Use AI Search in a real application path
AI Search bindings let Workers search and chat with indexed content from Cloudflare AI Search instances.
A compact AI Search recipe with config and worker usage in one application path.
Use this as the copyable starter before threading the feature into a larger application.
- Config focus
- bindings.aiSearch
- Runtime shape
- or
- Best use
- search/chat flows where the app calls an AI Search instance or namespace from a Worker
Start by wiring the binding clearly in config
Smallest AI Search config
Build the application flow around the binding
Treat this as the app-level AI Search path: the route, event handler, or service module receives a real request and uses the binding to do useful work.
Keep product limits, remote ownership, and fallback behavior visible in the code around the binding instead of hiding everything behind a vague utility too early.
- Keep the first example short enough to paste into a new Worker.
- Cloudflare owns crawling, indexing, ranking, and hosted model behavior; local mocks only prove app control flow.
Search one AI Search instance
Keep production boundaries visible
- Config focus: bindings.aiSearch.
- Runtime shape: or .
- Best use: search/chat flows where the app calls an AI Search instance or namespace from a Worker.
Thread this into the next recipe
Once this smallest path works, add routing, generated types, and feature-specific abstraction in that order.
Previous
Testing AI Search
Test AI Search by choosing the local harness that matches the product boundary instead of reaching for Cloudflare by default.
Next
mTLS Certificates
Add the mTLS Certificates config, call from worker code, and start with the local test path Devflare supports.