Snapshots Ops And Scaling
Qdrant · Qdrant
Vector Database — Qdrant
Evaluates Qdrant's Snapshots, Collections Ops & Scaling across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Vector Database eval coverage.
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.
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 |
How this eval is graded
Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
Rubric criteria
- Qdrant
- Ai Platform
- Snapshots Ops And Scaling
Recommended for
Works with
Related evals
Claude API
Evaluates Anthropic's Batch API across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
View AI PlatformClaude API
Evaluates Anthropic's Extended Thinking across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
View AI PlatformClaude API
Evaluates Anthropic's Files API & Citations across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
ViewFrequently asked questions
What does the Snapshots Ops And Scaling eval for Qdrant Qdrant test?+
Evaluates Qdrant's Snapshots, Collections Ops & Scaling across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Vector Database eval coverage.
How is the Snapshots Ops And Scaling eval scored?+
The judge rubric: Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
How many test cases does this eval pack include?+
The Snapshots Ops And Scaling pack for Qdrant Qdrant contains 9 test cases. 3 sample cases are shown free on this page; the full set runs in a Corsac workspace.
How do I run this eval?+
Sign up for Corsac, connect your model or agent endpoint, and run the Snapshots Ops And Scaling pack as-is or after customizing thresholds. Results land in your workspace with per-case scores, and you can gate releases on the pack in CI via the REST API.
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.