sdg-hub 0.7.0__tar.gz → 0.7.2__tar.gz

{sdg_hub-0.7.0 → sdg_hub-0.7.2}/.github/workflows/docs.yml

@@ -39,6 +39,6 @@ jobs:
       - name: "Checkout"
         uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
       - name: "Check Markdown documents"
-        uses: DavidAnson/markdownlint-cli2-action@30a0e04f1870d58f8d717450cc6134995f993c63 # v21.0.0
+        uses: DavidAnson/markdownlint-cli2-action@07035fd053f7be764496c0f8d8f9f41f98305101 # v22.0.0
         with:
           globs: '**/*.md'

{sdg_hub-0.7.0 → sdg_hub-0.7.2}/.github/workflows/integration-test.yml

@@ -112,7 +112,7 @@ jobs:
 
 
       - name: Cache huggingface datasets
-        uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
+        uses: actions/cache@9255dc7a253b0ccc959486e2bca901246202afeb # v5.0.1
         with:
           path: ~/.cache/huggingface
           # Invalidate cache when any example notebook changes (may affect dataset downloads)
@@ -127,6 +127,7 @@ jobs:
         env:
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
         run: |
+          # Uses .[dev,integration] - lightweight, no torch/transformers
           tox -e py3-integrationcov
 
 
@@ -139,7 +140,7 @@ jobs:
           flags: integration
 
       - name: Upload integration test artifacts
-        uses: actions/upload-artifact@v5
+        uses: actions/upload-artifact@v6
         if: always()
         with:
           name: integration-test-results-${{ matrix.python }}-${{ matrix.platform }}

{sdg_hub-0.7.0 → sdg_hub-0.7.2}/.github/workflows/pypi.yaml

@@ -72,7 +72,7 @@ jobs:
                   egress-policy: audit # TODO: change to 'egress-policy: block' after couple of runs
 
             - name: "Download build artifacts"
-              uses: actions/download-artifact@018cc2cf5baa6db3ef3c5f8a56943fffe632ef53 # v6.0.0
+              uses: actions/download-artifact@37930b1c2abaa49bbe596cd826c3c89aef350131 # v7.0.0
               with:
                   name: Packages
                   path: dist
@@ -104,13 +104,13 @@ jobs:
                   egress-policy: audit # TODO: change to 'egress-policy: block' after couple of runs
 
             - name: "Download build artifacts"
-              uses: actions/download-artifact@018cc2cf5baa6db3ef3c5f8a56943fffe632ef53 # v6.0.0
+              uses: actions/download-artifact@37930b1c2abaa49bbe596cd826c3c89aef350131 # v7.0.0
               with:
                   name: Packages
                   path: dist
 
             - name: "Sigstore sign package"
-              uses: sigstore/gh-action-sigstore-python@f832326173235dcb00dd5d92cd3f353de3188e6c # v3.1.0
+              uses: sigstore/gh-action-sigstore-python@a5caf349bc536fbef3668a10ed7f5cd309a4b53d # v3.2.0
               with:
                   inputs: |
                       ./dist/*.tar.gz

{sdg_hub-0.7.0 → sdg_hub-0.7.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sdg_hub
-Version: 0.7.0
+Version: 0.7.2
 Summary: Synthetic Data Generation
 Author-email: Red Hat AI Innovation <abhandwa@redhat.com>
 License: Apache-2.0
@@ -33,6 +33,20 @@ 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: 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"
+Requires-Dist: pytest-env; extra == "dev"
+Requires-Dist: nbconvert>=7.0.0; extra == "dev"
+Provides-Extra: integration
+Requires-Dist: nest-asyncio; extra == "integration"
 Provides-Extra: examples
 Requires-Dist: tabulate>=0.9.0; extra == "examples"
 Requires-Dist: transformers>=4.37.0; extra == "examples"
@@ -46,20 +60,7 @@ 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"
 Requires-Dist: ipykernel; 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"
-Requires-Dist: pytest-env; extra == "dev"
-Requires-Dist: nbconvert>=7.0.0; extra == "dev"
 Dynamic: license-file
 
