Lead engineer here, happy to answer any questions
Personally, without a way to run it locally, I'd look at either using pgvector or something like ChromaDB.
Totally fair about cloud-only. Many developers prefer developing on cloud, but some prefer local dev. YMMV.
By the way timescale vector offers pgvector as well so it's easy to test and compare. (Note: I work for Timescale)
According to the single-threaded QPS experiments, your DiskANN solution should clock in at about 4.5ms latency (1000ms/224QPS) whereas pgvector is about 5.8ms latency (1000ms/173QPS). How is that possible? My (very shallow) knowledge of DiskANN vs HNSW tells me that DiskANN should generally have higher latency than HNSW — DiskANN needs to touch the SSD while HNSW only touches RAM.
Also, compared to pgvector and HNSWPQ in faiss, how much less RAM does your DiskANN-based solution use?
To your question about RAM usage, we provide a graph of index size. When enabling PQ, our new index is 10x smaller than pgvector HNSW. We don't have numbers for HNSWPQ in FAISS yet.