sdg-hub 0.1.3__py3-none-any.whl → 0.2.0__py3-none-any.whl

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

@@ -0,0 +1,54 @@
+- role: system
+  content: You are a very knowledgeable AI Assistant that will faithfully assist the user with their task.
+
+- role: user
+  content: |
+    Develop a series of educational question and answer pairs from a chapter in a {{domain}} textbook.
+
+    The questions should:
+    * Be self-contained, not requiring references to tables, figures, or specific sections in the text for understanding.
+    * Focus on teaching and reinforcing the key knowledge and concepts presented in the chapter.
+    * Avoid sections with minimal educational content like index pages or prefaces. In such cases, respond with [UNANSWERABLE].
+    * Be directly relevant to the textbook's domain. For instance, in a science textbook, questions should revolve around scientific terms, definitions, and practical applications, while in a legal textbook, they should cover legal principles, case law, and precedents.
+    * Be formulated to allow for independent answers, avoiding direct references to specific theorems or text sections. For example, rather than asking 'Under what conditions is the fixed point of a function unique according to Theorem 3.1.5?', ask 'How does the Fixed Point Iteration method contribute to understanding function uniqueness?'
+    * Span a range of difficulty levels to accommodate a diverse student audience, from basic understanding to advanced comprehension.
+    * Include a variety of question types such as multiple-choice for basic recall, short answer for deeper understanding, and essay or problem-solving questions to test application and analysis skills.
+    * Align closely with the learning objectives of the textbook or the specific chapter, ensuring that the questions test the fundamental concepts and skills that the chapter aims to impart.
+
+    Strictly follow this format for each question answer pair your generate while responding:
+
+    [QUESTION]
+    <Insert question here>
+    [ANSWER]
+    <Insert answer here>
+    [END]
+
+    Each question and answer pair should stand alone as a mini-lesson, encapsulating a key concept or idea from the chapter in a way that is accessible and informative without requiring the reader to refer back to the textbook.
+
+    Here are some examples of questions:
+
+    [Document]
+    {{icl_document}}
+
+    [QUESTION]
+    {{icl_query_1}}
+    [ANSWER]
+    {{icl_response_1}}
+    [END]
+
+    [QUESTION]
+    {{icl_query_2}}
+    [ANSWER]
+    {{icl_response_2}}
+    [END]
+
+    [QUESTION]
+    {{icl_query_3}}
+    [ANSWER]
+    {{icl_response_3}}
+    [END]
+
+    Now, here is the document:
+    [DOCUMENT]
+    {{document_outline}}
+    {{document}}

sdg_hub-0.2.0.dist-info/METADATA

@@ -0,0 +1,218 @@
+Metadata-Version: 2.4
+Name: sdg_hub
+Version: 0.2.0
+Summary: Synthetic Data Generation
+Author-email: Red Hat AI Innovation <abhandwa@redhat.com>
+License: Apache-2.0
+Project-URL: homepage, https://ai-innovation.team/
+Project-URL: source, https://github.com/Red-Hat-AI-Innovation-Team/sdg_hub
+Project-URL: issues, https://github.com/Red-Hat-AI-Innovation-Team/sdg_hub/issues
+Classifier: Environment :: Console
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: MacOS :: MacOS X
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: Implementation :: CPython
+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: 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
+Requires-Dist: tenacity!=8.4.0,>=8.3.0
+Requires-Dist: tqdm<5.0.0,>=4.66.2
+Provides-Extra: vllm
+Requires-Dist: vllm>=0.9.1; extra == "vllm"
+Requires-Dist: torch>=2.0.0; extra == "vllm"
+Requires-Dist: transformers>=4.37.0; extra == "vllm"
+Requires-Dist: accelerate>=0.21.0; extra == "vllm"
+Requires-Dist: xformers>=0.0.22.post7; extra == "vllm"
+Provides-Extra: examples
+Requires-Dist: tabulate>=0.9.0; extra == "examples"
+Requires-Dist: transformers>=4.37.0; extra == "examples"
+Requires-Dist: langchain-text-splitters; extra == "examples"
+Requires-Dist: docling>=2.3.0; extra == "examples"
+Requires-Dist: scikit-learn; extra == "examples"
+Requires-Dist: pandas; extra == "examples"
+Requires-Dist: polars; extra == "examples"
+Requires-Dist: matplotlib; extra == "examples"
+Requires-Dist: spacy; extra == "examples"
+Requires-Dist: nltk; extra == "examples"
+Requires-Dist: sentence-transformers; extra == "examples"
+Requires-Dist: instructor; extra == "examples"
+Requires-Dist: fastapi; extra == "examples"
+Requires-Dist: nest-asyncio; extra == "examples"
+Provides-Extra: dev
+Requires-Dist: pre-commit<4.0,>=3.0.4; extra == "dev"
+Requires-Dist: pylint<4.0,>=2.16.2; extra == "dev"
+Requires-Dist: pylint-pydantic; extra == "dev"
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: pytest-asyncio; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+Requires-Dist: pytest-html; extra == "dev"
+Requires-Dist: tox<5,>=4.4.2; extra == "dev"
+Requires-Dist: ruff; extra == "dev"
+Dynamic: license-file
+
+# `sdg_hub`: Synthetic Data Generation Toolkit
+
+[![Build](https://github.com/Red-Hat-AI-Innovation-Team/sdg_hub/actions/workflows/pypi.yaml/badge.svg?branch=main)](https://github.com/Red-Hat-AI-Innovation-Team/sdg_hub/actions/workflows/pypi.yaml)
+[![Release](https://img.shields.io/github/v/release/Red-Hat-AI-Innovation-Team/sdg_hub)](https://github.com/Red-Hat-AI-Innovation-Team/sdg_hub/releases)
+[![License](https://img.shields.io/github/license/Red-Hat-AI-Innovation-Team/sdg_hub)](https://github.com/Red-Hat-AI-Innovation-Team/sdg_hub/blob/main/LICENSE)
+[![Tests](https://github.com/Red-Hat-AI-Innovation-Team/sdg_hub/actions/workflows/test.yml/badge.svg)](https://github.com/Red-Hat-AI-Innovation-Team/sdg_hub/actions/workflows/test.yml)
+[![codecov](https://codecov.io/gh/Red-Hat-AI-Innovation-Team/sdg_hub/graph/badge.svg?token=SP75BCXWO2)](https://codecov.io/gh/Red-Hat-AI-Innovation-Team/sdg_hub)
+
+
+
+A modular Python framework for building synthetic data generation pipelines using composable blocks and flows. Transform datasets through **building-block composition** - mix and match LLM-powered and traditional processing blocks to create sophisticated data generation workflows.
+
+**📖 Full documentation available at: [https://ai-innovation.team/sdg_hub](https://ai-innovation.team/sdg_hub)**
+
+## ✨ Key Features
+
+**🔧 Modular Composability** - Mix and match blocks like Lego pieces. Build simple transformations or complex multi-stage pipelines with YAML-configured flows.
+
+**⚡ Async Performance** - High-throughput LLM processing with built-in error handling.
+
+**🛡️ Built-in Validation** - Pydantic-based type safety ensures your configurations and data are correct before execution.
+
+**🔍 Auto-Discovery** - Automatic block and flow registration. No manual imports or complex setup.
+
+**📊 Rich Monitoring** - Detailed logging with progress bars and execution summaries.
+
+**🧩 Easily Extensible** - Create custom blocks with simple inheritance. Rich logging and monitoring built-in.
+
+
+## 📦 Installation
+
+Recommended: Install uv  — see https://docs.astral.sh/uv/getting-started/installation/
+
+```bash
+# Production
+uv pip install sdg-hub
+
+# Development
+git clone https://github.com/Red-Hat-AI-Innovation-Team/sdg_hub.git
+cd sdg_hub
+uv pip install .[dev]
+# or: uv sync --extra dev
+```
+
+### Optional Dependencies
+```bash
+# For vLLM support
+uv pip install sdg-hub[vllm]
+
+# For examples
+uv pip install sdg-hub[examples]
+```
+
+## 🚀 Quick Start
+
+### 🧱 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.
+
+**Flows** orchestrate multiple blocks into complete pipelines defined in YAML. Chain blocks together to create complex data generation workflows with validation and parameter management.
+
+```python
+# Simple concept: Blocks transform data, Flows chain blocks together
+dataset → Block₁ → Block₂ → Block₃ → enriched_dataset
+```
+
+### Try it out!
+
+#### Flow Discovery
+```python
+from sdg_hub import FlowRegistry
+
+# Auto-discover all available flows (no setup needed!)
+FlowRegistry.discover_flows()
+
+# List available flows
+flows = FlowRegistry.list_flows()
+print(f"Available flows: {flows}")
+
+# Search for specific types
+qa_flows = FlowRegistry.search_flows(tag="question-generation")
+print(f"QA flows: {qa_flows}")
+```
+
+#### Using Flows
+```python
+from sdg_hub import FlowRegistry, Flow
+from datasets import Dataset
+
+# 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)
+flow = Flow.from_yaml(flow_path)
+
+# Discover recommended models
+default_model = flow.get_default_model()
+recommendations = flow.get_model_recommendations()
+
+# Configure model settings at runtime
+# This assumes you have a hosted vLLM instance of meta-llama/Llama-3.3-70B-Instruct running at http://localhost:8000/v1
+flow.set_model_config(
+    model=f"hosted_vllm/{default_model}",
+    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']
+})
+
+# Generate high-quality QA pairs
+result = flow.generate(dataset)
+
+# Access generated content
+questions = result['question']
+answers = result['response']
+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
+
+This project is licensed under the Apache License 2.0 - see the [LICENSE](LICENSE) file for details.
+
+## 🤝 Contributing
+
+We welcome contributions! Please see [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines on how to contribute to this project.
+
+---
+
+Built with ❤️ by the Red Hat AI Innovation Team