 # `sdg_hub`: Synthetic Data Generation Toolkit

{sdg_hub-0.7.0 → sdg_hub-0.7.2}/examples/knowledge_tuning/enhanced_summary_knowledge_tuning/README.md

@@ -48,29 +48,38 @@ Only claims passing this check are retained. This process filters out **hallucin
 
 ---
 
-## Data Generation Statistics
+## Data Generation Statistics and Results
+
+**Teacher model for generation:** `openai/gpt-oss-120b`  
+**Student model trained:** `meta-llama/Llama-3.1-8B-Instruct`  
+**Training method:** Supervised Fine-Tuning (SFT)
+
+---
 
 ### Summary Augmentation
 
-Each “cut” represents the total number of summaries generated per document across all three augmentation types.
+For each document, we generate three augmentation types—detailed summaries, extractive summaries, and atomic facts. Each “cut” on the table below represents the total number of summary augmentations per document (i.e., how many times each augmentation process is run).
 
-| Cut (NUMBER\_OF\_SUMMARIES = 3) | Token Count |
-| ------------------------------- | ----------- |
-| 1                               | 2,193,502   |
-| 2                               | 4,383,655   |
-| 5                               | 10,870,396  |
-| 10                              | 21,815,170  |
-| 20                              | 43,601,976  |
-| 30                              | 65,395,710  |
-| 40                              | 87,118,308  |
-| 50                              | 108,779,213 |
+| Cut (NUMBER\_OF\_SUMMARIES = 3) | Token Count   |
+| ------------------------------- | ------------- |
+| Input Corpus                    | 1,517,465     |
+| 10                              | 87,248,889    |
+| 20                              | 158,615,276   |
+| 30                              | 230,306,195   |
+| 40                              | 301,805,906   |
+| 50                              | 373,183,414   |
 
 ---
 
-### Finance Bench Example
+### Benchmark Results
 
-For Finance Bench (NUMBER\_OF\_SUMMARIES = 1):
+- **Evaluation benchmark:** [QuALITY benchmark](https://nyu-mll.github.io/quality/)
+- **Evaluation script & metric:** [Synthetic_Continued_Pretraining](https://github.com/ZitongYang/Synthetic_Continued_Pretraining/blob/main/evaluation.py), Exact Match (EM)
+- **Student model:** meta-llama/Llama-3.1-8B-Instruct (after SFT on generated/augmented summaries)
+- **Performance metric:** Model accuracy
 
-| Cut | Token Count |
-| --- | ----------- |
-| 50  | 213,333,192 |
+![Quality Benchmark Accuracy](imgs/quality_benchmark_accuracy.png)
+
+*Figure: Model accuracy across the QuALITY benchmark datasets, comparing SFT training on enhanced document summaries with the original model performance.*
+
+---

{sdg_hub-0.7.0 → sdg_hub-0.7.2}/examples/knowledge_tuning/knowledge_utils.py

@@ -602,13 +602,14 @@ def _num_chars_from_tokens(num_tokens) -> int:
     return int(num_tokens * 4)  # 1 token ~ 4 English character
 
 
-def chunk_document(documents: List, server_ctx_size, chunk_word_count) -> List[str]:
+def chunk_document(documents: List, server_ctx_size, chunk_word_count, **kwargs) -> List[str]:
     """
     Iterates over the documents and splits them into chunks based on the word count provided by the user.
     Args:
         documents (list): List of documents retrieved from git (can also consist of a single document).
         server_ctx_size (int): Context window size of server.
         chunk_word_count (int): Maximum number of words to chunk a document.
+        chunk_overlap (int): Overlap in characters between chunks.
     Returns:
          List[str]: List of chunked documents.
     """
@@ -634,7 +635,7 @@ def chunk_document(documents: List, server_ctx_size, chunk_word_count) -> List[s
     # Placeholder for params
     content = []
     chunk_size = _num_chars_from_tokens(no_tokens_per_doc)
-    chunk_overlap = _DEFAULT_CHUNK_OVERLAP
+    chunk_overlap = int(kwargs.pop("chunk_overlap", str(_DEFAULT_CHUNK_OVERLAP)))
 
