Swapping pgvector for turbopuffer made our whole database faster and cheaper
Comments
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Summary
Modem, a product that groups customer messages into topics, found its pgvector-based similarity search slowing sharply as data grew, with its smallest customers the slowest. Adding an HNSW index made results worse and altered some matches, so the team dropped it.