Timescale Vector enhances pgvector with a state-of-the-art, memory-efficient DiskANN index type. Get the performance of a specialized vector database without the hassle of learning and maintaining one.
Access pgvector's indexes, data types, and operators too. Timescale Vector supports exact and approximate nearest neighbor search, cosine distance, and out-of-the-box support for up to 2,000 dimensional vectors.
One platform for your AI application
Timescale’s enhanced PostgreSQL data platform is the home for your application's vector, relational and time-series data.
Flexible and transparent pricing
No “pay per query” or “pay per index”. Decoupled compute and storage for flexible resource scaling as you grow. Usage-based storage and dynamic compute (coming soon), so you pay only for what you actually use.
Ready to scale from day one
Push to prod with the confidence of automatic backups, failover and High Availability. Use read replicas to scale query load. One-click database forking for testing new embedding and LLM models. Consultative support to guide you as you grow at no extra cost.
Enterprise-grade security and data privacy
SOC2 Type II and GDPR compliance. Data encryption at rest and in motion. VPC peering for your Amazon VPC. Secure backups. Multi-factor authentication.
-- Activate Timescale Vector
CREATE EXTENSION timescale_vector CASCADE;
-- Create index for fast search
CREATE INDEX idx_tsv ON embeddings USING tsv (embedding) WITH (num_neighbors = 10, search_list_size = 10, use_pq = true);
-- Search index
SELECT * FROM embeddings
WHERE create_date >= now() - INTERVAL '7 days'
ORDER by embedding <=> '[query vector]'
LIMIT 10;
90 day extended free trial • No credit card needed • Usage based pricing