Postgres multi-tenant architecture for AI apps (database per user/workspace/org)
Instead of storing all vector embeddings in one shared Postgres database, you provide each tenant (a user, an organization, a workspace, etc.) their own dedicated Postgres database with pgvector
Code + demo: https://github.com/neondatabase/db-pe...
This means:
1. Each tenant's data is stored in a separate, isolated database not shared with other tenants. This makes it possible for you to be compliant with data residency requirements (e.g., GDPR)
2. Database resources can be allocated based on each tenant's requirements.
3. A tenant with a large workload that can impact the database's performance won't affect other tenants; it would also be easier to manage.
This is possible to implement using Postgres on Neon for the following reasons:
1. Postgres on Neon can be provisioned within ~2 seconds. You don't need to wait several minutes for the database to be ready.
2. The database's compute can automatically scale up to meet an application's workload and can shut down when the database is unused. Making this architecture manageable and cost-effective.
Try Neon at https://neon.tech/youtube
→ Neon Discord: https://neon.tech/discord
→ Follow us on Twitter: / neondatabase
→ Star us on GitHub https://github.com/neondatabase/neon