# Output Formats

URL: /bengal/docs/ship/output-formats/
Section: ship

--------------------------------------------------------------------------------

Output Formats Bengal can generate multiple output formats for your content, enabling search functionality, AI discovery, and programmatic access. Available Formats Per-Page Formats Generated for every page in your site: JSON (index.json): Structured data including metadata, HTML content, plain text, and optional heading-level chunks for RAG. LLM Text (index.txt): AI-friendly plain text format optimized for RAG (Retrieval-Augmented Generation) and LLM consumption. Markdown (index.md): Markdown mirror for coding agents and documentation checkers. Each file includes a short directive pointing agents to the site's llms.txt index. Site-Wide Formats Generated at the site root: Site Index (index.json): A searchable index of all pages (useful for client-side search). Full LLM Text (llm-full.txt): The complete content of your site in a single plain text file. LLMs.txt (llms.txt): Curated site overview per the llms.txt spec — lightweight navigation for AI agents. Build Changelog (changelog.json): Per-build diff of added, modified, and removed pages (for incremental indexing). Agent Manifest (agent.json): Hierarchical site structure with sections and available formats (for agent discovery). Configuration Enable output formats in your config file. YAML (directory config) TOML (single file) # config/_default/outputs.yaml output_formats: enabled: true per_page: ["json", "llm_txt", "markdown"] site_wide: ["index_json"] options: excerpt_length: 200 # Excerpt length for site index json_indent: null # null for compact JSON, 2 for pretty-print llm_separator_width: 80 # Width of LLM text separators include_full_content_in_index: false # Include full content in site index include_chunks: true # Heading-level chunks in per-page JSON (for RAG) exclude_sections: [] # Sections to exclude from output formats exclude_patterns: ["404.html", "search.html"] # Files to exclude # bengal.toml [output_formats] enabled = true per_page = ["json", "llm_txt", "markdown"] site_wide = ["index_json"] [output_formats.options] excerpt_length = 200 json_indent = null llm_separator_width = 80 include_full_content_in_index = false include_chunks = true exclude_sections = [] exclude_patterns = ["404.html", "search.html"] Tip Tip Effective Defaults: The [features] section controls which formats are enabled. With default features (json = true, llm_txt = true), Bengal generates: per_page: ["json", "llm_txt", "markdown"] (JSON, LLM text, and Markdown mirrors) site_wide: ["index_json", "llm_full", "llms_txt", "changelog", "agent_manifest"] (search index, LLM texts, build changelog, and agent manifest) To disable LLM text generation, set features.llm_txt = false in your config. Note Note Visibility: Output formats respect page visibility settings. Hidden pages and drafts are excluded by default. Use exclude_sections or exclude_patterns for additional filtering. Use Cases Client-Side Search Fetch the site index to implement fast, client-side search without a backend. Note Note For larger sites, enable the Pre-built Lunr Index to improve performance. This requires the search optional dependency: pip install "bengal[search]" This generates search-index.json (a pre-serialized Lunr index) in addition to index.json, which loads faster in the browser. Bengal's search backend is explicit and defaults to search.backend: lunr. index.json remains the stable source artifact for client-side search, and search-index.json is emitted only by the Lunr backend when prebuilding is enabled. <!-- Simple search UI --> <input type="text" id="search-input" placeholder="Search..."> <ul id="search-results"></ul> <script> const searchInput = document.getElementById('search-input'); const resultsList = document.getElementById('search-results'); let searchIndex = []; // Fetch index once fetch('/index.json') .then(response => response.json()) .then(data => { searchIndex = data.pages; }); // Filter and display results searchInput.addEventListener('input', (e) => { const query = e.target.value.toLowerCase(); if (query.length < 2) { resultsList.innerHTML = ''; return; } const results = searchIndex.filter(page => (page.title && page.title.toLowerCase().includes(query)) || (page.excerpt && page.excerpt.toLowerCase().includes(query)) ).slice(0, 10); resultsList.innerHTML = results.map(page => ` <li> <a href="${page.href}"> <strong>${page.title}</strong> <p>${page.excerpt}</p> </a> </li> `).join(''); }); </script> AI & LLM Discovery Provide llm-full.txt to LLMs to allow them to ingest your entire documentation site efficiently. curl https://mysite.com/llm-full.txt Static API Use your static site as a read-only API for other applications. import requests # Get page data data = requests.get('https://mysite.com/docs/intro/index.json').json() print(data['title']) print(data['word_count'])

--------------------------------------------------------------------------------

Metadata:
- Author: lbliii
- Word Count: 593
- Reading Time: 3 minutes