This documentation is sourced from a third-party project and is not maintained by pgEdge.
Scaling
For a smaller working set:
- Use the
halfvectype instead ofvectorfor tables - Use binary quantization for indexes (with re-ranking for search)
Scale vertically by increasing memory, CPU, and storage on a single instance. Use existing tools to tune parameters and monitor performance.
Scale horizontally with replicas, or use Citus, PgDog, or another approach for sharding (example).