data-designer 0.1.0__tar.gz → 0.1.1__tar.gz

data_designer-0.1.1/.github/workflows/pack-tutorials.yml

@@ -0,0 +1,74 @@
+name: Pack Tutorials
+
+on:
+  workflow_dispatch:
+  release:
+    types: [published]
+
+jobs:
+  zip_and_upload:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up environment variables
+        id: env_setup
+        run: |
+          echo "SOURCE_FOLDER_PATH=docs/notebooks" >> $GITHUB_ENV
+          echo "TARGET_FOLDER_NAME=data_designer_tutorial" >> $GITHUB_ENV
+          echo "ZIP_FILE_NAME=data_designer_tutorial.zip" >> $GITHUB_ENV
+          
+      - name: Check if source folder exists
+        run: |
+          if [ ! -d "${{ env.SOURCE_FOLDER_PATH }}" ]; then
+            echo "::error::Source folder '${{ env.SOURCE_FOLDER_PATH }}' not found. Check the input value."
+            exit 1
+          fi
+
+      - name: Rename source folder
+        run: mv ${{ env.SOURCE_FOLDER_PATH }} ${{ env.TARGET_FOLDER_NAME }}
+
+      - name: Zip the target folder
+        run: |
+          zip -r ${{ env.ZIP_FILE_NAME }} ${{ env.TARGET_FOLDER_NAME }}
+          echo "Successfully created ${{ env.ZIP_FILE_NAME }}"
+
+      - name: Find the latest existing release tag
+        id: get_release
+        run: |
+          if [ "${{ github.event_name }}" == "release" ]; then
+            LATEST_TAG="${{ github.event.release.tag_name }}"
+          else
+            echo "::notice::Running manually via workflow_dispatch. Fetching latest release tag..."
+
+            gh auth status || echo "GitHub CLI is not authenticated, relying on GITHUB_TOKEN."
+
+            # We use tr -d '\n' to remove the trailing newline for a clean tag string
+            LATEST_TAG=$(gh release view --json tagName -q .tagName 2>/dev/null)
+
+            if [ -z "$LATEST_TAG" ]; then
+              echo "::error::Could not find the latest published release tag. Ensure a release exists."
+              exit 1
+            fi
+          fi
+          
+          echo "Latest release tag found: $LATEST_TAG"
+          echo "tag=$LATEST_TAG" >> $GITHUB_OUTPUT
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Upload zip file as release asset
+        uses: softprops/action-gh-release@v2
+        with:
+          tag_name: ${{ steps.get_release.outputs.tag }}
+          files: ${{ env.ZIP_FILE_NAME }}
+          draft: false
+          prerelease: false
+          
+      - name: Cleanup
+        if: always()
+        run: rm -f ${{ env.ZIP_FILE_NAME }}

{data_designer-0.1.0 → data_designer-0.1.1}/CONTRIBUTING.md

@@ -12,7 +12,6 @@ This guide will help you get started with the contribution process.
 - [Ways to Contribute](#ways-to-contribute)
 - [Feature Requests](#feature-requests)
 - [Development Guide](#development-guide)
-- [Code Quality Standards](#code-quality-standards)
 - [Submitting Changes](#submitting-changes)
 - [Code of Conduct](#code-of-conduct)
 - [Signing off on your work](#signing-off-on-your-work)
@@ -88,94 +87,97 @@ Data Designer uses [`uv`](https://github.com/astral-sh/uv) for dependency manage
 ### Initial Setup
 0. **Create or find an issue**
 
-   Before starting work, ensure there's an issue tracking your contribution:
-   - For bug fixes: Search [existing issues](https://github.com/NVIDIA-NeMo/DataDesigner/issues) or [create a new one](https://github.com/NVIDIA-NeMo/DataDesigner/issues/new)
-   - For new features: Open a [feature request](#feature-requests) to discuss the approach first
-   - Comment on the issue to let maintainers know you're working on it
+    Before starting work, ensure there's an issue tracking your contribution:
+
+    - For bug fixes: Search [existing issues](https://github.com/NVIDIA-NeMo/DataDesigner/issues) or [create a new one](https://github.com/NVIDIA-NeMo/DataDesigner/issues/new)
+    - For new features: Open a [feature request](#feature-requests) to discuss the approach first
+    - Comment on the issue to let maintainers know you're working on it
 
