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

add fixes

Browse Source
This commit is contained in:
David Myriel
2025-04-30 17:47:55 +02:00
parent 2333e7d010
commit a31e030091
1 changed files with 1 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
qdrant-landing/content/articles/vector-search-production.md
+1 -3
View File
@@ -149,7 +149,7 @@ Once all records are inserted, you can rebuild the index in a single pass. Consi
> By default, Qdrant uses up to 16 threads for indexing, but if you notice your CPU isn't being fully utilized during indexing, you can increase this number. > By default, Qdrant uses up to 16 threads for indexing, but if you notice your CPU isn't being fully utilized during indexing, you can increase this number.
✅ **Optimize batch size and concurrency:** Keep your batch size at the default (around 100) and instead increase the number of concurrent processes. Running 50-60 concurrent processes can significantly improve upload performance. Using just one or two processes won't allow you to see the true performance potential. ✅ **Use Batch Processes:** Increase the number of concurrent processes. Running 50-60 processes can significantly improve upload performance. Using just one or two processes won't allow you to see the true performance potential.
**Be patient with indexing:** After uploading large datasets, there's a waiting period for indexing to complete. This is normal and can take time depending on your dataset size. **Be patient with indexing:** After uploading large datasets, there's a waiting period for indexing to complete. This is normal and can take time depending on your dataset size.
@@ -509,8 +509,6 @@ For users of Qdrant's managed cloud service, there's an option to configure RBAC
❌ Don't keep outdated Qdrant versions running—**update regularly**. ❌ Don't keep outdated Qdrant versions running—**update regularly**.
❌ Resharding isn't the ultimate solution—**strike a balance between replica and shard counts.**
## Conclusion ## Conclusion
In conclusion, **vector search in production** isn't tied to a specific cloud provider or infrastructure. The same core principles of **careful configuration, robust ingestion/indexing, intelligent scaling, thorough backups, strong observability, and security** apply universally. By embracing these fundamentals, you'll deliver fast, reliable, and scalable search for your users, regardless of where your hardware or services run. In conclusion, **vector search in production** isn't tied to a specific cloud provider or infrastructure. The same core principles of **careful configuration, robust ingestion/indexing, intelligent scaling, thorough backups, strong observability, and security** apply universally. By embracing these fundamentals, you'll deliver fast, reliable, and scalable search for your users, regardless of where your hardware or services run.