Reka Research adds real-time web results to your AI app — so answers stay fresh, relevant, and grounded in current information.
Web search is on by default. Use these parameters to control how and where your agent searches:
Use max_uses to limit how many searches the agent can run per request. Once the limit’s reached, it reason based on with what it has.
Choose where the agent can — or can’t — search:
allowed_domains: Only search from this listblocked_domains: Never search from this listControl where your agent is allowed to search — and where it isn’t.
http://, https://, or www. — just write example.com.nytimes.com applies to all its subdomains too.allowed_domains and blocked_domains at the same time — doing so will trigger a validation error.Use user_location to set where the agent searches from. This helps it find local results and understand context better.