Content RAG (Semantic Search)

Search your bucket content by meaning instead of exact keywords. Content RAG embeds your objects into a vector index so a natural-language query returns the most semantically relevant objects, even when the wording differs.

The POST /v3/buckets/:bucket_slug/ai/search endpoint embeds a query and returns the objects whose content is closest in meaning, ranked by similarity score. This is retrieval only (no answer generation) and requires a bucket write key.

Required parameters

• query — The natural-language search query. Results are ranked by semantic similarity to this text.

Optional parameters

• type — Restrict results to a single object type slug (e.g. blog-posts).
• locale — Restrict results to a single locale.
• status — Filter by object status (e.g. published, draft).
• limit — Maximum number of results to return. Default 10, maximum 50.
• min_score — Minimum similarity score (0–1). Results below this threshold are dropped. Default 0.

Powering Agents

The same retrieval powers Agents: when enabled, content and team agents can find objects by meaning with the search_content tool instead of scanning titles.