sdg_hub-0.2.0.dist-info/RECORD

@@ -0,0 +1,63 @@
+sdg_hub/__init__.py,sha256=Tw-6R5a8_W1kJcTAsW3R9ltBDP1dy5-fe7Tvt3cSyCQ,550
+sdg_hub/_version.py,sha256=iB5DfB5V6YB5Wo4JmvS-txT42QtmGaWcWp3udRT7zCI,511
+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/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=ABcXZrqEMsgKfdGAkSo2plMp4LsZSqPhEQugoDEYm1I,2950
+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/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/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/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/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/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/utils/error_handling.py,sha256=yku8cGj_nKCyXDsnb-mHCpgukkkAMucJ4iAUrIzqysc,5510
+sdg_hub/core/utils/logger_config.py,sha256=MPYdpyNXh_pxFUOAvSCHa98LGjxjaLXoUoqWekqTG4s,422
+sdg_hub/core/utils/path_resolution.py,sha256=yWof4kGNpQ5dKcrVHg0h9KfOKLZ6ROjdfsLAZsQT5rM,2000
+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
+sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/instructlab/detailed_summary.yaml,sha256=_vF-AzjC8d6wqAle5pkQ103EW-BbAhNA0qllk3ojUZc,353
+sdg_hub/flows/qa_generation/document_grounded_qa/multi_summary_qa/instructlab/evaluate_faithfulness.yaml,sha256=GiIipXrjm7btghvpgFUoTZYAJRyu7yE-WEi5yDLxjY4,3032
+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/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/blocks/__init__.py