 1. **Fork and clone the repository**
 
-   Start by [forking the Data Designer repository](https://github.com/NVIDIA-NeMo/DataDesigner/fork), then clone your fork and add the upstream remote:
+    Start by [forking the Data Designer repository](https://github.com/NVIDIA-NeMo/DataDesigner/fork), then clone your fork and add the upstream remote:
 
-   ```bash
-   git clone https://github.com/YOUR_GITHUB_USERNAME/DataDesigner.git
+    ```bash
+    git clone https://github.com/YOUR_GITHUB_USERNAME/DataDesigner.git
 
-   cd DataDesigner
+    cd DataDesigner
 
-   git remote add upstream https://github.com/NVIDIA-NeMo/DataDesigner.git
-   ```
+    git remote add upstream https://github.com/NVIDIA-NeMo/DataDesigner.git
+    ```
 
 2. **Install dependencies**
 
-   ```bash
-   # Install project with dev dependencies
-   make install-dev
+    ```bash
+    # Install project with dev dependencies
+    make install-dev
 
-   # Or, if you use Jupyter / IPython for development
-   make install-dev-notebooks
-   ```
+    # Or, if you use Jupyter / IPython for development
+    make install-dev-notebooks
+    ```
 
 3. **Verify your setup**
 
-   ```bash
-   make test && make check-all
-   ```
+    ```bash
+    make test && make check-all
+    ```
 
-   If no errors are reported, you're ready to develop 🚀
+    If no errors are reported, you're ready to develop 🚀
 
 ### Making Changes
 
 1. **Create a feature branch**
 
-   ```bash
-   git checkout main
-   git pull upstream main
-   git checkout -b <username>/<type-of-change>/<issue-number>-<short-description>
-   ```
-
-   Example types of change:
-   - `feat` for new features
-   - `fix` for bug fixes
-   - `docs` for documentation updates
-   - `test` for testing changes
-   - `refactor` for code refactoring
-   - `chore` for chore tasks
-   - `style` for style changes
-   - `perf` for performance improvements
-
-   Example branch name:
-   - `johnnygreco/feat/123-add-xyz-generator` for a new feature by @johnnygreco, addressing issue #123
+    ```bash
+    git checkout main
+    git pull upstream main
+    git checkout -b <username>/<type-of-change>/<issue-number>-<short-description>
+    ```
+
+    Example types of change:
+
+    - `feat` for new features
+    - `fix` for bug fixes
+    - `docs` for documentation updates
+    - `test` for testing changes
+    - `refactor` for code refactoring
+    - `chore` for chore tasks
+    - `style` for style changes
+    - `perf` for performance improvements
+
+    Example branch name:
+
+    - `johnnygreco/feat/123-add-xyz-generator` for a new feature by @johnnygreco, addressing issue #123
 
 2. **Develop your changes**
 
-   Please follow the patterns and conventions used throughout the codebase, as well as those outlined in [AGENTS.md](AGENTS.md).
+    Please follow the patterns and conventions used throughout the codebase, as well as those outlined in [AGENTS.md](https://github.com/NVIDIA-NeMo/DataDesigner/blob/main/AGENTS.md).
 
