mkdocs.yml

# Project information
site_name: Distilabel Docs
site_url: https://argilla-io.github.io/distilabel
site_author: Argilla, Inc.
site_description: Distilabel is an AI Feedback (AIF) framework for building datasets with and for LLMs.

# Repository
repo_name: argilla-io/distilabel
repo_url: https://github.com/argilla-io/distilabel
edit_uri: edit/main/docs/

extra:
  version:
    provider: mike
  social:
    - icon: fontawesome/brands/linkedin
      link: https://www.linkedin.com/company/argilla-io
    - icon: fontawesome/brands/x-twitter
      link: https://twitter.com/argilla_io
    - icon: fontawesome/brands/youtube
      link: https://www.youtube.com/channel/UCAIz8TmvQQrLqbD7sd-5S2A
    - icon: fontawesome/brands/discord
      link: http://hf.co/join/discord
  analytics:
    provider: plausible
    domain: distilabel.argilla.io
    feedback:
      title: Was this page helpful?
      ratings:
        - icon: material/thumb-up-outline
          name: This page was helpful
          data: 1
          note: >-
            Thanks for your feedback!
        - icon: material/thumb-down-outline
          name: This page could be improved
          data: 0
          note: >-
            Thanks for your feedback! Help us improve this page by
            <a href="https://github.com/argilla-io/distilabel/issues/new/?title=[Feedback]+{title}+-+{url}" target="_blank" rel="noopener">opening a GitHub issue</a>.
extra_css:
  - stylesheets/extra.css

extra_javascript:
  - javascripts/mathjax.js
  - https://polyfill.io/v3/polyfill.min.js?features=es6
  - https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js

theme:
  name: material
  logo: assets/logo.svg
  favicon: assets/logo.svg
  icon:
    repo: fontawesome/brands/github
  features:
    - navigation.instant
    - navigation.sections
    - navigation.tabs
    - navigation.footer
    - navigation.top
    - navigation.tracking
    - navigation.path
    - header.autohide # header disappears as you scroll
    - content.code.copy
    - content.code.annotate
    - content.tabs.link
    - content.action.edit
    - toc.follow
    - search.suggest
    - search.highlight
    - search.share

  palette:
    - media: "(prefers-color-scheme)"
      primary: white
      toggle:
        icon: material/brightness-auto
        name: Switch to light mode
    - media: "(prefers-color-scheme: light)"
      scheme: default
      primary: custom
      toggle:
        icon: material/brightness-7
        name: Switch to dark mode

    # Palette toggle for dark mode
    - media: "(prefers-color-scheme: dark)"
      scheme: slate
      primary: custom
      toggle:
        icon: material/brightness-4
        name: Switch to system preference

watch:
  - src/distilabel

strict: true

# Extensions
markdown_extensions:
  - attr_list
  - md_in_html
  - admonition
  - pymdownx.superfences
  - pymdownx.arithmatex:
      generic: true
  - pymdownx.highlight:
      anchor_linenums: true
      line_spans: __span
      pygments_lang_class: true
  - pymdownx.inlinehilite
  - pymdownx.keys
  - pymdownx.superfences:
      custom_fences:
        - name: mermaid
          class: mermaid
          format: !!python/name:pymdownx.superfences.fence_code_format
  - pymdownx.snippets:
      check_paths: true
      base_path: [examples/, docs/, "."]
  - pymdownx.details
  - pymdownx.tabbed:
      alternate_style: true
  - pymdownx.emoji:
      emoji_index: !!python/name:material.extensions.emoji.twemoji
      emoji_generator: !!python/name:material.extensions.emoji.to_svg
  - footnotes
  - toc:
      permalink: true

plugins:
  - search
  - autorefs # Cross-links to headings
  - gen-files:
      scripts:
        - docs/scripts/gen_popular_issues.py
  - section-index
  - mkdocstrings:
      handlers:
        python:
          setup_commands:
            - import sys; sys.path.insert(0, 'src') # API references are built from source
          options:
            show_inheritance_diagram: false
            show_source: true # include source code
            # Headings
            heading_level: 3
            show_root_heading: true # show the python path of the class
            show_root_toc_entry: true # show the toc entry for the root class
            show_root_full_path: false # display "diffrax.asdf" not just "asdf"
            show_object_full_path: false # display "diffrax.asdf" not just "asdf"
            show_symbol_type_heading: true
            show_symbol_type_toc: true
            # Members
            inherited_members: false # allow looking up inherited methods
            members_order: source # order methods according to their order of definition in the source code, not alphabetical order
            show_labels: true
            # Docstring
            docstring_style: google # more info: https://sphinxcontrib-napoleon.readthedocs.io/en/latest/example_google.html
            show_if_no_docstring: false
            # Signature
            separate_signature: false
            show_signature_annotations: false
  - social
  - mknotebooks
  - material-plausible
  - glightbox
  - distilabel/components-gallery:
      add_after_page: How-to guides

