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 tutorial

Browse Source
This commit is contained in:
Derrick Mwiti
2025-06-09 12:02:22 +03:00
parent 1a991c92ff
commit b9e9266dd8
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
qdrant-landing/content/documentation/advanced-tutorials/using-multivector-representations.md
+1 -1
View File
@@ -33,7 +33,7 @@ In multivector representations (such as those used by Late Interaction models li
- High RAM usage
- Slow insert times due to the complexity of maintaining the HNSW graph
However, because multivector search is typically used in the reranking stage (after a first-pass retrieval using dense vectors), there's often no need to index these token-level vectors with HNSW.
Because multivector search is usually part of reranking rather than initial retrieval, indexing token-level vectors with HNSW is often redundant.
Instead, they can be stored as multi-vector fields (without HNSW indexing) and used at query-time for reranking, which reduces resource overhead and improves performance.