site_name: NeMo Data Designer site_url: https://nvidia-nemo.github.io/DataDesigner/ repo_url: https://github.com/NVIDIA-NeMo/DataDesigner nav: - Getting Started: - Welcome: index.md - Contributing: CONTRIBUTING.md - Concepts: - Columns: concepts/columns.md - Seed Datasets: concepts/seed-datasets.md - Agent Rollout Ingestion: concepts/agent-rollout-ingestion.md - Models: - Default Model Settings: concepts/models/default-model-settings.md - Configure with the CLI: concepts/models/configure-model-settings-with-the-cli.md - Custom Model Settings: concepts/models/custom-model-settings.md - Model Providers: concepts/models/model-providers.md - Model Configs: concepts/models/model-configs.md - Inference Parameters: concepts/models/inference-parameters.md - Custom Columns: concepts/custom_columns.md - Validators: concepts/validators.md - Processors: concepts/processors.md - Workflow Chaining: concepts/workflow-chaining.md - Person Sampling: concepts/person_sampling.md - Traces: concepts/traces.md - Tool Use & MCP: - Overview: concepts/tool_use_and_mcp.md - MCP Providers: concepts/mcp/mcp-providers.md - Tool Configs: concepts/mcp/tool-configs.md - Enabling Tools: concepts/mcp/enabling-tools.md - CLI Configuration: concepts/mcp/configure-mcp-cli.md - Safety & Limits: concepts/mcp/safety-and-limits.md - Architecture & Performance: concepts/architecture-and-performance.md - Deployment Options: concepts/deployment-options.md - Security: concepts/security.md - Tutorials: - Overview: notebooks/README.md - The Basics: notebooks/1-the-basics.ipynb - Structured Outputs, Jinja Expressions, and Conditional Generation: notebooks/2-structured-outputs-and-jinja-expressions.ipynb - Seeding with an External Dataset: notebooks/3-seeding-with-a-dataset.ipynb - Providing Images as Context: notebooks/4-providing-images-as-context.ipynb - Generating Images: notebooks/5-generating-images.ipynb - Image-to-Image Editing: notebooks/6-editing-images-with-image-context.ipynb - Recipes: - Recipe Cards: recipes/cards.md - Code Generation: - Text to Python: recipes/code_generation/text_to_python.md - Text to SQL: recipes/code_generation/text_to_sql.md - "Nemotron Super Text to SQL": recipes/code_generation/enterprise_text_to_sql.md - Plugin Development: - Markdown Section Seed Reader Plugin: recipes/plugin_development/markdown_seed_reader.md - QA and Chat: - Product Info QA: recipes/qa_and_chat/product_info_qa.md - Multi-Turn Chat: recipes/qa_and_chat/multi_turn_chat.md - Trace Ingestion: - Agent Rollout Trace Distillation: recipes/trace_ingestion/agent_rollout_distillation.md - MCP and Tool Use: - "Basic MCP Tool Use": recipes/mcp_and_tooluse/basic_mcp.md - "PDF Document QA": recipes/mcp_and_tooluse/pdf_qa.md - "Nemotron Super Search Agent": recipes/mcp_and_tooluse/search_agent.md - VLM Long-Document Understanding: - "Seed Dataset Preparation": recipes/vlm_long_doc/seed_dataset_preparation.md - "Nemotron Parse OCR": recipes/vlm_long_doc/nemotron_parse_ocr.md - "Text QA from OCR Transcripts": recipes/vlm_long_doc/text_qa.md - "Page Classification": recipes/vlm_long_doc/page_classification.md - "Visual QA": recipes/vlm_long_doc/visual_qa.md - "Single-Page QA": recipes/vlm_long_doc/single_page_qa.md - "Multi-Page Windowed QA": recipes/vlm_long_doc/multi_page_windowed_qa.md - "Whole-Document QA": recipes/vlm_long_doc/whole_document_qa.md - "Frontier Judge QA Filter": recipes/vlm_long_doc/frontier_judge.md - Plugins: - Overview: plugins/overview.md - Build Your Own: plugins/build_your_own.md - Using Models: plugins/models.md - Discover Plugins: plugins/discover.md - Dev Notes: # NOTE: Order is most recent -> oldest (so sidebar shows recent first!) - devnotes/index.md - Retriever SDG Plugin: devnotes/posts/retrieval-sdg-toolkit.md - Have It Your Way: devnotes/posts/have-it-your-way.md - VLM Long Document Understanding: devnotes/posts/vlm-long-document-understanding.md - Push Datasets to Hugging Face Hub: devnotes/posts/push-datasets-to-hugging-face-hub.md - "Text-to-SQL for Nemotron Super": devnotes/posts/text-to-sql.md - "Async All the Way Down": devnotes/posts/async-all-the-way-down.md - Owning the Model Stack: devnotes/posts/owning-the-model-stack.md - Data Designer Got Skills: devnotes/posts/data-designer-got-skills.md - Search Agent: devnotes/posts/search-agent.md - Structured Outputs from Nemotron: devnotes/posts/structured-outputs-from-nemotron.md - Deep Research Trajectories: devnotes/posts/deep-research-trajectories.md - Design Principles: devnotes/posts/design-principles.md - RQA Dataset: devnotes/posts/rqa.md theme: name: material custom_dir: docs/overrides font: text: Roboto code: Fira Code icon: logo: fontawesome/solid/palette repo: fontawesome/brands/github-alt favicon: assets/palette-favicon.png palette: - media: "(prefers-color-scheme: dark)" scheme: slate primary: black toggle: icon: material/lightbulb-outline name: Switch to light mode - media: "(prefers-color-scheme: light)" scheme: default primary: black toggle: icon: material/lightbulb name: Switch to dark mode features: - navigation.path - navigation.footer - navigation.indexes - content.code.copy - content.code.select - content.code.annotate extra: version: provider: mike alias: true default: latest watch: - docs/ plugins: - search - blog: blog_dir: devnotes blog_toc: true post_date_format: long post_url_format: "{slug}" categories: false archive: true archive_toc: true - mike: alias_type: symlink canonical_version: latest - mkdocs-jupyter: execute: false include_requirejs: true ignore_h1_titles: True include_source: True ignore: - "assets/recipes/**/*.py" extra_css: - css/style.css extra_javascript: - js/toc-toggle.js markdown_extensions: - tables - pymdownx.superfences - attr_list - md_in_html - admonition - pymdownx.snippets: base_path: - docs/ - . url_download: true - pymdownx.highlight: pygments_lang_class: true use_pygments: true - pymdownx.tabbed: alternate_style: true - pymdownx.emoji: emoji_index: !!python/name:material.extensions.emoji.twemoji emoji_generator: !!python/name:material.extensions.emoji.to_svg