 3. **Test and validate**
 
-   ```bash
-   make check-all-fix  # Format code and fix linting issues
-   make test           # Run all tests
-   make coverage       # Check test coverage (must be >90%)
-   ```
+    ```bash
+    make check-all-fix  # Format code and fix linting issues
+    make test           # Run all tests
+    make coverage       # Check test coverage (must be >90%)
+    ```
 
-   **Writing tests**: Place tests in [tests/](tests/) mirroring the source structure. Use fixtures from [tests/conftest.py](tests/conftest.py), mock external services with `unittest.mock` or `pytest-httpx`, and test both success and failure cases. See [AGENTS.md](AGENTS.md) for patterns and examples.
+    **Writing tests**: Place tests in [tests/](https://github.com/NVIDIA-NeMo/DataDesigner/blob/main/tests/) mirroring the source structure. Use fixtures from [tests/conftest.py](https://github.com/NVIDIA-NeMo/DataDesigner/blob/main/tests/conftest.py), mock external services with `unittest.mock` or `pytest-httpx`, and test both success and failure cases. See [AGENTS.md](https://github.com/NVIDIA-NeMo/DataDesigner/blob/main/AGENTS.md) for patterns and examples.
 
 4. **Commit your work**
 
-   Write clear, descriptive commit messages, optionally including a brief summary (50 characters or less) and reference issue numbers when applicable (e.g., "Fixes #123").
+    Write clear, descriptive commit messages, optionally including a brief summary (50 characters or less) and reference issue numbers when applicable (e.g., "Fixes #123").
 
-   ```bash
-   git commit -m "Add XYZ generator for synthetic data" -m "Fixes #123"
-   ```
+    ```bash
+    git commit -m "Add XYZ generator for synthetic data" -m "Fixes #123"
+    ```
 
 5. **Stay up to date**
 
-   Regularly sync your branch with upstream changes:
+    Regularly sync your branch with upstream changes:
 
-   ```bash
-   git fetch upstream
-   git merge upstream/main
-   ```
+    ```bash
+    git fetch upstream
+    git merge upstream/main
+    ```
 
 ## Submitting Changes
 
@@ -194,9 +196,9 @@ Ensure your changes meet the following criteria:
 
 1. **Push your changes** to your fork:
 
-   ```bash
-   git push origin <username>/<type-of-change>/<issue-number>-<short-description>
-   ```
+    ```bash
+    git push origin <username>/<type-of-change>/<issue-number>-<short-description>
+    ```
 
 2. **Open a pull request** on GitHub from your fork to the main repository
 
@@ -213,7 +215,7 @@ Ensure your changes meet the following criteria:
 ## Code of Conduct
 Data Designer follows the Contributor Covenant Code of Conduct. We are committed to providing a welcoming and inclusive environment for all contributors.
 
-**Please read our complete [Code of Conduct](CODE_OF_CONDUCT.md)** for full details on our standards and expectations.
+**Please read our complete [Code of Conduct](https://github.com/NVIDIA-NeMo/DataDesigner/blob/main/CODE_OF_CONDUCT.md)** for full details on our standards and expectations.
 
 ### License File Headers
 All code files that are added to this repository must include the appropriate NVIDIA copyright header:
@@ -225,17 +227,9 @@ All code files that are added to this repository must include the appropriate NV
 
 Use `make update-license-headers` to add headers automatically.
 
-## Getting Help
-Need help with your contribution?
-
-- **Documentation**: Check the [documentation](docs/) and [AGENTS.md](AGENTS.md) for additional information
-- **Issues**: Browse [existing issues](https://github.com/NVIDIA-NeMo/DataDesigner/issues) for similar questions
-- **Contact**: Reach out to the core maintainers at [data-designer@nvidia.com](mailto:data-designer@nvidia.com)
-
-
 ## Signing off on your work
 
-When contributing to this project, you must agree that you have authored 100% of the content, that you have the necessary rights to the content and that the content you contribute may be provided under the project license. All contributors are asked to sign the Data Designer [Developer Certificate of Origin (DCO)](DCO) when submitting their first pull request. The process is automated by a bot that will comment on the pull request. Our DCO is the same as the Linux Foundation requires its contributors to sign.
+When contributing to this project, you must agree that you have authored 100% of the content, that you have the necessary rights to the content and that the content you contribute may be provided under the project license. All contributors are asked to sign the Data Designer [Developer Certificate of Origin (DCO)](https://github.com/NVIDIA-NeMo/DataDesigner/blob/main/DCO) when submitting their first pull request. The process is automated by a bot that will comment on the pull request. Our DCO is the same as the Linux Foundation requires its contributors to sign.
 
