mirror of
https://github.com/supermemoryai/supermemory.git
synced 2026-10-11 03:37:56 +00:00
3b84713097
Document every migrated workflow, request and response change, typed-filter conversion, verification strategy, and rollout step so agents can upgrade integrations deterministically.
12 lines
649 B
Text
12 lines
649 B
Text
---
|
|
title: "Search"
|
|
sidebarTitle: "Overview"
|
|
description: "Recall the most relevant memories and source context"
|
|
icon: "book-open"
|
|
---
|
|
|
|
`POST /ns/{namespace}/search` recalls the most useful memories and source chunks for a query. Hybrid search combines both by default; use `searchMode=memories` or `searchMode=chunks` when your experience needs one result type.
|
|
|
|
Tune relevance with threshold, reranking, query rewriting, filters, and related context in the request body. Result controls `limit` and `searchMode` belong in the query string.
|
|
|
|
See [search migration](/migration/api-v5-recall) and [typed filter migration](/migration/api-v5-filters).
|