sdg-hub 0.7.2__py3-none-any.whl → 0.7.3__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 = '0.7.2'
-__version_tuple__ = version_tuple = (0, 7, 2)
+__version__ = version = '0.7.3'
+__version_tuple__ = version_tuple = (0, 7, 3)
 
 __commit_id__ = commit_id = None

sdg_hub/core/blocks/__init__.py

@@ -6,7 +6,13 @@ This package provides various block implementations for data generation, process
 # Local
 from .base import BaseBlock
 from .filtering import ColumnValueFilterBlock
-from .llm import LLMChatBlock, LLMParserBlock, PromptBuilderBlock, TextParserBlock
+from .llm import (
+    LLMChatBlock,
+    LLMParserBlock,
+    LLMResponseExtractorBlock,
+    PromptBuilderBlock,
+    TextParserBlock,
+)
 from .registry import BlockRegistry
 from .transform import (
     DuplicateColumnsBlock,
@@ -28,7 +34,8 @@ __all__ = [
     "TextConcatBlock",
     "UniformColumnValueSetter",
     "LLMChatBlock",
-    "LLMParserBlock",
+    "LLMParserBlock",  # Deprecated alias for LLMResponseExtractorBlock
+    "LLMResponseExtractorBlock",
     "TextParserBlock",
     "PromptBuilderBlock",
 ]

sdg_hub/core/blocks/base.py

@@ -49,6 +49,9 @@ class BaseBlock(BaseModel, ABC):
     block_name: str = Field(
         ..., description="Unique identifier for this block instance"
     )
+    block_type: Optional[str] = Field(
+        None, description="Block type (e.g., 'llm', 'transform', 'parser', 'filtering')"
+    )
     input_cols: Union[str, list[str], dict[str, Any], None] = Field(
         None, description="Input columns: str, list, or dict"
     )
@@ -366,5 +369,5 @@ class BaseBlock(BaseModel, ABC):
         Dict[str, Any]
         """
         config = self.get_config()
-        config["block_type"] = self.__class__.__name__
+        config["block_class"] = self.__class__.__name__
         return config

sdg_hub/core/blocks/filtering/column_value_filter.py

@@ -46,6 +46,8 @@ DTYPE_MAP = {
     "Filters datasets based on column values using various comparison operations",
 )
 class ColumnValueFilterBlock(BaseBlock):
+    block_type: str = "filtering"
+
     """A block for filtering datasets based on column values.
 
     This block allows filtering of datasets using various operations (e.g., equals, contains)

sdg_hub/core/blocks/llm/__init__.py

@@ -9,7 +9,7 @@ local models (vLLM, Ollama), and more.
 # Local
 from .error_handler import ErrorCategory, LLMErrorHandler
 from .llm_chat_block import LLMChatBlock
-from .llm_parser_block import LLMParserBlock
+from .llm_response_extractor_block import LLMParserBlock, LLMResponseExtractorBlock
 from .prompt_builder_block import PromptBuilderBlock
 from .text_parser_block import TextParserBlock
 
@@ -17,7 +17,8 @@ __all__ = [
     "LLMErrorHandler",
     "ErrorCategory",
     "LLMChatBlock",
-    "LLMParserBlock",
+    "LLMParserBlock",  # Deprecated alias for LLMResponseExtractorBlock
+    "LLMResponseExtractorBlock",
     "PromptBuilderBlock",
     "TextParserBlock",
 ]

sdg_hub/core/blocks/llm/llm_chat_block.py

@@ -32,6 +32,8 @@ logger = setup_logger(__name__)
 class LLMChatBlock(BaseBlock):
     model_config = ConfigDict(extra="allow")
 
+    block_type: str = "llm"
+
     """Unified LLM chat block supporting all providers via LiteLLM.
 
     This block provides a minimal wrapper around LiteLLM's completion API,

sdg_hub/core/blocks/llm/{llm_parser_block.py → llm_response_extractor_block.py}

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: Apache-2.0
-"""LLM parser block for extracting fields from LLM response objects.
+"""LLM response extractor block for extracting fields from LLM response objects.
 
-This module provides the LLMParserBlock for extracting specific fields
+This module provides the LLMResponseExtractorBlock for extracting specific fields
 (content, reasoning_content, tool_calls) from chat completion response objects.
 """
 
@@ -22,13 +22,15 @@ logger = setup_logger(__name__)
 
 
 @BlockRegistry.register(
-    "LLMParserBlock",
+    "LLMResponseExtractorBlock",
     "llm",
     "Extracts specified fields from LLM response objects",
 )
-class LLMParserBlock(BaseBlock):
+class LLMResponseExtractorBlock(BaseBlock):
     _flow_requires_jsonl_tmp: bool = True
 
+    block_type: str = "llm_util"
+
     """Block for extracting fields from LLM response objects.
 