 ---
 

{data_designer-0.1.0 → data_designer-0.1.1}/PKG-INFO

@@ -1,18 +1,18 @@
 Metadata-Version: 2.4
 Name: data-designer
-Version: 0.1.0
+Version: 0.1.1
 Summary: General framework for synthetic data generation
+License-Expression: Apache-2.0
 License-File: LICENSE
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
-Classifier: License :: Other/Proprietary License
+Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Classifier: Topic :: Scientific/Engineering :: Human Machine Interfaces
 Classifier: Topic :: Software Development
 Requires-Python: >=3.10
 Requires-Dist: anyascii<1.0,>=0.3.3
@@ -51,7 +51,7 @@ Description-Content-Type: text/markdown
 
 [![CI](https://github.com/NVIDIA-NeMo/DataDesigner/actions/workflows/ci.yml/badge.svg)](https://github.com/NVIDIA-NeMo/DataDesigner/actions/workflows/ci.yml)
 [![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
-[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/) [![NeMo Microservices](https://img.shields.io/badge/NeMo-Microservices-76b900)](https://docs.nvidia.com/nemo/microservices/latest/index.html)
+[![Python 3.10 - 3.13](https://img.shields.io/badge/🐍_Python-3.10_|_3.11_|_3.12_|_3.13-blue.svg)](https://www.python.org/downloads/) [![NeMo Microservices](https://img.shields.io/badge/NeMo-Microservices-76b900)](https://docs.nvidia.com/nemo/microservices/latest/index.html) [![Code](https://img.shields.io/badge/Code-Documentation-8A2BE2.svg)](https://nvidia-nemo.github.io/DataDesigner/)
 
 **Generate high-quality synthetic datasets from scratch or using your own seed data.**
 
@@ -147,10 +147,12 @@ preview.display_sample_record()
 
 ### 📚 Learn more
 
-- **[Quick Start Guide](https://nvidia-nemo.github.io/DataDesigner)** – Detailed walkthrough with more examples
-- **[Tutorial Notebooks](https://nvidia-nemo.github.io/DataDesigner/notebooks/1-the-basics/)** – Step-by-step interactive tutorials
+- **[Quick Start Guide](https://nvidia-nemo.github.io/DataDesigner/quick-start/)** – Detailed walkthrough with more examples
+- **[Tutorial Notebooks](https://nvidia-nemo.github.io/DataDesigner/notebooks/intro/)** – Step-by-step interactive tutorials
 - **[Column Types](https://nvidia-nemo.github.io/DataDesigner/concepts/columns/)** – Explore samplers, LLM columns, validators, and more
+- **[Validators](https://nvidia-nemo.github.io/DataDesigner/concepts/validators/)** – Learn how to validate generated data with Python, SQL, and remote validators
 - **[Model Configuration](https://nvidia-nemo.github.io/DataDesigner/models/model-configs/)** – Configure custom models and providers
+- **[Person Sampling](https://nvidia-nemo.github.io/DataDesigner/concepts/person_sampling/)** – Learn how to sample realistic person data with demographic attributes
 
 ### 🔧 Configure models via CLI
 
@@ -162,12 +164,27 @@ data-designer config list      # View current settings
 
 ### 🤝 Get involved
 
-- **[Contributing Guide](https://nvidia-nemo.github.io/DataDesigner/CONTRIBUTING.md)** – Help improve Data Designer
-- **[GitHub Issues](https://github.com/NVIDIA-NeMo/DataDesigner/issues)** – Report bugs or request features
-- **[GitHub Discussions](https://github.com/NVIDIA-NeMo/DataDesigner/discussions)** – Ask questions and share ideas
+- **[Contributing Guide](https://nvidia-nemo.github.io/DataDesigner/CONTRIBUTING)** – Help improve Data Designer
+- **[GitHub Issues](https://github.com/NVIDIA-NeMo/DataDesigner/issues)** – Report bugs or make a feature request
 
