Open SourceRAG37k
Milvus
Cloud-native vector database built for billion-scale similarity search.
Milvus is an open-source vector database built for large-scale similarity search, with a cloud-native, distributed architecture that separates compute and storage. It supports multiple ANN index types (HNSW, IVF, DiskANN, and others), scalar filtering, and billion-scale vector workloads. It is widely used where very high-volume, production-grade vector retrieval is required.
Repository
milvus-io/milvusLanguage
GoWhat you'd build with it
- Indexing and querying billions of embeddings for enterprise-scale RAG or semantic search
- Tuning index types and parameters to balance recall, latency, and cost for large vector workloads
- Backing image, audio, or multimodal similarity search at scale
Tags
vector-dbscaleann