krzysztof/landing_page
1
0
Fork 0
mirror of https://github.com/qdrant/landing_page.git synced 2026-09-29 07:58:31 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #725 from qdrant/mjang-disk-space-reasons

Browse Source 
Support info from UI for disk space considerations
This commit is contained in:
Mike Jang
2024-03-18 05:47:16 -07:00
committed by GitHub
parent 9e4afd2dd7 e899d52733
commit 94ecd23a1b
1 changed files with 18 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
qdrant-landing/content/documentation/cloud/capacity-sizing.md
+18
View File
@@ -51,3 +51,21 @@ In this case you can estimate required memory size as follows:
```text
memory_size = number_of_active_vectors * vector_dimension * 4 bytes * 1.5
```
## Disk space
Clusters that support vector search require significant disk space. If you're
running low on disk space in your cluster, you can use the UI at
[cloud.qdrant.io](https://cloud.qdrant.io/) to **Scale Up** your cluster.
<aside role="status">If you use the Qdrant UI to increase the disk space in your cluster, you
cannot decrease that allocation later.</aside>
If you're running low on disk space, consider the following advantages:
- Larger Datasets: Supports larger datasets. With vector search,
larger datasets can improve the relevance and quality of search results.
- Improved Indexing: Supports the use of indexing strategies such as
HNSW (Hierarchical Navigable Small World).
- Caching: Improves speed when you cache frequently accessed data on disk.
- Backups and Redundancy: Allows more frequent backups. Perhaps the most important advantage.