 ---
 
 ## License
 
 Apache License 2.0 – see [LICENSE](LICENSE) for details.
+
+---
+
+## Citation
+
+If you use NeMo Data Designer in your research, please cite it using the following BibTeX entry:
+
+```bibtex
+@misc{nemo-data-designer,
+  author = {The NeMo Data Designer Team},
+  title = {NeMo Data Designer: A framework for generating synthetic data from scratch or based on your own seed data},
+  howpublished = {\url{https://github.com/NVIDIA-NeMo/DataDesigner}},
+  year = {2025},
+  note = {GitHub Repository},
+}
+```

{data_designer-0.1.0 → data_designer-0.1.1}/README.md

@@ -2,7 +2,7 @@
 
 [![CI](https://github.com/NVIDIA-NeMo/DataDesigner/actions/workflows/ci.yml/badge.svg)](https://github.com/NVIDIA-NeMo/DataDesigner/actions/workflows/ci.yml)
 [![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
-[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/) [![NeMo Microservices](https://img.shields.io/badge/NeMo-Microservices-76b900)](https://docs.nvidia.com/nemo/microservices/latest/index.html)
+[![Python 3.10 - 3.13](https://img.shields.io/badge/🐍_Python-3.10_|_3.11_|_3.12_|_3.13-blue.svg)](https://www.python.org/downloads/) [![NeMo Microservices](https://img.shields.io/badge/NeMo-Microservices-76b900)](https://docs.nvidia.com/nemo/microservices/latest/index.html) [![Code](https://img.shields.io/badge/Code-Documentation-8A2BE2.svg)](https://nvidia-nemo.github.io/DataDesigner/)
 
 **Generate high-quality synthetic datasets from scratch or using your own seed data.**
 
@@ -98,10 +98,12 @@ preview.display_sample_record()
 
 ### 📚 Learn more
 
-- **[Quick Start Guide](https://nvidia-nemo.github.io/DataDesigner)** – Detailed walkthrough with more examples
-- **[Tutorial Notebooks](https://nvidia-nemo.github.io/DataDesigner/notebooks/1-the-basics/)** – Step-by-step interactive tutorials
+- **[Quick Start Guide](https://nvidia-nemo.github.io/DataDesigner/quick-start/)** – Detailed walkthrough with more examples
+- **[Tutorial Notebooks](https://nvidia-nemo.github.io/DataDesigner/notebooks/intro/)** – Step-by-step interactive tutorials
 - **[Column Types](https://nvidia-nemo.github.io/DataDesigner/concepts/columns/)** – Explore samplers, LLM columns, validators, and more
+- **[Validators](https://nvidia-nemo.github.io/DataDesigner/concepts/validators/)** – Learn how to validate generated data with Python, SQL, and remote validators
 - **[Model Configuration](https://nvidia-nemo.github.io/DataDesigner/models/model-configs/)** – Configure custom models and providers
+- **[Person Sampling](https://nvidia-nemo.github.io/DataDesigner/concepts/person_sampling/)** – Learn how to sample realistic person data with demographic attributes
 
 ### 🔧 Configure models via CLI
 
@@ -113,12 +115,27 @@ data-designer config list      # View current settings
 
 ### 🤝 Get involved
 
-- **[Contributing Guide](https://nvidia-nemo.github.io/DataDesigner/CONTRIBUTING.md)** – Help improve Data Designer
-- **[GitHub Issues](https://github.com/NVIDIA-NeMo/DataDesigner/issues)** – Report bugs or request features
-- **[GitHub Discussions](https://github.com/NVIDIA-NeMo/DataDesigner/discussions)** – Ask questions and share ideas
+- **[Contributing Guide](https://nvidia-nemo.github.io/DataDesigner/CONTRIBUTING)** – Help improve Data Designer
+- **[GitHub Issues](https://github.com/NVIDIA-NeMo/DataDesigner/issues)** – Report bugs or make a feature request
 
 ---
 
 ## License
 
 Apache License 2.0 – see [LICENSE](LICENSE) for details.
+
+---
+
+## Citation
+
+If you use NeMo Data Designer in your research, please cite it using the following BibTeX entry:
+
+```bibtex
+@misc{nemo-data-designer,
+  author = {The NeMo Data Designer Team},
+  title = {NeMo Data Designer: A framework for generating synthetic data from scratch or based on your own seed data},
+  howpublished = {\url{https://github.com/NVIDIA-NeMo/DataDesigner}},
+  year = {2025},
+  note = {GitHub Repository},
+}
+```

data_designer-0.1.1/docs/concepts/person_sampling.md

@@ -0,0 +1,36 @@
+# Person Sampling in Data Designer
+
+Person sampling in Data Designer allows you to generate synthetic person data for your datasets using the Faker library.
+
+## Faker-Based Sampling
+
+### What It Does
+Uses the Faker library to generate random personal information. The data is basic and not demographically accurate, but is useful for quick testing, prototyping, or when realistic demographic distributions are not relevant for your use case.
+
+### Features
+- Gives you access to person attributes that Faker exposes
+- Quick to set up with no additional downloads
+- Generates random names, emails, addresses, phone numbers, etc.
+- Supports [all Faker-supported locales](https://faker.readthedocs.io/en/master/locales.html)
+- **Not demographically grounded** - data patterns don't reflect real-world demographics
+
+### Usage Example
+```python
+from data_designer.essentials import (
+    SamplerColumnConfig,
+    SamplerType,
+    PersonFromFakerSamplerParams,
+)
+
+config_builder.add_column(
+    SamplerColumnConfig(
+        name="customer",
+        sampler_type=SamplerType.PERSON_FROM_FAKER,
+        params=PersonFromFakerSamplerParams(
+            locale="en_US",
+            age_range=[25, 65],
+            sex="Female",
+        ),
+    )
+)
+```

{data_designer-0.1.0 → data_designer-0.1.1}/docs/models/default-model-settings.md

@@ -92,5 +92,4 @@ Both methods operate on the same files, ensuring consistency across your entire
 
 - **[Configure Model Settings With the CLI](configure-model-settings-with-the-cli.md)**: Learn how to use the CLI to manage model settings.
 - **[Quick Start Guide](../quick-start.md)**: Get started with a simple example
-- **[Model Configuration Reference](../code_reference/config_builder.md)**: Detailed API documentation
-- **[Column Configurations](../code_reference/column_configs.md)**: Learn about all column types
+- **[Model Configurations](model-configs.md)**: Learn about model configurations

data_designer-0.1.0/docs/notebooks/intro.md → data_designer-0.1.1/docs/notebooks/README.md

@@ -6,21 +6,15 @@ Welcome to the Data Designer tutorial series! These hands-on notebooks will guid
 
 ### Local Setup Best Practices
 
-The notebooks can be downloaded using the link on the top of each of them.
-To run them locally, we recommend using a virtual environment to manage dependencies:
+First, download the tutorial [from the release assets](https://github.com/NVIDIA-NeMo/DataDesigner/releases/latest/download/data_designer_tutorial.zip).
+To run the tutorial notebooks locally, we recommend using a virtual environment to manage dependencies:
 
 === "uv (Recommended)"
 
     ```bash
-    # Create a new project directory
-    mkdir data-designer-tutorials
-    cd data-designer-tutorials
-
-    # Initialize a new uv project
-    uv init
-
-    # Add data-designer and jupyter
-    uv add data-designer jupyter
+    # Extract tutorial notebooks
+    unzip data_designer_tutorial.zip
+    cd data_designer_tutorial
 
     # Launch Jupyter
     uv run jupyter notebook
@@ -29,15 +23,13 @@ To run them locally, we recommend using a virtual environment to manage dependen
 === "pip + venv"
 
     ```bash
-    # Create a new project directory
-    mkdir data-designer-tutorials
-    cd data-designer-tutorials
+    # Extract tutorial notebooks
+    unzip data_designer_tutorial.zip
+    cd data_designer_tutorial
 
-    # Create and activate a virtual environment
+    # Create Python virtual environment and install required packages
     python -m venv venv
     source venv/bin/activate
-
-    # Install data-designer and jupyter
     pip install data-designer jupyter
 
     # Launch Jupyter
@@ -108,7 +100,7 @@ Understanding these concepts will help you make the most of the tutorials:
 
 - **[Columns](../concepts/columns.md)** - Learn about different column types (Sampler, LLM, Expression, Validation, etc.)
 - **[Validators](../concepts/validators.md)** - Understand how to validate generated data with Python, SQL, and remote validators
-- **[Plugins](../concepts/plugins.md)** - Extend Data Designer with custom functionality
+- **[Person Sampling](../concepts/person_sampling.md)** - Learn how to sample realistic person data with demographic attributes
 
 ### Code Reference
 
@@ -117,4 +109,4 @@ Quick reference guides for the main configuration objects:
 - **[column_configs](../code_reference/column_configs.md)** - All column configuration types
 - **[config_builder](../code_reference/config_builder.md)** - The `DataDesignerConfigBuilder` API
 - **[data_designer_config](../code_reference/data_designer_config.md)** - Main configuration schema
-- **[validator_params](../code_reference/validator_params.md)** - Validator configuration options
+- **[validator_params](../code_reference/validator_params.md)** - Validator configuration options

data_designer-0.1.1/docs/notebooks/pyproject.toml

@@ -0,0 +1,9 @@
+[project]
+name = "data_designer_tutorial"
+version = "0.1.0"
+readme = "README.md"
+requires-python = ">=3.11"
+dependencies = [
+    "data-designer>=0.1.0",
+    "jupyter>=1.1.1",
+]

{data_designer-0.1.0 → data_designer-0.1.1}/mkdocs.yml

@@ -10,15 +10,14 @@ nav:
   - Concepts:
       - Columns: concepts/columns.md
       - Validators: concepts/validators.md
-      - Persons: concepts/persons.md
-      # - Plugins: concepts/plugins.md
+      - Person Sampling: concepts/person_sampling.md
   - Models:
       - Default Model Settings: models/default-model-settings.md
       - Configure with the CLI: models/configure-model-settings-with-the-cli.md
       - Model Providers: models/model-providers.md
       - Model Configs: models/model-configs.md
   - Tutorials:
-      - Overview: notebooks/intro.md
+      - Overview: notebooks/README.md
       - The Basics: notebooks/1-the-basics.ipynb
       - Structured Outputs and Jinja Expressions: notebooks/2-structured-outputs-and-jinja-expressions.ipynb
       - Seeding with an External Dataset: notebooks/3-seeding-with-a-dataset.ipynb

{data_designer-0.1.0 → data_designer-0.1.1}/pyproject.toml

@@ -4,15 +4,15 @@ dynamic = ["version"]
 description = "General framework for synthetic data generation"
 readme = "README.md"
 requires-python = ">=3.10"
+license = "Apache-2.0"
 
 classifiers = [
   "Development Status :: 4 - Beta",
   "Intended Audience :: Developers",
   "Intended Audience :: Science/Research",
   "Topic :: Scientific/Engineering :: Artificial Intelligence",
-  "Topic :: Scientific/Engineering :: Human Machine Interfaces",
   "Topic :: Software Development",
-  "License :: Other/Proprietary License",
+  "License :: OSI Approved :: Apache Software License",
   "Programming Language :: Python :: 3.10",
   "Programming Language :: Python :: 3.11",
   "Programming Language :: Python :: 3.12",

