akb_search
Search documents with hybrid retrieval combining dense vector and BM25 keyword search via Reciprocal Rank Fusion. Handles natural language and keyword queries, returning URIs of relevant hits.
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.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Natural language search query | |
| vault | No | Limit search to a specific vault | |
| collection | No | Limit search to a specific collection | |
| type | No | Filter by document type | |
| tags | No | Filter by tags | |
| limit | No | ||
| include_archived | No | Include archived documents. Default false — `status: archived` docs are hidden from search. | |
| 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. |