Metis · Memory Curator — Semantic Search
semantic_searchRetrieve relevant personal memories by searching across episodic, semantic, and procedural layers using vector similarity and keyword matching fused via reciprocal rank fusion.
Instructions
Search across memory layers using vector similarity + keyword RRF fusion.
Searches your personal MEMORY layers (episodic/semantic/procedural — things
you or Metis recorded), NOT your document library. For documents/PDFs use
search_pdf_knowledge; for reference metadata use search_library.
Retrieval pipeline (M5.8):
1. Embed the query.
2. Run vector similarity search on each requested layer.
3. Run keyword LIKE search on each layer.
4. Fuse results using Reciprocal Rank Fusion (RRF, k=60).
5. Return top_k deduplicated results ranked by fused score.
Args:
query: Natural language search query to embed and keyword-match.
layers: Comma-separated memory layers to search, drawn from 'episodic',
'semantic', and 'procedural'.
top_k: Number of fused results to return (default 5).
Returns:
A single TextContent listing the top fused results (layer, title, score,
timestamp, and a content preview), or a "no results" / error message.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| top_k | No | ||
| layers | No | episodic,semantic,procedural |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |