{
 "schema_version": 1,
 "generated": "2026-10-25",
 "id": "firecrawl-firecrawl--crawl-a-docs-site-into-a-knowledge-base",
 "repo": "firecrawl/firecrawl",
 "repo_url": "https://github.com/firecrawl/firecrawl",
 "repo_slug": "firecrawl-firecrawl",
 "title": "Crawl a whole docs site into a knowledge base",
 "page_title": "How to crawl a whole docs site into a knowledge base with Firecrawl",
 "summary": "Map every URL on a site, then crawl it to markdown in one job for RAG or offline reading.",
 "who": "Someone building a chatbot or search over a product's documentation.",
 "problem": "Copying a docs site page by page is slow and misses pages.",
 "outcome": "Markdown for every page of the site, ready to chunk and index.",
 "steps": [
  "Discover pages first with the Map endpoint, optionally with `search` to rank URLs by relevance",
  "Start a crawl with a POST to the v2 crawl endpoint with the site URL, a page `limit` and markdown format",
  "Poll the returned job ID until the crawl finishes",
  "Chunk and index the markdown in your vector store"
 ],
 "agent_prompt": "Use firecrawl/firecrawl to map <docs url>, then crawl up to <n> pages as markdown, save each page to ./kb/<slug>.md, and give me a count of pages and any that failed.",
 "agents": [
  "any"
 ],
 "difficulty": "Intermediate",
 "time": "30 minutes",
 "basis": "readme",
 "caveat": "Crawls use credits on the hosted plan; set a page limit before you start.",
 "category": "Data and analytics",
 "tags": [
  "Data and analytics"
 ],
 "lang": "typescript",
 "requirements": [
  "A Firecrawl API key from the hosted service, or a self-hosted instance",
  "Python, Node.js, or curl; or an MCP client such as Claude Code or Cursor"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.8,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/firecrawl-firecrawl/crawl-a-docs-site-into-a-knowledge-base/",
 "md": "https://dedupedai.com/use-cases/firecrawl-firecrawl/crawl-a-docs-site-into-a-knowledge-base/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/firecrawl-firecrawl--crawl-a-docs-site-into-a-knowledge-base.json",
 "api_version": "v1"
}