Cloud-native, Apache-2.0 vector database for similarity search at scale, powering RAG, semantic and multimodal search, and recommendations. Its distributed architecture separates storage and compute and supports many index types (HNSW, IVF, FLAT, DiskANN, SCANN) with quantization and mmap. Created by Zilliz, which offers the managed Zilliz Cloud.
MI
Vector DB · Zilliz
Milvus
Distributed open-source vector DB built for billion-scale.
FREEMIUMOpen coreHybridAPI
Model support
Model-agnostic
Where it runs
- API
Tags
- #vector-db
- #open-source
- #rag
- #ann-search
- #scalable
Related in Vector DB
View Pinecone details Vector DBFREEMIUMPIPinecone
Pinecone
Managed vector database. The industry-default serverless option.
Fully-managed vector DB built for production RAG and semantic search at scale. Serverless pricing, low-latency reads, integrations across every framework. Most Blokz-adjacent AI teams reach for it first.
AI insight: Fully managed with no self-host option — the trade-off for the serverless pricing it popularized in the vector-DB space.
- managed
- serverless
- rag
- semantic-search
View Chroma details Vector DBFREEMIUMOpen coreCHChroma
Chroma
Embedded vector DB. Pip-install, prototype, scale later.
The low-friction starting point — Chroma runs embedded inside your Python process or as a hosted service. Great for prototypes and small-to-medium RAG apps; upgrade to a managed option when you outgrow it.
AI insight: Runs embedded inside your Python process — the lowest-friction way to prototype RAG before you need a server at all.
- open-source
- embedded
- prototype
- python
View pgvector details Vector DBFREEOSSPGpgvector
pgvector community
Vector similarity search inside Postgres. The pragmatic default.
Postgres extension that adds a vector type plus exact and approximate nearest-neighbour search. Pairs naturally with Supabase, Neon, and any managed Postgres. The lowest-friction RAG backend if you already run Postgres.
AI insight: Keeps embeddings in the same Postgres as your relational data, so you can JOIN against them and back everything up together.
- postgres
- open-source
- extension
- rag
View Qdrant details Vector DBFREEMIUMOpen coreQDQdrant
Qdrant
Open-source, Rust-based vector DB. Fast, predictable, self-hostable.
Vector database written in Rust with a strong focus on filtering, payloads, and predictable latency at scale. Self-host on a single binary or use the managed cloud.
AI insight: Written in Rust and ships as a single self-hostable binary — its payload filtering is why teams pick it for metadata-heavy search.
- open-source
- rust
- self-hosted
- fast
View Turbopuffer details Vector DBPAIDTUTurbopuffer
Turbopuffer
Object-storage-backed vector DB. Serverless economics at scale.
Bills like S3 — cold rest, warm reads, no per-namespace minimums. Designed for very-large, mostly-cold vector workloads where you can't justify keeping every index in RAM. Operated by Notion in production.
AI insight: Stores indexes on object storage instead of RAM, so cost tracks usage not corpus size — Notion runs it in production.
- serverless
- object-storage
- cold-storage
- scale
View Weaviate details Vector DBFREEMIUMOpen coreWEWeaviate
Weaviate
Open-source vector database with built-in vectorisers.
Cloud-native vector DB that can compute embeddings inline — pass raw text in, store vectors out. Strong hybrid (BM25 + vector) search; self-hostable or managed.
AI insight: Embeds text inline so you can skip a separate vectorizer step, and does hybrid BM25 + vector search out of the box.
- open-source
- self-hosted
- hybrid-search
- rag