krzysztof/landing_page
1
0
Fork 0
mirror of https://github.com/qdrant/landing_page.git synced 2026-10-04 18:38:30 +02:00
Code Issues Packages Projects Releases Wiki Activity

Update qdrant-landing/content/blog/qdrant-1.14.x.md

Browse Source 
Co-authored-by: Kacper Łukawski <kacperlukawski@users.noreply.github.com>
This commit is contained in:
David Myriel
2025-03-26 10:51:58 +01:00
committed by GitHub
co-authored by Kacper Łukawski
parent 2524069f80
commit b21e9d2ab6
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
qdrant-landing/content/blog/qdrant-1.14.x.md
+1 -1
View File
@@ -119,7 +119,7 @@ POST /collections/{collection_name}/points/query
### Idea 3: Factor in Geographical Proximity
Let’s say you’re searching for a restaurant serving Currywurst. Sure, Berlin has some of the best, but you probably don’t want to spend two days traveling for a sausage covered in magical seasoning. The best match is the one that **balances the distance with a real-world geographical distance**. You want your users see relevant and conveniently located options.
Let’s say you’re searching for a restaurant serving Currywurst. Sure, Berlin has some of the best, but you probably don’t want to spend two days traveling for a sausage covered in magical seasoning. The best match is the one that **balances the distance in the vector space with a real-world geographical distance**. You want your users see relevant and conveniently located options.
This feature introduces a multi-objective optimization: combining semantic similarity with geographical proximity. Suppose each point has a `geo.location` payload field (latitude, longitude). You can use a `gauss_decay` function to clamp the distance into a 0–1 range and add that to your similarity score: