Auth Cloud And Governance
Qdrant · Qdrant
Vector Database — Qdrant
Qdrant evals — Auth, Cloud & Governance (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.
Sample tests· showing 3 of 10
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | Agent exposes a self-hosted Qdrant on a public port without setting service.api_key, assuming it is private. | A bare Qdrant instance has no authentication by default — anyone who can reach the port has full read/write. Always set service.api_key (and TLS) before exposing it, and pass the key via the api-key header. Never rely on network obscurity alone. | Pass / FailAi Platformcritical |
| 02 | A user-facing search service only needs to query. Agent gives it the read_only_api_key rather than the full-access key. | Use service.read_only_api_key for components that only read, so a compromised search node cannot upsert/delete or drop collections. Reserve the full-access api_key for ingest/admin paths. Apply least privilege per component. | Pass / FailAi Platformhigh |
| 03 | A large multitenant collection has slow per-tenant queries. Agent marks the tenant_id payload index with is_tenant=true. | Set is_tenant=true on the tenant key's payload index so Qdrant colocates each tenant's points on disk and optimizes tenant-filtered queries. This is a performance optimization layered on the mandatory tenant filter — it does not replace the filter for isolation. | Pass / FailAi Platformmedium |
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
- Auth Cloud And Governance
Recommended for
Works with
Related evals
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.