GlossaryRetrieval
Web retrieval API
An API that takes a query and returns ranked web documents in a format an LLM can consume.
A web retrieval API is the layer between an LLM/agent and the live web. Given a natural-language or keyword query, it returns ranked results with titles, URLs, snippets, and often full extracted content. The good ones expose options for scope (web / news / academic / etc.), structured output, and content extraction with highlighted spans. SiftQ, Exa, Tavily, Brave Search API, and Serper are all examples.