When working with vector search, dimension limits matter. Many embedding models fit comfortably inside 768, 1,024, or 1,536 dimensions. But some use […]
Read More
Why HNSW Indexes Are So Fast in YugabyteDB
Vector search gets expensive fast. Without an index, every query has to compare your search embedding against every row in the table. […]
Read MoreExploring National Parks with AI: Using pgvector + YugabyteDB for Semantic Search
Introduction Finding the right U.S. National Park to explore is often about vibes. Some people want jagged mountains and glaciers, others want […]
Read More