     This block extracts specified fields from chat completion response objects.
@@ -88,7 +90,7 @@ class LLMParserBlock(BaseBlock):
             ]
         ):
             raise ValueError(
-                "LLMParserBlock requires at least one extraction field to be enabled: "
+                "LLMResponseExtractorBlock requires at least one extraction field to be enabled: "
                 "extract_content, extract_reasoning_content, or extract_tool_calls"
             )
 
@@ -106,7 +108,7 @@ class LLMParserBlock(BaseBlock):
         return self
 
     def _validate_custom(self, dataset: pd.DataFrame) -> None:
-        """Validate LLMParserBlock specific requirements.
+        """Validate LLMResponseExtractorBlock specific requirements.
 
         Parameters
         ----------
@@ -116,14 +118,16 @@ class LLMParserBlock(BaseBlock):
         Raises
         ------
         ValueError
-            If LLMParserBlock requirements are not met.
+            If LLMResponseExtractorBlock requirements are not met.
         """
         # Validate that we have exactly one input column
         if len(self.input_cols) == 0:
-            raise ValueError("LLMParserBlock expects at least one input column")
+            raise ValueError(
+                "LLMResponseExtractorBlock expects at least one input column"
+            )
         if len(self.input_cols) > 1:
             logger.warning(
-                f"LLMParserBlock expects exactly one input column, but got {len(self.input_cols)}. "
+                f"LLMResponseExtractorBlock expects exactly one input column, but got {len(self.input_cols)}. "
                 f"Using the first column: {self.input_cols[0]}"
             )
 
@@ -324,3 +328,22 @@ class LLMParserBlock(BaseBlock):
             new_data.extend(self._generate(sample))
 
         return pd.DataFrame(new_data)
+
+
+# Backwards compatibility alias (deprecated)
+# Register deprecated alias in BlockRegistry so old YAML flows still work
+@BlockRegistry.register(
+    "LLMParserBlock",
+    "llm",
+    "Deprecated: Use LLMResponseExtractorBlock instead",
+    deprecated=True,
+    replacement="LLMResponseExtractorBlock",
+)
+class LLMParserBlock(LLMResponseExtractorBlock):
+    """Deprecated alias for LLMResponseExtractorBlock.
+
+    This class exists for backwards compatibility with existing code and YAML flows.
+    Use LLMResponseExtractorBlock instead.
+    """
+
+    pass

sdg_hub/core/blocks/llm/prompt_builder_block.py

@@ -222,6 +222,8 @@ class PromptRenderer:
     "Formats prompts into structured chat messages or plain text using Jinja templates",
 )
 class PromptBuilderBlock(BaseBlock):
+    block_type: str = "llm_util"
+
     """Block for formatting prompts into structured chat messages or plain text.
 
     This block takes input from dataset columns, applies Jinja templates from a YAML config

sdg_hub/core/blocks/llm/text_parser_block.py

@@ -30,6 +30,8 @@ logger = setup_logger(__name__)
 class TextParserBlock(BaseBlock):
     _flow_requires_jsonl_tmp: bool = True
 
+    block_type: str = "parser"
+
     """Block for parsing and post-processing text content.
 
     This block handles text parsing using start/end tags, custom regex patterns,

sdg_hub/core/blocks/transform/duplicate_columns.py

@@ -27,6 +27,8 @@ logger = setup_logger(__name__)
     "Duplicates existing columns with new names according to a mapping specification",
 )
 class DuplicateColumnsBlock(BaseBlock):
+    block_type: str = "transform"
+
     """Block for duplicating existing columns with new names.
 
     This block creates copies of existing columns with new names according to a mapping specification.

sdg_hub/core/blocks/transform/index_based_mapper.py

@@ -28,6 +28,8 @@ logger = setup_logger(__name__)
     "Maps values from source columns to output columns based on choice columns using shared mapping",
 )
 class IndexBasedMapperBlock(BaseBlock):
+    block_type: str = "transform"
+
     """Block for mapping values from source columns to output columns based on choice columns.
 
     This block uses a shared mapping dictionary to select values from source columns and

sdg_hub/core/blocks/transform/json_structure_block.py

@@ -28,6 +28,8 @@ logger = setup_logger(__name__)
     "Combines multiple columns into a single column containing a structured JSON object",
 )
 class JSONStructureBlock(BaseBlock):
+    block_type: str = "transform"
+
     """Block for combining multiple columns into a structured JSON object.
 
     This block takes values from multiple input columns and combines them into a single

sdg_hub/core/blocks/transform/melt_columns.py

@@ -28,6 +28,8 @@ logger = setup_logger(__name__)
     "Transforms wide dataset format into long format by melting columns into rows",
 )
 class MeltColumnsBlock(BaseBlock):
+    block_type: str = "transform"
+
     """Block for flattening multiple columns into a long format.
 
     This block transforms a wide dataset format into a long format by melting

sdg_hub/core/blocks/transform/rename_columns.py

@@ -27,6 +27,8 @@ logger = setup_logger(__name__)
     "Renames columns in a dataset according to a mapping specification",
 )
 class RenameColumnsBlock(BaseBlock):
+    block_type: str = "transform"
+
     """Block for renaming columns in a dataset.
 
