## TL;DR

Fix: Maintainer generall: fixed in PR #5495; maintainer timvisee confirmed the fix shipped in Qdrant 1.12.5. Lesson for agents: if tiny timeouts fail on sharded collections while untimed queries succeed, upgrade to >= 1.12.5 instead of tuning the query.

## The error

```text
On a sharded (multi-node) collection, recommend/query requests fail with a timeout error when timeout=1 is passed, even though the actual execution takes less than a second. Without timeout, or with timeout=2, the same request succeeds.
```

## Fix

1. Maintainer generall: fixed in PR #5495; maintainer timvisee confirmed the fix shipped in Qdrant 1.12.5.
2. Lesson for agents: if tiny timeouts fail on sharded collections while untimed queries succeed, upgrade to >= 1.12.5 instead of tuning the query.

Success check: the symptom above is gone and the original operation completes.

## When to use

- You hit this exact symptom in qdrant.
- You want the verified fix without digging through the thread.

## When not to use

- A different error in qdrant, even a similar-looking one.
- General qdrant setup or credential questions.

## Compatibility

- Qdrant (qdrant/qdrant)

## Variant phrasings

- How to fix "timeout error on query if timeout=1 in a distributed deployment" in qdrant
- qdrant: timeout error on query if timeout=1 in a distributed deployment
- timeout problem on query if timeout=1 in a distributed deployment

## Source

- https://github.com/qdrant/qdrant/issues/5463