Similar Notes
get_similarRead-onlyIdempotent
Retrieve notes semantically similar to a reference document using precomputed embeddings. Excludes the reference from results and requires semantic search setup.
Instructions
Find notes most semantically similar to the given document.
Uses stored embedding vectors — no re-embedding needed. The reference document is excluded from results. Requires semantic search to be configured (check 'stats' for semantic_search_available). Returns an empty list if embeddings are not configured (check 'embeddings_status') or the document has no stored vectors (call 'build_embeddings' to embed missing chunks).
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Relative path of the reference document (e.g. "notes/topic.md"). Case-sensitive. | |
| limit | No | Maximum number of similar notes to return (default 10). | |
| chunks_per_file | No | Maximum sections returned per file (default 2). Set to 1 for one best section per file. Must be >= 1. | |
| wait_for_pending_writes | No | When True, wait until your recent write/edit/delete/rename operations have been applied to the index before answering, so the results reflect those changes. Use it right after modifying notes when this read must see them (e.g. right after a write/edit/delete/rename whose effect this read should reflect). Default False answers immediately from the current index — almost always already up to date; inspect the response's ``_meta.index_stale`` field to tell whether a write was still in flight. Bounded by a server timeout (default 60s); on timeout it answers from the current index rather than waiting longer. |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |