---
title: "Search"
sidebarTitle: "Overview"
description: "Recall the most relevant memories and source context"
icon: "/icons/hugeicons/book-open-01.svg"
---

`POST /ns/{namespace}/search` recalls the most useful memories and source chunks for a query. Hybrid search combines both by default; set `searchMode` to `memories` or `chunks` when your experience needs one result type.

Every option goes in the JSON request body: `query`, `searchMode`, `limit`, `threshold`, `filter`, `include`, `rerank`, and `rewriteQuery`.

<CodeGroup>
```ts TypeScript
const { results, searchTime } = await client.search("user_1", {
  query: "What did the user decide about the launch?",
  limit: 10,
})
```

```python Python
response = client.search("user_1", query="What did the user decide about the launch?", limit=10)
```

```bash curl
curl -X POST "https://api.supermemory.ai/ns/user_1/search" \
  -H "Authorization: Bearer $SUPERMEMORY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query":"What did the user decide about the launch?","limit":10}'
```
</CodeGroup>

Two defaults differ from the legacy API: `searchMode` defaults to `hybrid` (legacy `memories`) and `threshold` defaults to `0.3` (legacy `0.6`). Pass both explicitly if you need legacy-equivalent results.

See [search migration](/migration/api-v5-recall) and [typed filter migration](/migration/api-v5-filters).