     This block renames columns in a dataset according to a mapping specification.

sdg_hub/core/blocks/transform/text_concat.py

@@ -27,6 +27,8 @@ logger = setup_logger(__name__)
     "Combines multiple columns into a single column using a specified separator",
 )
 class TextConcatBlock(BaseBlock):
+    block_type: str = "transform"
+
     """Block for combining multiple columns into a single column.
 
     This block concatenates values from multiple columns into a single output column,

sdg_hub/core/blocks/transform/uniform_col_val_setter.py

@@ -28,6 +28,8 @@ logger = setup_logger(__name__)
     "Replaces all values in a column with a single summary statistic (e.g., mode, mean, median)",
 )
 class UniformColumnValueSetter(BaseBlock):
+    block_type: str = "transform"
+
     """Block that replaces all values in a column with a single aggregate value.
 
     Supported strategies include: mode, min, max, mean, median.

sdg_hub/core/flow/base.py

@@ -679,7 +679,7 @@ class Flow(BaseModel):
                 self._block_metrics.append(
                     {
                         "block_name": block.block_name,
-                        "block_type": block.__class__.__name__,
+                        "block_class": block.__class__.__name__,
                         "execution_time": execution_time,
                         "input_rows": input_rows,
                         "output_rows": output_rows,
@@ -701,7 +701,7 @@ class Flow(BaseModel):
                 self._block_metrics.append(
                     {
                         "block_name": block.block_name,
-                        "block_type": block.__class__.__name__,
+                        "block_class": block.__class__.__name__,
                         "execution_time": execution_time,
                         "input_rows": input_rows,
                         "output_rows": 0,
@@ -882,38 +882,14 @@ class Flow(BaseModel):
             )
 
     def _detect_llm_blocks(self) -> list[str]:
-        """Detect LLM blocks in the flow by checking for model-related attribute existence.
-
-        LLM blocks are identified by having model, api_base, or api_key attributes,
-        regardless of their values (they may be None until set_model_config() is called).
+        """Detect blocks with block_type='llm'.
 
         Returns
         -------
         List[str]
-            List of block names that have LLM-related attributes.
+            List of block names that are LLM blocks.
         """
-        llm_blocks = []
-
-        for block in self.blocks:
-            block_type = block.__class__.__name__
-            block_name = block.block_name
-
-            # Check by attribute existence (not value) - LLM blocks have these attributes even if None
-            has_model_attr = hasattr(block, "model")
-            has_api_base_attr = hasattr(block, "api_base")
-            has_api_key_attr = hasattr(block, "api_key")
-
-            # A block is considered an LLM block if it has any LLM-related attributes
-            is_llm_block = has_model_attr or has_api_base_attr or has_api_key_attr
-
-            if is_llm_block:
-                llm_blocks.append(block_name)
-                logger.debug(
-                    f"Detected LLM block '{block_name}' ({block_type}): "
-                    f"has_model_attr={has_model_attr}, has_api_base_attr={has_api_base_attr}, has_api_key_attr={has_api_key_attr}"
-                )
-
-        return llm_blocks
+        return [block.block_name for block in self.blocks if block.block_type == "llm"]
 
     def is_model_config_required(self) -> bool:
         """Check if model configuration is required for this flow.
@@ -1152,7 +1128,7 @@ class Flow(BaseModel):
                 # Record block execution info
                 block_info = {
                     "block_name": block.block_name,
-                    "block_type": block.__class__.__name__,
+                    "block_class": block.__class__.__name__,
                     "execution_time_seconds": block_execution_time,
                     "input_rows": input_rows,
                     "output_rows": len(current_dataset),
@@ -1341,7 +1317,7 @@ class Flow(BaseModel):
             "metadata": self.metadata.model_dump(),
             "blocks": [
                 {
-                    "block_type": block.__class__.__name__,
+                    "block_class": block.__class__.__name__,
                     "block_name": block.block_name,
                     "input_cols": getattr(block, "input_cols", None),
                     "output_cols": getattr(block, "output_cols", None),

sdg_hub/core/utils/flow_metrics.py

@@ -31,12 +31,12 @@ def aggregate_block_metrics(entries: list[dict[str, Any]]) -> list[dict[str, Any
     """
     agg: dict[tuple[str, str], dict[str, Any]] = {}
     for m in entries:
-        key = (m.get("block_name"), m.get("block_type"))
+        key = (m.get("block_name"), m.get("block_class"))
         a = agg.setdefault(
             key,
             {
                 "block_name": key[0],
-                "block_type": key[1],
+                "block_class": key[1],
                 "execution_time": 0.0,
                 "input_rows": 0,
                 "output_rows": 0,
@@ -138,7 +138,7 @@ def display_metrics_summary(
 
         table.add_row(
             metrics["block_name"],
-            metrics["block_type"],
+            metrics["block_class"],
             duration,
             row_change,
             col_change,

sdg_hub/flows/evaluation/rag/flow.yaml

@@ -41,7 +41,7 @@ blocks:
       max_tokens: 2048
       temperature: 0.7
 
-  - block_type: LLMParserBlock
+  - block_type: LLMResponseExtractorBlock
     block_config:
       block_name: parse_topic
       input_cols: topic_response
@@ -73,7 +73,7 @@ blocks:
       max_tokens: 2048
       temperature: 0.7
 