     # Using Markdown as default, document-specific chunking will be implemented in seperate pr.
     text_splitter = RecursiveCharacterTextSplitter.from_language(
@@ -729,16 +730,21 @@ class DocProcessor:
             }
         )
 
-    def _add_icls(self, chunked_document: Dataset) -> Dataset:
+    def _add_icls(self, chunked_document: Dataset, **kwargs) -> Dataset:
         """
         Add the ICLS label to the dataset.
         Args:
             dataset (Dataset): Dataset object.
+            server_ctx_size (int): Context window size of server.
+            chunk_word_count (int): Maximum number of words to chunk a document.
+            chunk_overlap (int): Overlap in characters between chunks.
 
         Returns
         -------
             Dataset: Dataset object with ICLS label.
         """
+        server_ctx_size = int(kwargs.pop("server_ctx_size", "4096"))
+        chunk_word_count = int(kwargs.pop("chunk_word_count", "1024"))
         icl = self.user_config["seed_examples"]
         chunked_document_all_icl = []
         for icl_ in icl:
@@ -762,7 +768,7 @@ class DocProcessor:
         chunked_document_all_icl = chunked_document_all_icl.map(
             lambda x: {
                 "chunks": chunk_document(
-                    [x["document"]], server_ctx_size=4096, chunk_word_count=1024
+                    [x["document"]], server_ctx_size=server_ctx_size, chunk_word_count=chunk_word_count, **kwargs
                 )
                 if get_token_count(x["document"], self.tokenizer) > 1024
                 else [x["document"]]
@@ -797,7 +803,7 @@ class DocProcessor:
         df = safe_concatenate_datasets([ds.to_pandas() for ds in datasets])
         return Dataset.from_pandas(df) if df is not None else None
 
-    def get_processed_markdown_dataset(self, list_md_files: list[Path]) -> Dataset:
+    def get_processed_markdown_dataset(self, list_md_files: list[Path], **kwargs) -> Dataset:
         chunks_mds = []
         for md_file in list_md_files:
             with open(md_file, "r", encoding="utf-8") as f:
@@ -811,5 +817,5 @@ class DocProcessor:
                     }
                 )
         chunk_ds = Dataset.from_list(chunks_mds)
-        chunk_ds_with_icls = self._add_icls(chunk_ds)
+        chunk_ds_with_icls = self._add_icls(chunk_ds, **kwargs)
         return chunk_ds_with_icls

{sdg_hub-0.7.0 → sdg_hub-0.7.2}/pyproject.toml

@@ -51,22 +51,7 @@ source = "https://github.com/Red-Hat-AI-Innovation-Team/sdg_hub"
 issues = "https://github.com/Red-Hat-AI-Innovation-Team/sdg_hub/issues"
 
 [project.optional-dependencies]
-examples = [
-    "tabulate>=0.9.0",
-    "transformers>=4.37.0",
-    "langchain-text-splitters",
-    "docling>=2.3.0",
-    "scikit-learn",
-    "polars",
-    "matplotlib",
-    "spacy",
-    "nltk",
-    "sentence-transformers",
-    "instructor",
-    "fastapi",
-    "nest-asyncio",
-    "ipykernel",
-]
+# Development and testing dependencies (lightweight, no ML libraries)
 dev = [
     "pre-commit>=3.0.4,<4.0",
     "pylint>=2.16.2,<4.0",
@@ -81,6 +66,28 @@ dev = [
     # Integration testing dependencies
     "nbconvert>=7.0.0",
 ]
+# Minimal dependencies for integration testing only
+# Integration tests run knowledge_generation.ipynb which only needs nest-asyncio
+integration = [
+    "nest-asyncio",
+]
+# Heavy dependencies for example notebooks (knowledge_mixing.ipynb, etc.)
+# NOT required for core functionality testing or integration tests
+examples = [
+    "tabulate>=0.9.0",
+    "transformers>=4.37.0",      # For knowledge_mixing.ipynb, NOT integration tests
+    "langchain-text-splitters",
+    "docling>=2.3.0",            # For document parsing examples
+    "scikit-learn",              # For raft_builder.py utility
+    "polars",                     # For knowledge_mixing_utils.py
+    "matplotlib",
+    "spacy",
+    "nltk",
+    "sentence-transformers",
+    "instructor",
+    "fastapi",
+    "ipykernel",
+]
 
 [tool.setuptools_scm]
 version_file = "src/sdg_hub/_version.py"

{sdg_hub-0.7.0 → sdg_hub-0.7.2}/src/sdg_hub/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.7.0'
-__version_tuple__ = version_tuple = (0, 7, 0)
+__version__ = version = '0.7.2'
+__version_tuple__ = version_tuple = (0, 7, 2)
 
-__commit_id__ = commit_id = 'g33f3e7e56'
+__commit_id__ = commit_id = 'g99a40a268'

{sdg_hub-0.7.0 → sdg_hub-0.7.2}/src/sdg_hub/core/blocks/llm/llm_chat_block.py

@@ -6,7 +6,8 @@ from typing import Any, Optional
 import asyncio
 
 from litellm import acompletion, completion
-from pydantic import ConfigDict, Field, field_validator
+from pydantic import ConfigDict, Field, SecretStr, field_validator
+from tqdm.asyncio import tqdm_asyncio
 import litellm
 
 # Third Party
@@ -52,8 +53,9 @@ class LLMChatBlock(BaseBlock):
     model : Optional[str], optional
         Model identifier in LiteLLM format. Can be set later via flow.set_model_config().
         Examples: "openai/gpt-4", "anthropic/claude-3-sonnet-20240229"
-    api_key : Optional[str], optional
+    api_key : Optional[SecretStr], optional
         API key for the provider. Falls back to environment variables.
+        Automatically redacted in logs and string representations.
     api_base : Optional[str], optional
         Base URL for the API. Required for local models.
     async_mode : bool, optional
@@ -97,7 +99,7 @@ class LLMChatBlock(BaseBlock):
     model: Optional[str] = Field(
         None, exclude=True, description="Model identifier in LiteLLM format"
     )
-    api_key: Optional[str] = Field(
+    api_key: Optional[SecretStr] = Field(
         None, exclude=True, description="API key for the provider"
     )
     api_base: Optional[str] = Field(
@@ -301,7 +303,7 @@ class LLMChatBlock(BaseBlock):
         if self.model is not None:
             completion_kwargs["model"] = self.model
         if self.api_key is not None:
-            completion_kwargs["api_key"] = self.api_key
+            completion_kwargs["api_key"] = self.api_key.get_secret_value()
         if self.api_base is not None:
             completion_kwargs["api_base"] = self.api_base
         if self.timeout is not None:
@@ -501,7 +503,9 @@ class LLMChatBlock(BaseBlock):
                     for messages in messages_list
                 ]
 
-            responses = await asyncio.gather(*tasks)
+            responses = await tqdm_asyncio.gather(
+                *tasks, desc=self.block_name, unit="req"
+            )
             return responses
 
         except Exception as e:

{sdg_hub-0.7.0 → sdg_hub-0.7.2}/src/sdg_hub/core/flow/base.py

@@ -13,6 +13,7 @@ from pydantic import (
     ConfigDict,
     Field,
     PrivateAttr,
+    SecretStr,
     field_validator,
     model_validator,
 )
@@ -793,7 +794,10 @@ class Flow(BaseModel):
         if api_base is not None:
             config_params["api_base"] = api_base
         if api_key is not None:
-            config_params["api_key"] = api_key
+            # Convert string api_key to SecretStr for automatic redaction in logs
+            config_params["api_key"] = (
+                SecretStr(api_key) if isinstance(api_key, str) else api_key
+            )
 
