akb_search
Find relevant documents by combining semantic and keyword search, then access full content via returned URIs.
Instructions
Search documents with hybrid retrieval — dense vector (semantic) fused with BM25 sparse (keyword) via Reciprocal Rank Fusion. Handles both natural-language questions and short keyword queries well. For exact string / regex matches (code, URLs, version numbers) prefer akb_grep. Returns each hit's uri; use akb_drill_down or akb_get with that URI for full content. Response reports returned (in results) and total_matches (size of the deduped prefetch pool — NOT a corpus-wide hit count; vector ANN is top-K only). When truncated=true the prefetch pool was capped, meaning the corpus may hold more hits than reported — switch to akb_grep with count_only=true for an exact literal-substring count, or refine the query. When degraded=true the retrieval index hit a transient failure (vector-store outage or a degraded leg), so results may be incomplete or empty — this is NOT a genuine zero-match; degradation_reason names the cause. Retry shortly, or fall back to akb_grep for a literal search.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| tags | No | Filter by tags | |
| type | No | Filter by document type (any string). Common values: note, report, decision, spec, plan, session, task, reference, skill. | |
| limit | No | ||
| query | Yes | Natural language search query | |
| vault | No | Limit search to a specific vault | |
| collection | No | Limit search to a specific collection | |
| source_uris | No | Restrict the search to a specific set of already-known resources by their canonical akb:// URIs (e.g. from a previous akb_search / akb_browse). Hybrid retrieval (dense + BM25 + ranking) runs only inside this set, intersected with the other filters and your access. Omit for the normal whole-vault search. | |
| include_archived | No | Include archived documents. Default false — `status: archived` docs are hidden from search. |