-  - block_type: LLMParserBlock
+  - block_type: LLMResponseExtractorBlock
     block_config:
       block_name: parse_question
       input_cols: question_response
@@ -97,7 +97,7 @@ blocks:
       max_tokens: 4096
       temperature: 0.7
 
-  - block_type: LLMParserBlock
+  - block_type: LLMResponseExtractorBlock
     block_config:
       block_name: parse_evolved_question
       input_cols: evolution_response
@@ -123,7 +123,7 @@ blocks:
       max_tokens: 4096
       temperature: 0.2
 
-  - block_type: LLMParserBlock
+  - block_type: LLMResponseExtractorBlock
     block_config:
       block_name: parse_answer
       input_cols: answer_response
@@ -150,7 +150,7 @@ blocks:
       max_tokens: 512
       temperature: 0.0
 
-  - block_type: LLMParserBlock
+  - block_type: LLMResponseExtractorBlock
     block_config:
       block_name: parse_critic_score
       input_cols: critic_response
@@ -185,7 +185,7 @@ blocks:
       max_tokens: 4096
       temperature: 0.0
 
-  - block_type: LLMParserBlock
+  - block_type: LLMResponseExtractorBlock
     block_config:
       block_name: parse_extracted_context
       input_cols: extraction_response

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

@@ -60,7 +60,7 @@ blocks:
     temperature: 0.7
     n: 50
     async_mode: true
-- block_type: LLMParserBlock
+- block_type: LLMResponseExtractorBlock
   block_config:
     block_name: extract_detailed_summary
     input_cols: raw_summary
@@ -108,7 +108,7 @@ blocks:
     temperature: 0.7
     n: 1
     async_mode: true
-- block_type: LLMParserBlock
+- block_type: LLMResponseExtractorBlock
   block_config:
     block_name: extract_questions
     input_cols: question_list
@@ -142,7 +142,7 @@ blocks:
     temperature: 0.7
     n: 1
     async_mode: true
-- block_type: LLMParserBlock
+- block_type: LLMResponseExtractorBlock
   block_config:
     block_name: extract_answers
     input_cols: response_dict
@@ -174,7 +174,7 @@ blocks:
     output_cols: eval_faithful_response_dict
     n: 1
     async_mode: true
-- block_type: LLMParserBlock
+- block_type: LLMResponseExtractorBlock
   block_config:
     block_name: extract_eval_faithful
     input_cols: eval_faithful_response_dict

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

@@ -64,7 +64,7 @@ blocks:
     temperature: 1.0
     n: 1
     async_mode: true
-- block_type: LLMParserBlock
+- block_type: LLMResponseExtractorBlock
   block_config:
     block_name: extract_questions
     input_cols: question_list
@@ -98,7 +98,7 @@ blocks:
     temperature: 1.0
     n: 1
     async_mode: true
-- block_type: LLMParserBlock
+- block_type: LLMResponseExtractorBlock
   block_config:
     block_name: extract_answer
     input_cols: response_dict
@@ -130,7 +130,7 @@ blocks:
     output_cols: eval_faithful_response_dict
     n: 1
     async_mode: true
-- block_type: LLMParserBlock
+- block_type: LLMResponseExtractorBlock
   block_config:
     block_name: extract_eval_faithful
     input_cols: eval_faithful_response_dict

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

@@ -62,7 +62,7 @@ blocks:
     temperature: 0.7
     n: 50
     async_mode: true
-- block_type: LLMParserBlock
+- block_type: LLMResponseExtractorBlock
   block_config:
     block_name: extract_extractive_summary
     input_cols: raw_summary
@@ -110,7 +110,7 @@ blocks:
     temperature: 0.7
     n: 1
     async_mode: true
-- block_type: LLMParserBlock
+- block_type: LLMResponseExtractorBlock
   block_config:
     block_name: extract_questions
     input_cols: question_list
@@ -144,7 +144,7 @@ blocks:
     temperature: 0.7
     n: 1
     async_mode: true
-- block_type: LLMParserBlock
+- block_type: LLMResponseExtractorBlock
   block_config:
     block_name: extract_answers
     input_cols: response_dict
@@ -176,7 +176,7 @@ blocks:
     output_cols: eval_faithful_response_dict
     n: 1
     async_mode: true
-- block_type: LLMParserBlock
+- block_type: LLMResponseExtractorBlock
   block_config:
     block_name: extract_eval_faithful
     input_cols: eval_faithful_response_dict

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

@@ -49,7 +49,7 @@ blocks:
     temperature: 0.7
     n: 1
     async_mode: true
-- block_type: LLMParserBlock
+- block_type: LLMResponseExtractorBlock
   block_config:
     block_name: extract_atomic_facts
     input_cols: raw_summary
@@ -98,7 +98,7 @@ blocks:
     temperature: 0.7
     n: 1
     async_mode: true
-- block_type: LLMParserBlock
+- block_type: LLMResponseExtractorBlock
   block_config:
     block_name: extract_key_fact_qa
     input_cols: raw_key_fact_qa