         # Add any additional kwargs (temperature, max_tokens, etc.)
         config_params.update(kwargs)
@@ -855,6 +859,7 @@ class Flow(BaseModel):
 
         if modified_count > 0:
             # Enhanced logging showing what was configured
+            # Note: SecretStr values automatically display as '**********' in logs
             param_summary = []
             for param_name, param_value in config_params.items():
                 if param_name == "model":

{sdg_hub-0.7.0 → sdg_hub-0.7.2}/src/sdg_hub.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sdg_hub
-Version: 0.7.0
+Version: 0.7.2
 Summary: Synthetic Data Generation
 Author-email: Red Hat AI Innovation <abhandwa@redhat.com>
 License: Apache-2.0
@@ -33,6 +33,20 @@ 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: 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"
+Requires-Dist: pytest-env; extra == "dev"
+Requires-Dist: nbconvert>=7.0.0; extra == "dev"
+Provides-Extra: integration
+Requires-Dist: nest-asyncio; extra == "integration"
 Provides-Extra: examples
 Requires-Dist: tabulate>=0.9.0; extra == "examples"
 Requires-Dist: transformers>=4.37.0; extra == "examples"
@@ -46,20 +60,7 @@ 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"
 Requires-Dist: ipykernel; 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"
-Requires-Dist: pytest-env; extra == "dev"
-Requires-Dist: nbconvert>=7.0.0; extra == "dev"
 Dynamic: license-file
 
 # `sdg_hub`: Synthetic Data Generation Toolkit

{sdg_hub-0.7.0 → sdg_hub-0.7.2}/src/sdg_hub.egg-info/SOURCES.txt

@@ -54,6 +54,7 @@ examples/knowledge_tuning/enhanced_summary_knowledge_tuning/knowledge_generation
 examples/knowledge_tuning/enhanced_summary_knowledge_tuning/knowledge_mixing.ipynb
 examples/knowledge_tuning/enhanced_summary_knowledge_tuning/knowledge_mixing_utils.py
 examples/knowledge_tuning/enhanced_summary_knowledge_tuning/raft_builder.py
+examples/knowledge_tuning/enhanced_summary_knowledge_tuning/imgs/quality_benchmark_accuracy.png
 examples/knowledge_tuning/instructlab/.gitignore
 examples/knowledge_tuning/instructlab/README.md
 examples/knowledge_tuning/instructlab/docling_v2_config.yaml

{sdg_hub-0.7.0 → sdg_hub-0.7.2}/src/sdg_hub.egg-info/requires.txt

@@ -36,5 +36,7 @@ nltk
 sentence-transformers
 instructor
 fastapi
-nest-asyncio
 ipykernel
+
+[integration]
+nest-asyncio

{sdg_hub-0.7.0 → sdg_hub-0.7.2}/tests/flow/test_base.py

@@ -527,13 +527,15 @@ class TestFlow:
     ):
         """Create a mock LLM block with model attributes."""
         # First Party
+        from pydantic import SecretStr
         from tests.flow.conftest import MockBlock
 
         block = MockBlock(block_name=name, input_cols=["input"], output_cols=["output"])
         # Add LLM-related attributes
         block.model = model
         block.api_base = api_base
-        block.api_key = api_key
+        # Convert api_key to SecretStr to match real LLM blocks
+        block.api_key = SecretStr(api_key) if isinstance(api_key, str) else api_key
         block.temperature = 0.0
         block.max_tokens = 1024
         return block
@@ -637,7 +639,7 @@ class TestFlow:
         # Check that LLM blocks were modified
         assert flow.blocks[1].model == "new-model"  # llm_block1
         assert flow.blocks[1].api_base == "http://localhost:8101/v1"
-        assert flow.blocks[1].api_key == "NEW_KEY"
+        assert flow.blocks[1].api_key.get_secret_value() == "NEW_KEY"
         assert flow.blocks[1].temperature == 0.7
         assert flow.blocks[1].max_tokens == 2048
 
@@ -696,7 +698,7 @@ class TestFlow:
 
