your dataset
+```python
+# 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")
+print(f"Output columns: {dry_result['final_dataset']['columns']}")
+
 # Generate high-quality QA pairs
 result = flow.generate(dataset)
 
@@ -196,14 +232,6 @@ faithfulness_scores = result['faithfulness_judgment']
 relevancy_scores = result['relevancy_score']
 ```
 
-#### Quick Testing with Dry Run
-```python
-# Test the flow with a small sample first
-dry_result = flow.dry_run(dataset, sample_size=1)
-print(f"Dry run completed in {dry_result['execution_time_seconds']:.2f}s")
-print(f"Output columns: {dry_result['final_dataset']['columns']}")
-```
-
 
 ## 📄 License
 

{sdg_hub-0.2.0.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=iB5DfB5V6YB5Wo4JmvS-txT42QtmGaWcWp3udRT7zCI,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=a9CcjA5n7JWmfTyeQPml14aW0tlYU9QLkSkskKWJT2o,9771
+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
@@ -13,39 +13,44 @@ 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=qAb-pzbI3EqjOVjU48Y63cR3Oly5ZjCkhdwkk1ltqTc,732
-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/__init__.py,sha256=N6-Prgd4X85oWbMQzhYMrq7OX-NTJm57cghowK-val0,844
+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_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=9n6pHKVmMD1wwEYdFs0kIz5TblmDxl5dtmbyLZHGivo,12005
+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=0sx_chQIeuBcLH1fNMkkD0PxX5UeEv_pCBxYI0Byzi8,36884
-sdg_hub/core/flow/metadata.py,sha256=_IfFWtCukYoMMG2QWRganUl0uGQO_jxniIVBlVmutus,11487
-sdg_hub/core/flow/migration.py,sha256=g0Ug4ZrR_ssxJ-ESVP7ubkD0kql6aSChOuMmx-ZMn8A,7198
-sdg_hub/core/flow/registry.py,sha256=T2veU05h4Q9vb_6F_NYHnNuFZE21orWsx1-iGl0aoJk,9564
-sdg_hub/core/flow/validation.py,sha256=g0G7MH3bz7kcNsfRrlSi8iJZi8gqVcgODhHygVYtJVI,9185
-sdg_hub/core/utils/__init__.py,sha256=y_D7HcRxw7FXShw5USQpCt-5h4VXOFFvMOMN3_oALiw,279
-sdg_hub/core/utils/datautils.py,sha256=qKK2HXAqI4t-O-9RMu2DdaQVZwTnJj-W7-Hc5o1iqZw,379
+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=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
 sdg_hub/core/utils/logger_config.py,sha256=MPYdpyNXh_pxFUOAvSCHa98LGjxjaLXoUoqWekqTG4s,422
 sdg_hub/core/utils/path_resolution.py,sha256=yWof4kGNpQ5dKcrVHg0h9KfOKLZ6ROjdfsLAZsQT5rM,2000
+sdg_hub/core/utils/yaml_utils.py,sha256=tShCd-FFkp0xlKnLe7dXsMOR4AvT9d2qRUmu4ZnPSEY,1458
 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
 sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/instructlab/atomic_facts.yaml,sha256=xgUNY793y4lcpdtuWm5Ah1CmbU2gvvPQCpZMMa6kPXU,2447
@@ -54,10 +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=RrWr2jaandGgLkJiBLFPPA1g6B6vmL98-qXPozqjHKQ,6286
+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-0.2.0.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-sdg_hub-0.2.0.dist-info/METADATA,sha256=APjsGUk94_tQRVlncgVxkEOTSOpHY25SOMmOO1lt0P0,8464
-sdg_hub-0.2.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-sdg_hub-0.2.0.dist-info/top_level.txt,sha256=TqI7d-HE1n6zkXFkU0nF3A1Ct0P0pBaqI675uFokhx4,8
-sdg_hub-0.2.0.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,,