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

@@ -55,7 +55,7 @@ blocks:
       async_mode: true
       n: 2
 
-  - block_type: LLMParserBlock
+  - block_type: LLMResponseExtractorBlock
     block_config:
       block_name: detailed_summary
       input_cols: raw_summary_detailed
@@ -85,7 +85,7 @@ blocks:
       max_tokens: 2048
       async_mode: true
 
-  - block_type: LLMParserBlock
+  - block_type: LLMResponseExtractorBlock
     block_config:
       block_name: atomic_facts
       input_cols: raw_atomic_facts
@@ -114,7 +114,7 @@ blocks:
       max_tokens: 2048
       async_mode: true
 
-  - block_type: LLMParserBlock
+  - block_type: LLMResponseExtractorBlock
     block_config:
       block_name: extractive_summary
       input_cols: raw_summary_extractive
@@ -160,7 +160,7 @@ blocks:
       max_tokens: 2048
       async_mode: true
 
-  - block_type: LLMParserBlock
+  - block_type: LLMResponseExtractorBlock
     block_config:
       block_name: get_knowledge_generation
       input_cols: raw_knowledge_generation
@@ -191,7 +191,7 @@ blocks:
       n: 1
       async_mode: true
 
-  - block_type: LLMParserBlock
+  - block_type: LLMResponseExtractorBlock
     block_config:
       block_name: extract_eval_faithful
       input_cols: eval_faithful_response_dict
@@ -236,7 +236,7 @@ blocks:
       max_tokens: 2048
       n: 1
       async_mode: true
-  - block_type: LLMParserBlock
+  - block_type: LLMResponseExtractorBlock
     block_config:
       block_name: extract_eval_relevancy
       input_cols: eval_relevancy_response_dict
@@ -280,7 +280,7 @@ blocks:
       max_tokens: 2048
       n: 1
       async_mode: true
-  - block_type: LLMParserBlock
+  - block_type: LLMResponseExtractorBlock
     block_config:
       block_name: extract_verify_question
       input_cols: verify_question_response_dict

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

@@ -57,7 +57,7 @@ blocks:
       async_mode: true
       # n: 2
 
-  - block_type: LLMParserBlock
+  - block_type: LLMResponseExtractorBlock
     block_config:
       block_name: detailed_summary
       input_cols: raw_summary_detailed
@@ -87,7 +87,7 @@ blocks:
       max_tokens: 2048
       async_mode: true
 
-  - block_type: LLMParserBlock
+  - block_type: LLMResponseExtractorBlock
     block_config:
       block_name: atomic_facts
       input_cols: raw_atomic_facts
@@ -116,7 +116,7 @@ blocks:
       max_tokens: 2048
       async_mode: true
 
-  - block_type: LLMParserBlock
+  - block_type: LLMResponseExtractorBlock
     block_config:
       block_name: extractive_summary
       input_cols: raw_summary_extractive
@@ -161,7 +161,7 @@ blocks:
       max_tokens: 2048
       async_mode: true
 
-  - block_type: LLMParserBlock
+  - block_type: LLMResponseExtractorBlock
     block_config:
       block_name: get_knowledge_generation
       input_cols: raw_knowledge_generation
@@ -192,7 +192,7 @@ blocks:
       n: 1
       async_mode: true
 
-  - block_type: LLMParserBlock
+  - block_type: LLMResponseExtractorBlock
     block_config:
       block_name: extract_eval_faithful
       input_cols: eval_faithful_response_dict
@@ -237,7 +237,7 @@ blocks:
       max_tokens: 2048
       n: 1
       async_mode: true
-  - block_type: LLMParserBlock
+  - block_type: LLMResponseExtractorBlock
     block_config:
       block_name: extract_eval_relevancy
       input_cols: eval_relevancy_response_dict
@@ -281,7 +281,7 @@ blocks:
       max_tokens: 2048
       n: 1
       async_mode: true
-  - block_type: LLMParserBlock
+  - block_type: LLMResponseExtractorBlock
     block_config:
       block_name: extract_verify_question
       input_cols: verify_question_response_dict

sdg_hub/flows/text_analysis/structured_insights/flow.yaml

@@ -49,7 +49,7 @@ blocks:
       max_tokens: 1024
       temperature: 0.3
       async_mode: true
-  - block_type: "LLMParserBlock"
+  - block_type: "LLMResponseExtractorBlock"
     block_config:
       block_name: "extract_summary"
       input_cols: "raw_summary"
@@ -81,7 +81,7 @@ blocks:
       max_tokens: 512
       temperature: 0.3
       async_mode: true
-  - block_type: "LLMParserBlock"
+  - block_type: "LLMResponseExtractorBlock"
     block_config:
       block_name: "extract_keywords"
       input_cols: "raw_keywords"
@@ -113,7 +113,7 @@ blocks:
       max_tokens: 1024
       temperature: 0.3
       async_mode: true
-  - block_type: "LLMParserBlock"
+  - block_type: "LLMResponseExtractorBlock"
     block_config:
       block_name: "extract_entities"
       input_cols: "raw_entities"
@@ -145,7 +145,7 @@ blocks:
       max_tokens: 256
       temperature: 0.1
       async_mode: true
-  - block_type: "LLMParserBlock"
+  - block_type: "LLMResponseExtractorBlock"
     block_config:
       block_name: "extract_sentiment"
       input_cols: "raw_sentiment"

