Databricks(@databricks):We benchmarked Lakebase Search on 1M to 4M passages to understand how vector search performs as the index grows. Here's what we learned 👇 Cache size relative to the vector index mattered more than row count. When the cache roughly matched the index, 95–98% of page reads avoided storage and warm vector search p50 latency stayed between 11 and 23 ms. As datasets grow, sizing the cache alongside the vector index helps maintain low-latency search.

Databricks

@databricks

Databricks is the Data + AI company, helping organizations build and scale data and AI apps, analytics and agents.

Joined July 2013

1.1K Following 99.6K Followers

Databricks@databricks

2026.11.03 20:38

We benchmarked Lakebase Search on 1M to 4M passages to understand how vector search performs as the index grows. Here's what we learned 👇 Cache size relative to the vector index mattered more than row count. When the cache roughly matched the index, 95–98% of page reads avoided storage and warm vector search p50 latency stayed between 11 and 23 ms. As datasets grow, sizing the cache alongside the vector index helps maintain low-latency search.