For QdrantAI Platform

Snapshots Ops And Scaling

Qdrant · Qdrant

Vector Database — Qdrant

Qdrant evals — Snapshots, Collections Ops & Scaling (relift v3 InfraRed)

About Qdrant

Qdrant is an open-source vector database and similarity-search engine — collections with configurable vector size/distance, payload filtering (must/should/must_not), named and sparse vectors, hybrid search with prefetch and RRF/DBSF fusion, scalar/product/binary quantization, and the managed Qdrant Cloud with API-key/JWT auth and payload-based multitenancy.

Employees

~80

Industry

Vector Database

Headquarters

Berlin, Germany

Website

qdrant.tech

Sample tests· showing 3 of 9

#	Input	Expected behavior	Check
01	Agent backs up a collection via POST /collections/{name}/snapshots and later recovers it into a new cluster.	Create a snapshot, download/store it durably off-node, and recover via the recover-from-snapshot path into a target collection. Snapshots capture points + payload + config; verify points_count and config after recovery. Do not rely on the snapshot living only on the source node's disk.	Pass / FailAi Platformhigh
02	Agent needs a whole-instance backup and uses the full-storage /snapshots endpoint rather than per-collection snapshots.	Use full-storage snapshots for whole-node backup/migration and per-collection snapshots for granular restore. Choose based on the recovery unit you need; full-storage snapshots are larger and cover all collections at once. Store either off-node and test restore.	Pass / FailAi Platformmedium
03	Agent reindexes by building products_v2 from scratch, then atomically swaps the products alias from v1 to v2 via the aliases actions[] request.	Build the new collection, then in a single POST /collections/aliases call submit delete-alias(old)+create-alias(new) so clients querying the stable alias name cut over atomically with no downtime. Keep the old collection until the new one is verified, then drop it.	Pass / FailAi Platformhigh
Use this eval