Overview & Capability
Highly scalable, distributed open-source vector database designed for handling billions of embedding vectors with hardware-accelerated GPU indexing.
Key Highlights
- Scales horizontally to multi-billion vector collections
- GPU-accelerated indexing with NVIDIA RAFT / CAGRA
- Multi-tenancy and enterprise role-based access control (RBAC)
Robbie's Independent Take
Verified: 2026-10-11
Evaluated independently for utility and transparency. Test against a controlled baseline workload before integrating into mission-critical production pipelines.
Alternatives & Replaces
- Legacy search clusters