Retrieval API
A hosted API that takes a query and returns relevant, structured web content or search results — built for LLM/agent consumption rather than for rendering a human-facing results page.
Where a consumer search engine returns a page of links and ads for a person to click through, a retrieval API is designed to be called programmatically by an LLM or agent: it returns clean, structured content (often full page text, not just a snippet) optimized for grounding an answer or feeding a RAG pipeline. Some are neural/semantic search built specifically for this use case; others are wrappers around traditional search indexes exposed as an API. Key differentiators are freshness (how current the index is), content quality (full text vs. snippet-only), and whether results include structured metadata an agent can filter on.
Last verified: