Quickstart for pgvector

pgvector is an Open-source vector similarity search for Postgres. In this, you can store your vectors with the rest of your data. Supports: exact and approximate nearest neighbor search, single-precision, half-precision, binary, and sparse vectors, L2 distance, inner product, cosine distance, L1 distance, Hamming distance, and Jaccard distance, and any language with a Postgres client.

Deploy pgvector on Elestio

1. Open the pgvector deployment page and sign in, or create an account.
2. Choose a cloud provider, a region and a data center. Pick the region closest to your users for the lowest latency.
3. Choose an instance size. Elestio only lists the sizes that can run pgvector properly (at least 1 vCPU and 0.5 GB of RAM).
4. Choose your support plan and the maintenance window for system and software updates (times are in UTC).
5. Click Create Service. pgvector is deployed and ready in a few minutes, and you receive an email with the access details.

The full walkthrough with screenshots is in the installation guide.

Access pgvector

Open your service in the Elestio dashboard and go to the Overview tab. Click Display Admin UI to reveal the URL, username and password of your pgvector instance.

If the password field is blank, pgvector does not ship with a pre-created admin user: open the admin URL to start its setup. Software without a web interface, such as databases, is reached with the credentials and port listed in the same tab. See Admin UI and credentials.

Next steps

• Custom domain and SSL: point your own domain to pgvector (guide).
• Backups: new services follow a 3-2-1 backup strategy by default (backups).
• Updates: manage the pgvector version and update policy (software versions and updates).
• Learn pgvector: read the official pgvector documentation.