         # Other parameters should remain unchanged
         assert flow.blocks[0].api_base == "http://localhost:8000/v1"
-        assert flow.blocks[0].api_key == "OLD_KEY"
+        assert flow.blocks[0].api_key.get_secret_value() == "OLD_KEY"
         assert flow.blocks[0].max_tokens == 1024
 
     def test_set_model_config_with_kwargs(self):
@@ -793,7 +795,7 @@ class TestFlow:
 
         # Everything else should remain the same
         assert flow.blocks[0].api_base == "http://localhost:8000/v1"
-        assert flow.blocks[0].api_key == "ORIGINAL_KEY"
+        assert flow.blocks[0].api_key.get_secret_value() == "ORIGINAL_KEY"
         assert flow.blocks[0].temperature == 0.5
         assert flow.blocks[0].max_tokens == 1024
         assert flow.blocks[0].custom_param == "custom_value"
@@ -1422,3 +1424,47 @@ class TestFlow:
             FlowValidationError, match="max_concurrency must be greater than 0"
         ):
             flow.generate(dataset, max_concurrency=-1)
+
+    def test_set_model_config_redacts_sensitive_params(self, caplog):
+        """Test API key and secrets redaction in logs using Pydantic SecretStr.
+
+        Verifies that sensitive parameters (api_key) are automatically redacted
+        by SecretStr while non-sensitive ones remain visible.
+        """
+        # Standard
+        import logging
+
+        # First Party
+        from sdg_hub.core.blocks.llm.llm_chat_block import LLMChatBlock
+
+        llm_block = LLMChatBlock(
+            block_name="test_llm", input_cols="messages", output_cols="response"
+        )
+        flow = Flow(metadata=self.test_metadata, blocks=[llm_block])
+
+        with caplog.at_level(logging.INFO, logger="sdg_hub.core.flow.base"):
+            flow.set_model_config(
+                model="openai/gpt-4",
+                api_key="sk-secret-key",
+                temperature=0.7,
+                max_tokens=100,
+            )
+
+        log_messages = [record.message for record in caplog.records]
+        relevant_logs = [
+            msg for msg in log_messages if "Successfully configured" in msg
+        ]
+        assert len(relevant_logs) > 0
+        log_text = relevant_logs[0]
+
+        # Sensitive params must be redacted - SecretStr displays as '**********'
+        assert "**********" in log_text or "SecretStr" in log_text
+        assert "sk-secret-key" not in log_text
+
+        # Non-sensitive params should be visible
+        assert "temperature: 0.7" in log_text
+        assert "max_tokens: 100" in log_text
+
+        # Verify that the api_key was actually set as a SecretStr on the block
+        assert llm_block.api_key is not None
+        assert llm_block.api_key.get_secret_value() == "sk-secret-key"

{sdg_hub-0.7.0 → sdg_hub-0.7.2}/tox.ini

@@ -22,28 +22,30 @@ commands =
     integration: {envpython} -m pytest {posargs:tests/integration}
 
 # Integration test environment - runs notebook-based integration tests
+# Lightweight: only requires nest-asyncio, NO torch/transformers needed
 [testenv:py3-integration]
-description = run integration tests (notebooks)
+description = run integration tests (notebooks) - lightweight, no torch/transformers needed
 package = wheel
 wheel_build_env = pkg
 passenv =
     OPENAI_API_KEY
 deps =
     .[dev]
-    .[examples]
+    .[integration]
 commands =
     {envpython} -m pytest {posargs:tests/integration -v -s}
 
 # Integration test environment with coverage - runs notebook-based integration tests with coverage collection
+# Lightweight: only requires nest-asyncio, NO torch/transformers needed
 [testenv:py3-integrationcov]
-description = run integration tests (notebooks) with coverage
+description = run integration tests (notebooks) with coverage - lightweight, no torch/transformers needed
 package = wheel
 wheel_build_env = pkg
 passenv =
     OPENAI_API_KEY
 deps =
     .[dev]
-    .[examples]
+    .[integration]
 commands =
     {envpython} -m pytest --cov=sdg_hub --cov-report term --cov-report=html:coverage-{env_name} --cov-report=xml:coverage-{env_name}.xml --html=durations/{env_name}.html tests/integration {posargs:-v -s}