mkdocs.yml

site_name: Systematically Improving RAG Applications
site_url: https://567-labs.github.io/systematically-improving-rag/
theme:
  name: material
  custom_dir: docs/overrides
  palette:
    - scheme: slate
      primary: black
      accent: black
      toggle:
        icon: material/weather-night
        name: Switch to light mode
    - scheme: default
      primary: indigo
      accent: indigo
      toggle:
        icon: material/weather-sunny
        name: Switch to dark mode
  features:
    - announce.dismiss
    - navigation.instant
    - navigation.tracking
    - navigation.expand
    - navigation.indexes
    - navigation.sections
    - navigation.tabs
    - navigation.top
    - navigation.footer
    - search.highlight
    - search.share
    - search.suggest
    - toc.follow
    - content.code.copy
    - content.code.annotate
  icon:
    repo: fontawesome/brands/github

nav:
  - "Home": "index.md"
  - "Book":
      - "Overview": "book/index.md"
      - "Book 1: Foundations":
          - "Chapter 0: Introduction": "book/chapter0.md"
          - "Chapter 1: Evaluation-First Development": "book/chapter1.md"
          - "Chapter 2: Training Data and Fine-Tuning": "book/chapter2.md"
      - "Book 2: User-Centric Design":
          - "Chapter 3: Feedback Systems and UX": "book/chapter3.md"
          - "Chapter 4: Query Understanding": "book/chapter4.md"
      - "Book 3: Architecture and Production":
          - "Chapter 5: Specialized Retrieval": "book/chapter5.md"
          - "Chapter 6: Query Routing": "book/chapter6.md"
          - "Chapter 7: Production Operations": "book/chapter7.md"
      - "Book 4: Advanced Topics":
          - "Chapter 8: Hybrid Search": "book/chapter8.md"
          - "Chapter 9: Context Window Management": "book/chapter9.md"
      - "Appendices":
          - "A: Mathematical Foundations": "book/appendix-math.md"
          - "B: Algorithms Reference": "book/appendix-algorithms.md"
          - "C: Benchmarking": "book/appendix-benchmarks.md"
          - "D: Debugging RAG Systems": "book/appendix-debugging.md"
      - "Supporting Materials":
          - "How to Use This Book": "book/how-to-use.md"
          - "Glossary": "book/glossary.md"
          - "Quick Reference": "book/quick-reference.md"
      - "Case Studies":
          - "Construction Company": "book/case-study-construction.md"
          - "Voice AI": "book/case-study-voice-ai.md"
          - "WildChat": "book/case-study-wildchat.md"
  - "Workshops":
      - "Overview": "workshops/index.md"
      - "How to Use This Book": "workshops/how-to-use.md"
      - "Introduction": "workshops/chapter0.md"
      - "Chapter 1: Starting the Flywheel":
          - "Overview": "workshops/chapter1.md"
      - "Chapter 2: From Evaluation to Enhancement":
          - "Overview": "workshops/chapter2.md"
      - "Chapter 3: User Experience":
          - "Feedback Collection": "workshops/chapter3-1.md"
          - "Overcoming Latency": "workshops/chapter3-2.md"
          - "Quality of Life": "workshops/chapter3-3.md"
      - "Chapter 4: Topic Modeling":
          - "Analysis": "workshops/chapter4-1.md"
          - "Prioritization": "workshops/chapter4-2.md"
      - "Chapter 5: Multimodal Capabilities":
          - "Understanding": "workshops/chapter5-1.md"
          - "Implementation": "workshops/chapter5-2.md"
      - "Chapter 6: Architecture":
          - "Routing": "workshops/chapter6-1.md"
          - "Tools": "workshops/chapter6-2.md"
          - "Improvement": "workshops/chapter6-3.md"
      - "Chapter 7: Production":
          - "Overview": "workshops/chapter7.md"
      - "Reference":
          - "Glossary": "workshops/glossary.md"
          - "Quick Reference": "workshops/quick-reference.md"
          - "Exercises": "workshops/exercises.md"
  - "Office Hours":
      - "office-hours/index.md"
      - "FAQ": "office-hours/faq.md"
      - "Chapter 1: Starting the Flywheel":
          - "Cohort 2 - Week 1": "office-hours/cohort2/week1-summary.md"
          - "Cohort 3 - Session 1": "office-hours/cohort3/week-1-1.md"
          - "Cohort 3 - Session 2": "office-hours/cohort3/week-1-2.md"
      - "Chapter 2: From Evaluation to Enhancement":
          - "Cohort 2 - Week 2": "office-hours/cohort2/week2-summary.md"
          - "Cohort 3 - Session 1": "office-hours/cohort3/week-2-1.md"
          - "Cohort 3 - Session 2": "office-hours/cohort3/week-2-2.md"
      - "Chapter 3: User Experience":
          - "Cohort 2 - Week 3": "office-hours/cohort2/week3-summary.md"
          - "Cohort 3 - Session 1": "office-hours/cohort3/week-3-1.md"
      - "Chapter 4: Topic Modeling":
          - "Cohort 2 - Week 4": "office-hours/cohort2/week4-summary.md"
          - "Cohort 3 - Session 1": "office-hours/cohort3/week-4-1.md"
          - "Cohort 3 - Session 2": "office-hours/cohort3/week-4-2.md"
      - "Chapter 5: Multimodal Capabilities":
          - "Cohort 2 - Week 5": "office-hours/cohort2/week5-summary.md"
          - "Cohort 3 - Session 1": "office-hours/cohort3/week-5-1.md"
          - "Cohort 3 - Session 2": "office-hours/cohort3/week-5-2.md"
      - "Chapter 6: Architecture":
          - "Cohort 2 - Week 6": "office-hours/cohort2/week6-summary.md"
  - "Talks":
      - "Overview": "talks/index.md"
      - "Search / Indexing / Chunking":
          - "TurboPuffer: Object Storage-First Vector Database Architecture (Simon, TurboPuffer)": "talks/turbopuffer-engine.md"
          - "Text Chunking Strategies (Anton, ChromaDB)": "talks/chromadb-anton-chunking.md"
          - "Lexical Search in RAG Applications (John Berryman)": "talks/john-lexical-search.md"
          - "Query Routing for RAG Systems (Anton, ChromaDB)": "talks/query-routing-anton.md"
          - "Why Google Search Sucks for AI (Will Bryk, Exa)": "talks/semantic-search-exa-will-bryk.md"
          - "How OpenBB Ditched APIs and Put RAG in the Browser (Michael Struwig)": "talks/rag-without-apis-browser-michael-struwig.md"
          - "Billion Scale vector search with TurboPuffer (Simon, TurboPuffer)": "talks/turbopuffer-engine.md"
      - "Finetuning":
          - "Building Custom Embedding Models Per Customer (Manav, Glean)": "talks/glean-manav.md"
          - "The 12% RAG Performance Boost You're Missing (Ayush, LanceDB)": "talks/fine-tuning-rerankers-embeddings-ayush-lancedb.md"
          - "Stop Trusting MTEB Rankings (Kelly Hong, Chroma)": "talks/embedding-performance-generative-evals-kelly-hong.md"
      - "Monitoring":
          - "Why Your AI Is Failing in Production (Ben & Sidhant)": "talks/online-evals-production-monitoring-ben-sidhant.md"
          - "The RAG Mistakes That Are Killing Your AI (Skylar Payne)": "talks/rag-antipatterns-skylar-payne.md"
          - "How Zapier 4x'd Their AI Feedback Collection (Vitor)": "talks/zapier-vitor-evals.md"
          - "Domain Experts: The Lever for Vertical AI (Chris Lovejoy, Anterior)": "talks/chris-lovejoy-domain-expert-vertical-ai.md"
      - "Coding Agents":
          - "Why Cline Ditched RAG for Direct Code Reading (Nik Pash)": "talks/rag-is-dead-cline-nik.md"
          - "Grep Beat Embeddings on SWE-Bench (Colin Flaherty, Augment)": "talks/colin-rag-agents.md"
          - "Agentic RAG from first principles (Beyang Liu, Sourcegraph)": "talks/sourcegraph-agentic-code-agent-rag.md"
          - "Why Devin does not use multi-agents (Walden Yan)": "talks/devin-cognition-multi-agents.md"
      - "Document Processing":
          - "Why Most Document Parsing Sucks (Adit, Reducto)": "talks/reducto-docs-adit.md"
          - "Encoder Stacking and Multi-Modal Retrieval (Daniel, Superlinked)": "talks/superlinked-encoder-stacking.md"
          - "How Extend Achieves 95%+ Document Automation (Eli Badgio)": "talks/extend-document-automation.md"