{sdg_hub-0.7.2.dist-info → sdg_hub-0.7.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sdg_hub
-Version: 0.7.2
+Version: 0.7.3
 Summary: Synthetic Data Generation
 Author-email: Red Hat AI Innovation <abhandwa@redhat.com>
 License: Apache-2.0
@@ -26,7 +26,7 @@ Requires-Dist: click<9.0.0,>=8.1.7
 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
+Requires-Dist: litellm<2.0.0,>=1.73.0
 Requires-Dist: rich
 Requires-Dist: pandas
 Requires-Dist: pydantic<3.0.0,>=2.0.0

{sdg_hub-0.7.2.dist-info → sdg_hub-0.7.3.dist-info}/RECORD

@@ -1,28 +1,28 @@
 sdg_hub/__init__.py,sha256=TlkZT40-70urdcWLqv3kupaJj8s-SVgd2QyvlSFwb4A,510
-sdg_hub/_version.py,sha256=69rtUS5MR_8CGRaNqkaDM6V4ZDI_8FTMw2vDLxrWg0Q,704
+sdg_hub/_version.py,sha256=gWqiHfJwvZSzPQMjJVXuWX-SvdgzetfD6jyorihjahc,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=8Rn1SglH8V3jGmTD_cG-h7qk9ktAab2eaBdyk7RN_hY,865
-sdg_hub/core/blocks/base.py,sha256=EpHvqXySIdx0f672c-csGKKs7N57ablC8pad_SiB1s8,13066
+sdg_hub/core/blocks/__init__.py,sha256=TztBerg_7Ta8AHX9YM6RwzeoiO42nTHx2rekvMZSRf4,1000
+sdg_hub/core/blocks/base.py,sha256=LgRGvlMqZrxQYUcS_-9HBN_8FZFY1I3O4SBzh0iOCQc,13201
 sdg_hub/core/blocks/registry.py,sha256=FuEN_pnq-nSH1LguY3_oCubT6Kz3SuJjk3TcUpLT-lw,10695
 sdg_hub/core/blocks/filtering/__init__.py,sha256=isxSVSvDqkMjG8dQSl3Q2M4g5c1t9fTjBSA21icf-yA,275
-sdg_hub/core/blocks/filtering/column_value_filter.py,sha256=tHNykB-Q_ItbjDzvlpnjt0Z46mR67O6ZY29ed2ecOwo,6493
-sdg_hub/core/blocks/llm/__init__.py,sha256=1Oo2nv2uXJ2AzRlrQcqDi7gW1FNh9Fid84L89dvy4qM,683
+sdg_hub/core/blocks/filtering/column_value_filter.py,sha256=nT4vBFvi0Q8KoNvh2LkVWRGRp7HkiiLBcPPOGNZF6ig,6528
+sdg_hub/core/blocks/llm/__init__.py,sha256=GTyXZHNYoiyaajx600ouKIrwAg7aS8QjcgkDlThzbag,805
 sdg_hub/core/blocks/llm/error_handler.py,sha256=7T-019ZFB9qgZoX1ybIiXyaLjPzrF96qcKmUu6vmO6g,12178
-sdg_hub/core/blocks/llm/llm_chat_block.py,sha256=0J6oz3EHB8AXB8dicnt6XKvbKCKMvSAEbnLadNORFhs,22946
-sdg_hub/core/blocks/llm/llm_parser_block.py,sha256=NFk8xXceK_F1Pzn9dFNX65ynavuoQiH2ltDLLY_6SXQ,12136
-sdg_hub/core/blocks/llm/prompt_builder_block.py,sha256=zI8DFz34abGnH2Mk0KQe4Mkkb5ophwV7brn4axNsZ2I,14146
-sdg_hub/core/blocks/llm/text_parser_block.py,sha256=CoyfgKcJL9JpokzMcKk4bYeEBr6xnN0XYk45hJANnBQ,12763
+sdg_hub/core/blocks/llm/llm_chat_block.py,sha256=z_vLPrB2e1F4tficBJlTN9vxxnRmBOyOPK6bVFI1SkU,22975
+sdg_hub/core/blocks/llm/llm_response_extractor_block.py,sha256=FiSvAIahi0Tsfy91uMgTd7G2xlDGlOk3EJvQEWGwzu0,12855
+sdg_hub/core/blocks/llm/prompt_builder_block.py,sha256=oJSP5dSxJeva3JML6Yw5WLHxgHuIgw-_ZvFRC4FY5RA,14180
+sdg_hub/core/blocks/llm/text_parser_block.py,sha256=eDND255K3M2JNpAXmXKf4nZZhbypdfHIsnvBinGe8fo,12795
 sdg_hub/core/blocks/transform/__init__.py,sha256=lF9InjOzA6p_mjiwV-a2Kwstq9kqRiQ-dEwbsmR9yQs,825
-sdg_hub/core/blocks/transform/duplicate_columns.py,sha256=dYTxgkWq6X2B37pemJdmAVi56A29NF25YTwUUyN9xHs,2837
-sdg_hub/core/blocks/transform/index_based_mapper.py,sha256=W9ezZNgLUGbLk2U1UJCi2KFbSRPM0Q4vHnP5HGlhsoQ,8908
