Docs to FAQ Lab

cd apps/experiments/docs-to-faq-lab
pnpm install
pnpm dev

Docs to FAQ Lab turns markdown into FAQ pairs via generateObject. When Upstash Redis env vars are present, results are cached by SHA-256 of the content with a TTL. Without Redis, every request regenerates (no fabricated cache hits). Missing AI keys return 503.

FeaturesCopy Anchor Link

• Markdown - FAQ – up to 12 Q/A pairs from capped docs.
• Redis content-hash cache – TTL cache when Redis is configured.
• Cache miss transparency – UI shows hit/miss and backend.
• Sample docs – Redis cache lab snippet.
• Honest 503 when AI is unavailable.

Server ReferenceCopy Anchor Link

POST /api/faqCopy Anchor Link

{ "markdown": "# Title\n..." }

Success (200)Copy Anchor Link

{
  "faqs": [{ "question": "...", "answer": "..." }],
  "cached": false,
  "cache": "redis",
  "provider": "ai-gateway",
  "ttlSeconds": 3600
}

Implementation DetailsCopy Anchor Link

Use CasesCopy Anchor Link

• Learn composition patterns for this lab’s stack.
• Prototype before wiring production auth and quotas.
• Deploy the standalone app as a reference implementation.

LimitationsCopy Anchor Link

• Demo-scale caps on input size and output counts.
• No auth / rate limits on public deploys.
• Model quality depends on input clarity.

Use in your projectCopy Anchor Link

Copy the Route Handler and logic.ts helpers from apps/experiments/docs-to-faq-lab/. Wire your own persistence and auth as needed.

DeploymentCopy Anchor Link

Deploy on Vercel

Local DevelopmentCopy Anchor Link

cd apps/experiments/docs-to-faq-lab
pnpm install
pnpm dev

ConfigurationCopy Anchor Link

Vercel / Next.js Features UsedCopy Anchor Link

• AI SDK generateObject
• Upstash Redis
• Route Handlers
• Zod

Next StepsCopy Anchor Link