@@ -1,42 +0,0 @@
-"""Block implementations for SDG Hub.
-
-This package provides various block implementations for data generation, processing, and transformation.
-"""
-
-# Local
-from .block import Block
-from .llmblock import LLMBlock, ConditionalLLMBlock
-from .openaichatblock import (
-    OpenAIChatBlock,
-    OpenAIAsyncChatBlock
-)
-from .utilblocks import (
-    SamplePopulatorBlock,
-    SelectorBlock,
-    CombineColumnsBlock,
-    FlattenColumnsBlock,
-    DuplicateColumns,
-    RenameColumns,
-    SetToMajorityValue,
-    FilterByValueBlock,
-    IterBlock,
-)
-from ..registry import BlockRegistry
-
-__all__ = [
-    "Block",
-    "FilterByValueBlock",
-    "IterBlock",
-    "LLMBlock",
-    "ConditionalLLMBlock",
-    "SamplePopulatorBlock",
-    "SelectorBlock",
-    "CombineColumnsBlock",
-    "FlattenColumnsBlock",
-    "DuplicateColumns",
-    "RenameColumns",
-    "SetToMajorityValue",
-    "BlockRegistry",
-    "OpenAIChatBlock",
-    "OpenAIAsyncChatBlock"
-]

sdg_hub/blocks/block.py

@@ -1,96 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-"""Base block implementation for the SDG Hub system.
-
-This module provides the abstract base class for all blocks in the system,
-including functionality for template validation and configuration management.
-"""
-
-# Standard
-from abc import ABC
-from collections import ChainMap
-from typing import Any, Dict, Optional
-
-# Third Party
-from jinja2 import Template, UndefinedError
-import yaml
-
-# Local
-from ..registry import BlockRegistry
-from ..logger_config import setup_logger
-
-logger = setup_logger(__name__)
-
-
-@BlockRegistry.register("Block")
-class Block(ABC):
-    """Base abstract class for all blocks in the system.
-
-    This class provides common functionality for block validation and configuration loading.
-    All specific block implementations should inherit from this class.
-    """
-    
-    def __init__(self, block_name: str) -> None:
-        self.block_name = block_name
-
-    @staticmethod
-    def _validate(prompt_template: Template, input_dict: Dict[str, Any]) -> bool:
-        """Validate the input data for this block.
-
-        This method validates whether all required variables in the Jinja template are provided in the input_dict.
-
-        Parameters
-        ----------
-        prompt_template : Template
-            The Jinja2 template object.
-        input_dict : Dict[str, Any]
-            A dictionary of input values to check against the template.
-
-        Returns
-        -------
-        bool
-            True if the input data is valid (i.e., no missing variables), False otherwise.
-        """
-
-        class Default(dict):
-            def __missing__(self, key: str) -> None:
-                raise KeyError(key)
-
-        try:
-            # Try rendering the template with the input_dict
-            prompt_template.render(ChainMap(input_dict, Default()))
-            return True
-        except UndefinedError as e:
-            logger.error(f"Missing key: {e}")
-            return False
-
-    def _load_config(self, config_path: str) -> Optional[Dict[str, Any]]:
-        """Load the configuration file for this block.
-
-        Parameters
-        ----------
-        config_path : str
-            The path to the configuration file.
-
-        Returns
-        -------
-        Optional[Dict[str, Any]]
-            The loaded configuration. Returns None if file cannot be read or parsed.
-
-        Raises
-        ------
-        FileNotFoundError
-            If the configuration file does not exist.
-        """
-        try:
-            with open(config_path, "r", encoding="utf-8") as config_file:
-                try:
-                    return yaml.safe_load(config_file)
-                except yaml.YAMLError as e:
-                    logger.error(f"Error parsing YAML from {config_path}: {e}")
-                    return None
-        except FileNotFoundError:
-            logger.error(f"Configuration file not found: {config_path}")
-            raise
-        except Exception as e:
-            logger.error(f"Unexpected error reading config file {config_path}: {e}")
-            return None