nav:
  - Distilabel: "index.md"
  - Getting started:
      - Quickstart: "sections/getting_started/quickstart.md"
      - Installation: "sections/getting_started/installation.md"
      - FAQ: "sections/getting_started/faq.md"
  - How-to guides:
      - "sections/how_to_guides/index.md"
      - Basic:
          - Steps for processing data:
              - "sections/how_to_guides/basic/step/index.md"
              - GeneratorStep: "sections/how_to_guides/basic/step/generator_step.md"
              - GlobalStep: "sections/how_to_guides/basic/step/global_step.md"
          - Tasks for generating and judging with LLMs:
              - "sections/how_to_guides/basic/task/index.md"
              - GeneratorTask: "sections/how_to_guides/basic/task/generator_task.md"
              - ImageTask: "sections/how_to_guides/basic/task/image_task.md"
          - Executing Tasks with LLMs: "sections/how_to_guides/basic/llm/index.md"
          - Execute Steps and Tasks in a Pipeline: "sections/how_to_guides/basic/pipeline/index.md"
      - Advanced:
          - The Distiset dataset object: "sections/how_to_guides/advanced/distiset.md"
          - Pipeline cache: "sections/how_to_guides/advanced/caching.md"
          - Exporting data to Argilla: "sections/how_to_guides/advanced/argilla.md"
          - Structured data generation: "sections/how_to_guides/advanced/structured_generation.md"
          - Offline Batch Generation: "sections/how_to_guides/advanced/offline_batch_generation.md"
          - Specifying requirements for pipelines and steps: "sections/how_to_guides/advanced/pipeline_requirements.md"
          - Load groups and execution stages: "sections/how_to_guides/advanced/load_groups_and_execution_stages.md"
          - Using CLI to explore and re-run existing Pipelines: "sections/how_to_guides/advanced/cli/index.md"
          - Using a file system to pass data of batches between steps: "sections/how_to_guides/advanced/fs_to_pass_data.md"
          - Assigning resources to a step: "sections/how_to_guides/advanced/assigning_resources_to_step.md"
          - Saving step generated artifacts: "sections/how_to_guides/advanced/saving_step_generated_artifacts.md"
          - Serving an LLM for sharing it between several tasks: "sections/how_to_guides/advanced/serving_an_llm_for_reuse.md"
          - Scaling and distributing a pipeline with Ray: "sections/how_to_guides/advanced/scaling_with_ray.md"
  - Tutorials:
      - "sections/pipeline_samples/index.md"
      - Tutorials:
          - Generate a preference dataset: "sections/pipeline_samples/tutorials/generate_preference_dataset.ipynb"
          - Clean an existing preference dataset: "sections/pipeline_samples/tutorials/clean_existing_dataset.ipynb"
          - Synthetic data generation for fine-tuning custom retrieval and reranking models: "sections/pipeline_samples/tutorials/GenerateSentencePair.ipynb"
          - Generate synthetic text classification data: "sections/pipeline_samples/tutorials/generate_textcat_dataset.ipynb"
      - Papers:
          - DeepSeek Prover: "sections/pipeline_samples/papers/deepseek_prover.md"
          - DEITA: "sections/pipeline_samples/papers/deita.md"
          - Instruction Backtranslation: "sections/pipeline_samples/papers/instruction_backtranslation.md"
          - Prometheus 2: "sections/pipeline_samples/papers/prometheus.md"
          - UltraFeedback: "sections/pipeline_samples/papers/ultrafeedback.md"
          - APIGen: "sections/pipeline_samples/papers/apigen.md"
          - CLAIR: "sections/pipeline_samples/papers/clair.md"
          - Math Shepherd: "sections/pipeline_samples/papers/math_shepherd.md"
      - Examples:
          - Benchmarking with distilabel: "sections/pipeline_samples/examples/benchmarking_with_distilabel.md"
          - Structured generation with outlines: "sections/pipeline_samples/examples/llama_cpp_with_outlines.md"
          - Structured generation with instructor: "sections/pipeline_samples/examples/mistralai_with_instructor.md"
          - Create a social network with FinePersonas: "sections/pipeline_samples/examples/fine_personas_social_network.md"
          - Create questions and answers for a exam: "sections/pipeline_samples/examples/exam_questions.md"
          - Image generation with distilabel: "sections/pipeline_samples/examples/image_generation.md"
          - Text generation with images in distilabel: "sections/pipeline_samples/examples/text_generation_with_image.md"
  - API Reference:
      - Step:
          - "api/step/index.md"
          - GeneratorStep: "api/step/generator_step.md"
          - GlobalStep: "api/step/global_step.md"
          - "@step": "api/step/decorator.md"
          - StepResources: "api/step/resources.md"
          - Step Gallery:
              - Argilla: "api/step_gallery/argilla.md"
              - Hugging Face: "api/step_gallery/hugging_face.md"
              - Columns: "api/step_gallery/columns.md"
              - Extra: "api/step_gallery/extra.md"
      - Task:
          - "api/task/index.md"
          - GeneratorTask: "api/task/generator_task.md"
          - Task Gallery: "api/task/task_gallery.md"
      - LLM:
          - "api/models/llm/index.md"
          - LLM Gallery: "api/models/llm/llm_gallery.md"
      - Embedding:
          - "api/models/embedding/index.md"
          - Embedding Gallery: "api/models/embedding/embedding_gallery.md"
      - ImageGenerationModels:
          - "api/models/image_generation/index.md"
          - Image Generation Gallery: "api/models/image_generation/image_generation_gallery.md"
      - Pipeline:
          - "api/pipeline/index.md"
          - Routing Batch Function: "api/pipeline/routing_batch_function.md"
          - Step Wrapper: "api/pipeline/step_wrapper.md"
      - Mixins:
          - RuntimeParametersMixin: "api/mixins/runtime_parameters.md"
          - RequirementsMixin: "api/mixins/requirements.md"
      - Exceptions: "api/exceptions.md"
      - Errors: "api/errors.md"
      - Distiset: "api/distiset.md"
      - CLI: "api/cli.md"
      - Types: "api/typing.md"
  - Community:
      - sections/community/index.md
      - How to contribute?: sections/community/contributor.md
      - Developer Documentation: sections/community/developer_documentation.md
      - Issue dashboard: sections/community/popular_issues.md