pgvector vs Milvus
Both are alternatives to Pinecone. Here's how they stack up — verified facts, no spin.
Also searched as Milvus vs pgvector — same comparison, one verdict.
pgvector
Vector search inside the Postgres you already run — zero new infrastructure.
pgvector is an open-source extension (PostgreSQL license) that adds vector similarity search to PostgreSQL itself. If your app already has Postgres, this is the no-new-moving-parts answer: embeddings live next to your relational data, joins and filters are just SQL, and every major managed Postgres (RDS, Cloud SQL, Azure, Supabase, Neon) supports it. Recent releases added parallel HNSW index builds, iterative scans for filtered queries, and halfvec quantization — it now handles serious workloads, not just prototypes.
Milvus
The heavy-scale distributed choice — billions of vectors, Apache-2.0.
Milvus is a cloud-native, distributed vector database under the LF AI & Data Foundation, licensed Apache-2.0 and developed by Zilliz. It is engineered for the top end of scale — billions of vectors, horizontal scaling, tiered storage — with a managed option (Zilliz Cloud) when you want the same engine without the Kubernetes homework. If your vector workload is genuinely huge, this is the open-source engine built for it.
Side by side
| pgvector | Milvus | |
|---|---|---|
| Sovereignty Score | 94 | 88 |
| Open source | Yes | Yes |
| Self-hostable | Yes | Yes |
| Local-first | Yes | No |
| License | PostgreSQL | Apache-2.0 |
| Pricing | Free — an extension of PostgreSQL; runs wherever your Postgres runs | Free self-hosted (Apache-2.0); Zilliz Cloud managed tiers incl. a free tier |
pgvector edges it on the Sovereignty Score, but the right pick depends on the trade-offs below.
pgvector
Strengths
- +No new database to operate — it's your existing Postgres
- +Vectors join directly with relational data in SQL
- +Supported by every major managed Postgres provider
- +HNSW indexes, filtered iterative scans, quantization
Trade-offs
- −Very large collections (hundreds of millions of vectors) favor a dedicated engine
- −Tuning happens in Postgres terms — indexes, memory, vacuum
Milvus
Strengths
- +Proven at billion-vector scale, horizontally scalable
- +LF AI & Data governance — not a single-vendor project
- +Managed escape hatch (Zilliz Cloud) with the same engine
Trade-offs
- −Distributed architecture = real operational complexity self-hosted
- −Overkill for small and mid-size workloads
Related alternative guides
Facts verified 2026-07-15. Licenses and pricing change — spotted something out of date? That's a correction we want.