-sdg_hub/core/blocks/transform/json_structure_block.py,sha256=w7Ex2F3gvpG7uUnM2JM1a7D5xUKGE6HRKwyJpnfLPzc,5069
-sdg_hub/core/blocks/transform/melt_columns.py,sha256=zH3d3C0EO2DVRZqmhyr_g51xz1ZmuBRinrngUCiZkrM,4383
-sdg_hub/core/blocks/transform/rename_columns.py,sha256=EafchUDXvfXxqwRvNIcy92I1Zy6U8lsibtSqWaYdMPU,3150
-sdg_hub/core/blocks/transform/text_concat.py,sha256=Oo6VKGdmeiUmH3B0PDL1y_ot-bYmkT2jbGj7g7C84gg,3089
-sdg_hub/core/blocks/transform/uniform_col_val_setter.py,sha256=Osbz-jciBx5jFfzUbtbCBh_ET4CySG2h0IGWChESHi4,3239
+sdg_hub/core/blocks/transform/duplicate_columns.py,sha256=vK853XsNh62TAcanK8ioVtkWzmBupF4_v1EQUgfGT10,2872
+sdg_hub/core/blocks/transform/index_based_mapper.py,sha256=yN0i7kxv9Wn5VGWa1INMry6US3K9FS-jrYrb2GP1-BI,8943
+sdg_hub/core/blocks/transform/json_structure_block.py,sha256=vVnKCdE_Qs6bFoLG5mPp6LFXZf0UhucwGj_6r79nhFM,5104
+sdg_hub/core/blocks/transform/melt_columns.py,sha256=a6UjTKizsBP2CX8Opp0FmuembGXUJ8b0NGi5lZjmPm8,4418
+sdg_hub/core/blocks/transform/rename_columns.py,sha256=QCPD2vK7Xp6WD_tJrupAFtkMcn98xUK7Rt3trPqmTtE,3185
+sdg_hub/core/blocks/transform/text_concat.py,sha256=E4DoRDeIUgWuF-0a1vE8DpxPpBhQGgXW7wDWAKLSKdg,3124
+sdg_hub/core/blocks/transform/uniform_col_val_setter.py,sha256=mqDG5h0p2qfzWFLlxzOCkDQzYgVUVgKW4PLxKtuon3Q,3274
 sdg_hub/core/flow/__init__.py,sha256=0_m_htuZfPxk8xQ9IKfp0Pz-JRE4O7lYMUFrKyLNoLA,409
-sdg_hub/core/flow/base.py,sha256=0b2AQJ-OpqSQlt_c0tG84V_BdokZcFlkBKNbBLjGVTY,59368
+sdg_hub/core/flow/base.py,sha256=o7OBBH4LkMdJrvYbf3kX6NSAb6U8jQFoRXHKSFHjTEs,58278
 sdg_hub/core/flow/checkpointer.py,sha256=MJay3Q5cfRgJDetk82DaMKJ3ZZUYRHxQabEQTxhGukk,11850
 sdg_hub/core/flow/metadata.py,sha256=cFrpJjWOaK87aCuRFyC3Pdf83oYU93mrmZEMdUnhsN8,10540
 sdg_hub/core/flow/registry.py,sha256=N6KfX-L7QRkooznIFxDuhRZYuDA5g3N5zC-KRm2jVhk,12109
@@ -32,7 +32,7 @@ sdg_hub/core/utils/datautils.py,sha256=7YzG_IpMHj04zHl-r7mswOd3IzTQKJJdfmMBgm7VX
 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/flow_metrics.py,sha256=84ihZHOwbxhqPTdnUXclytf5Tva-IoA1oKIruIXv0Eo,12650
+sdg_hub/core/utils/flow_metrics.py,sha256=6D1o9wWRUcPkYBkrRUesXVXZ0Vf0lMw6D6rSe0_Unl0,12653
 sdg_hub/core/utils/logger_config.py,sha256=6_cnsIHtSAdq1iTTZ7Q7nAJ1dmldlxSZ0AB49yLiQ20,2034
 sdg_hub/core/utils/path_resolution.py,sha256=yWof4kGNpQ5dKcrVHg0h9KfOKLZ6ROjdfsLAZsQT5rM,2000
 sdg_hub/core/utils/time_estimator.py,sha256=rM3_R-Ka5DEtvOtlJoA_5pXSyQ6tT6t4h6qh3_5BCZo,12639
@@ -41,7 +41,7 @@ sdg_hub/flows/evaluation/rag/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NM
 sdg_hub/flows/evaluation/rag/answer_generation.yaml,sha256=dxsHIPyEs14e9fH6JeEJgnrLIV-nLqXmnynj0XF_4os,624
 sdg_hub/flows/evaluation/rag/conceptual_qa_generation.yaml,sha256=cvU8P3EUj9-Cr19Y3ASxkxEBh9ll_NYMC3s6-x1Monc,847
 sdg_hub/flows/evaluation/rag/context_extraction.yaml,sha256=StAAU8yCTzaeGFKieJKFIDRfe21aqk7VIekMH1oEuxA,724
-sdg_hub/flows/evaluation/rag/flow.yaml,sha256=ZDkCrQaN9WfvwWaMjgfA2qUrTVz7pCw-PiHzOyzXKio,5276
+sdg_hub/flows/evaluation/rag/flow.yaml,sha256=3HAZaedHPmjn_JWoLzXxHLXurAm9JXxj8pfHB3LNv-4,5342
