RAG Mini Search

A minimal retrieval-augmented generation demo: embed a small corpus of experiment descriptions into Vectorize, retrieve top matches for a question, and generate a grounded answer with Workers AI plus cited source titles.

Features

• POST /seed - Embed and upsert demo experiment docs into Vectorize
• POST /ask - Question → retrieve → generate grounded answer
• Cited sources - Response includes matched experiment titles and scores
• Demo corpus - 10 experiment descriptions from this repo

API Reference

POST /seed

Load the demo document corpus into Vectorize. Run once after deploy or locally before asking questions.

Example Request

curl -X POST "https://your-worker.workers.dev/seed"

Success Response

{
  "seeded": 10,
  "documents": ["Is It Down", "Link Shortener", "Cloud AI Proxy"]
}

Error Codes

• 502 - Seeding failed (SEED_ERROR)

POST /ask

Ask a question against the indexed corpus.

Example Request

curl -X POST "https://your-worker.workers.dev/ask" \
  -H "Content-Type: application/json" \
  -d '{"question":"Which experiment uses Durable Objects?"}'

Success Response

{
  "question": "Which experiment uses Durable Objects?",
  "answer": "The Durable Counter experiment uses Durable Objects for a globally consistent counter (Durable Counter).",
  "sources": [{ "id": "durable-counter", "title": "Durable Counter", "score": 0.89 }]
}

Error Codes

• 400 - Invalid JSON (INVALID_BODY) or question (INVALID_QUESTION)
• 404 - No indexed documents; run POST /seed first (NOT_INDEXED)
• 502 - RAG pipeline error (RAG_ERROR)

Use Cases

• Learn Vectorize + Workers AI RAG patterns end-to-end
• Prototype documentation or support bots over a small corpus
• Compare embedding retrieval quality before scaling to larger indexes

Limitations

• Demo corpus is fixed (10 documents); not auto-synced with repo changes
• Must call POST /seed before POST /ask
• Requires Vectorize index rag-mini-search and Workers AI

Deployment

curl -X POST "https://your-worker.workers.dev/seed"

Local Development

cd apps/experiments/rag-mini-search
npm install
npm run dev
npm run seed

Configuration

Cloudflare Features Used

• Workers - Edge compute runtime
• Workers AI - Embeddings and text generation
• Vectorize - Vector search at the edge