# --- Enhancements for mkdocs.yml ---
# 1. Add recommended plugins for better UX, SEO, and maintainability
# 2. Add markdown extensions for richer content
# 3. Add comments and placeholders for further improvements
# 4. Do not remove existing configuration

# --- Recommended Plugins ---
plugins:
  - search
  - mermaid2

# --- Markdown Extensions ---
markdown_extensions:
  - pymdownx.highlight
  - pymdownx.superfences
  - pymdownx.caret # Insertions, deletions, highlights
  - pymdownx.snippets # Reusable markdown snippets
  - pymdownx.inlinehilite # Inline code highlighting
  # - pymdownx.emoji        # Emoji shortcodes (optional)
  - admonition
  - pymdownx.details
  - pymdownx.tabbed
  - attr_list
  - md_in_html
  - pymdownx.tasklist
  - pymdownx.arithmatex

# --- Navigation Suggestions ---
# - Ensure each major section starts with an overview/landing page
# - Use .pages files for custom ordering if awesome-pages is enabled
# - Group long lists under collapsible headers for clarity

# --- Content & Authoring Utilities ---
# - Add a CONTRIBUTING.md for contributor guidelines (see below)
# - Add a 404.md for a custom not-found page (see below)
# - Add a robots.txt for SEO control (see below)

# --- Example: Custom 404 Page ---
# Create docs/404.md with helpful navigation links
# Then add to nav if desired:
#   - '404': '404.md'

# --- Example: robots.txt ---
# Place docs/robots.txt to control search engine indexing

# --- Example: CONTRIBUTING.md ---
# Place CONTRIBUTING.md in the root or docs/ for contributor guidelines

# --- End Enhancements ---

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

extra_css:
  - stylesheets/extra.css

extra:
  analytics:
    provider: google
    property: !ENV GOOGLE_ANALYTICS_KEY