VectorDB Cloud

Postgres for AI search and vector workloads.

VectorDB combines managed PostgreSQL, native vector search, real-time analytics, and multi-region infrastructure for teams building modern AI applications.

p95 search 20ms
uptime SLA 99.99%
cloud regions 42

Production cluster

rag-prod-us-east

Live
Queries 18.4M +24% today
Vectors 921M synced
Regions 6 active
select title, summary
from documents
order by embedding <-> vector($1)
limit 5;

Retrieval trace

1
Embed prompt open-source model
2
Filter context tenant + metadata
3
Return matches reranked in 18ms

Embedding job

1.8M rows

Synced across three regions with read latency under 21ms.

Trusted by developers shipping AI products worldwide

Northstar AIOrbit LabsSignalWorksHelioCloudRuneStack
AK
Ari Kim Founding Engineer, Northstar AI

VectorDB gave us one place for customer data, embeddings, and production retrieval analytics. Our RAG stack got simpler and faster in the same migration.

MS
Maya Singh VP Platform, Orbit Labs

We moved from a stitched-together search system to managed Postgres with vector indexes, replication, and real-time visibility our infra team can actually trust.

Platform

Everything AI teams expect from a modern database.

One managed platform for transactional data, embeddings, search, analytics, replication, and global deployment.

VS

Vector Search

High-performance approximate nearest neighbor search directly beside your transactional data.

AI

AI Embeddings

Generate, sync, and version embeddings from documents, events, and user content.

HS

Horizontal Scaling

Scale reads, writes, storage, and vector indexes independently as products grow.

RT

Real-time Replication

Stream changes to applications, warehouses, and AI pipelines with low latency.

SQL

SQL-first API

Use standard Postgres, familiar SQL, and type-safe SDKs without proprietary lock-in.

MR

Multi-region Deployment

Place data near users with regional replicas, failover, and policy-aware routing.

RAG

RAG Optimization

Tune chunking, metadata filters, reranking, and retrieval metrics for AI answers.

BAK

Automatic Backups

Point-in-time recovery, snapshots, audit trails, and enterprise-grade retention.

Developer experience

Easy to use with SQL, SDKs, and your favorite ORM.

Run vector generation, hybrid search, and retrieval pipelines from the tools your team already ships with.

query.sql
CREATE EXTENSION IF NOT EXISTS vector;

CREATE TABLE documents (
  id uuid PRIMARY KEY,
  title text NOT NULL,
  body text NOT NULL,
  embedding vector(1536)
);

CREATE INDEX documents_embedding_idx
ON documents USING hnsw (embedding vector_cosine_ops);
AI retrieval

Built for semantic search, RAG pipelines, and hybrid retrieval.

VectorDB keeps source data, generated embeddings, metadata filters, and retrieval analytics together so AI systems stay fresh and observable.

Semantic search

Rank results by meaning, not just keywords, with Postgres-native vector indexes.

Hybrid retrieval

Blend BM25, vector similarity, metadata filters, and business ranking in one query.

Observable RAG

Trace retrieval quality, token usage, latency, and feedback across production flows.

Fresh embeddings

Automatically regenerate vectors as documents, permissions, and models change.

Search preview

"Find enterprise contracts with renewal risk"
Acme renewal packet 0.94

Multiple late-stage support escalations and a 42 percent seat contraction risk.

Globex legal summary 0.89

Contract language flags renewal review, indemnity changes, and unresolved SLA terms.

Northwind account notes 0.86

Usage growth is strong, but payment history indicates procurement delay risk.

01 Ingest

Documents, events, tickets, and records stream into managed Postgres.

02 Embed

Vectors are generated, indexed, versioned, and replicated automatically.

03 Retrieve

Applications query fresh context with SQL, SDKs, or the REST API.

Pricing

Start small. Scale without re-architecting.

Transparent plans for prototypes, production teams, and enterprise AI platforms.

Starter

For prototypes and early AI features.

$0 /mo
  • 1 project
  • 2GB storage
  • 100K vectors
  • Community support

Pro

Popular

For production applications and fast-growing teams.

$32 /mo
  • Unlimited projects
  • 250GB storage
  • 50M vectors
  • Real-time replication
  • Priority support

Enterprise

For regulated, global, and mission-critical AI platforms.

Custom
  • Dedicated regions
  • SSO and audit logs
  • Private networking
  • Custom SLA
  • Solution engineering

Build your next AI application on VectorDB.

Provision managed Postgres, generate embeddings, deploy vector indexes, and query globally from one developer-first platform.