{data_designer-0.1.0 → data_designer-0.1.1}/src/data_designer/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.1.0'
-__version_tuple__ = version_tuple = (0, 1, 0)
+__version__ = version = '0.1.1'
+__version_tuple__ = version_tuple = (0, 1, 1)
 
 __commit_id__ = commit_id = None

{data_designer-0.1.0 → data_designer-0.1.1}/src/data_designer/config/datastore.py

@@ -124,7 +124,7 @@ def _fetch_seed_dataset_column_names_from_datastore(
         raise InvalidFileFormatError(f"🛑 Unsupported file type: {filename!r}")
 
     datastore_settings = resolve_datastore_settings(datastore_settings)
-    fs = HfFileSystem(endpoint=datastore_settings.endpoint, token=datastore_settings.token)
+    fs = HfFileSystem(endpoint=datastore_settings.endpoint, token=datastore_settings.token, skip_instance_cache=True)
 
     with fs.open(f"datasets/{repo_id}/{filename}") as f:
         return get_file_column_names(f, file_type)

{data_designer-0.1.0 → data_designer-0.1.1}/src/data_designer/config/default_model_settings.py

@@ -4,6 +4,7 @@
 
 from functools import lru_cache
 import logging
+import os
 from pathlib import Path
 from typing import Any, Literal, Optional
 
@@ -15,7 +16,6 @@ from .utils.constants import (
     PREDEFINED_PROVIDERS,
     PREDEFINED_PROVIDERS_MODEL_MAP,
 )
-from .utils.info import ConfigBuilderInfo, InfoType, InterfaceInfo
 from .utils.io_helpers import load_config_file, save_config_file
 
 logger = logging.getLogger(__name__)
@@ -75,7 +75,15 @@ def get_default_model_configs() -> list[ModelConfig]:
         config_dict = load_config_file(MODEL_CONFIGS_FILE_PATH)
         if "model_configs" in config_dict:
             return [ModelConfig.model_validate(mc) for mc in config_dict["model_configs"]]
-    raise FileNotFoundError(f"Default model configs file not found at {str(MODEL_CONFIGS_FILE_PATH)!r}")
+    return []
+
+
+def get_defaul_model_providers_missing_api_keys() -> list[str]:
+    missing_api_keys = []
+    for predefined_provider in PREDEFINED_PROVIDERS:
+        if os.environ.get(predefined_provider["api_key"]) is None:
+            missing_api_keys.append(predefined_provider["api_key"])
+    return missing_api_keys
 
 
 def get_default_providers() -> list[ModelProvider]:
@@ -91,21 +99,17 @@ def get_default_provider_name() -> Optional[str]:
 
 def resolve_seed_default_model_settings() -> None:
     if not MODEL_CONFIGS_FILE_PATH.exists():
-        logger.info(
+        logger.debug(
             f"🍾 Default model configs were not found, so writing the following to {str(MODEL_CONFIGS_FILE_PATH)!r}"
         )
-        config_builder_info = ConfigBuilderInfo(model_configs=get_builtin_model_configs())
-        config_builder_info.display(info_type=InfoType.MODEL_CONFIGS)
         save_config_file(
             MODEL_CONFIGS_FILE_PATH, {"model_configs": [mc.model_dump() for mc in get_builtin_model_configs()]}
         )
 
     if not MODEL_PROVIDERS_FILE_PATH.exists():
-        logger.info(
+        logger.debug(
             f"🪄  Default model providers were not found, so writing the following to {str(MODEL_PROVIDERS_FILE_PATH)!r}"
         )
-        interface_info = InterfaceInfo(model_providers=get_builtin_model_providers())
-        interface_info.display(info_type=InfoType.MODEL_PROVIDERS)
         save_config_file(
             MODEL_PROVIDERS_FILE_PATH, {"providers": [p.model_dump() for p in get_builtin_model_providers()]}
         )