 sdg_hub/flows/evaluation/rag/groundedness_critic.yaml,sha256=r5zqetGnNvg4UxCuENTzdWhCFbG6TnkY-seDMVRBBko,782
 sdg_hub/flows/evaluation/rag/question_evolution.yaml,sha256=d3G11dQ3Wkgz0JBNyqTi-6QMGIdODOVcGNw1x9OnTEE,649
 sdg_hub/flows/evaluation/rag/topic_generation.yaml,sha256=DhY_Wt7NzzjfirYlQQqABrXn73vMQj9W2XLZZEaofKc,303
@@ -51,14 +51,14 @@ 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=cxNpPh60mcvzxfczMH8hw66Ql3S8O-cWCCDeauO736c,5649
+sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/detailed_summary/flow.yaml,sha256=mBdgcG2wipY8uWO6IA-p1kstgzAhroS0Yc2Xou9vSL0,5693
 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/doc_direct_qa/flow.yaml,sha256=7f423gfJ7qGQHYBo43D4mw0fVs7iAxJYSpuPb0QhYCU,4446
 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=7dVc0_g7Ex5SfdX57pqtk9gmH_lC6Cdm3HC-lg8OiXQ,5817
+sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/extractive_summary/flow.yaml,sha256=tzUnZsI5iW8nxT5xRJIKQocUp8wUucQuUOrnh4vJRBM,5861
 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=7X4N19TcyHUo7pNo3C6Zv3w6br7hjzEfgv06XUVDaQo,3330
+sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/key_facts/flow.yaml,sha256=wuj_aZhW52PyrejIDucWXu8SEel4okMN8wFnol0_Bkc,3352
 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
@@ -68,24 +68,24 @@ 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=km0ggcmFsZJGc2TfyYLkzPTrHGmcOB-jBAHInqySisk,9176
+sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/instructlab/flow.yaml,sha256=BcNO79qG4L4A0BLtiV0bwn9mFkapRtZD3PjIHCf44yI,9253
 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=U9DBWSKkYGGtwWQ39o8l7g-mLb93505APTEFePyzqIc,9312
+sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/multilingual/japanese/flow.yaml,sha256=u9rNPWlTjH7qDvq7FO9fjgNLkOAV9_WNVHKpjKbl-ao,9389
 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
 sdg_hub/flows/text_analysis/structured_insights/analyze_sentiment.yaml,sha256=1YGPypFJYS8qfYFj2J6ERTgodKJvMF4YHNGt_vOF5qc,1000
 sdg_hub/flows/text_analysis/structured_insights/extract_entities.yaml,sha256=Q_SDy14Zu-qS2sbKfUBmGlYj3k7CUg6HzzXlFCXRKuU,1169
 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/flow.yaml,sha256=E9bx5QvmIwm69KITVwZFgwlwe33nhYbVRPRwrMrD8Xw,4978
 sdg_hub/flows/text_analysis/structured_insights/summarize.yaml,sha256=WXwQak1pF8e1OwnOoI1EHu8QB6iUNW89rfkTdi1Oq54,687
-sdg_hub-0.7.2.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-sdg_hub-0.7.2.dist-info/METADATA,sha256=V0DFJlc77tCFAiZY3AuAGXlbXo6hkeMTMm3YPhKiuZs,9615
-sdg_hub-0.7.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-sdg_hub-0.7.2.dist-info/top_level.txt,sha256=TqI7d-HE1n6zkXFkU0nF3A1Ct0P0pBaqI675uFokhx4,8
-sdg_hub-0.7.2.dist-info/RECORD,,
+sdg_hub-0.7.3.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+sdg_hub-0.7.3.dist-info/METADATA,sha256=8Pk7CkXl9klRjqpxMGHZp9gt7CuNozv2hV3gGPkRqow,9614
+sdg_hub-0.7.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+sdg_hub-0.7.3.dist-info/top_level.txt,sha256=TqI7d-HE1n6zkXFkU0nF3A1Ct0P0pBaqI675uFokhx4,8
+sdg_hub-0.7.3.dist-info/RECORD,,