The linked article goes into more detail about this release, including:
- HNSW indexing support
- Faster distance calculations
- Parallel builds for ivfflat
One of the most common complaints about pgvector is a lack of HNSW support, so it's an exciting release for the Postgres ecosystem. Congrats to Andrew (https://github.com/ankane) on the release
Interesting thing about faster distance calculations is that a very small change in the dot product calculation makes code compile to much more efficient CPU instructions and up to 2 times speedup for the whole algo.
But the real jewel in the crown is HNSW support that makes pgvector much faster than the competitors (the measurements with thorough and transparent description of method are in the linked blog post).
The linked article goes into more detail about this release, including:
- HNSW indexing support
- Faster distance calculations
- Parallel builds for ivfflat
One of the most common complaints about pgvector is a lack of HNSW support, so it's an exciting release for the Postgres ecosystem. Congrats to Andrew (https://github.com/ankane) on the release