timescale / pgvectorscale

A complement to pgvector for high performance, cost efficient vector search on large workloads.
PostgreSQL License
1.37k stars 58 forks source link

Maximum dimensions CONCURRENTLY #142

Closed SlaveRHNH closed 1 week ago

SlaveRHNH commented 1 month ago

app=# CREATE INDEX CONCURRENTLY idx_vectors_embeddings on vectors using diskann (feature_vector); NOTICE: Starting index build. num_neighbors=-1 search_list_size=100, max_alpha=1.2, storage_layout=SbqCompression ERROR: assertion failed: dimensions > 0 && dimensions < 2000

Сould you change the maximum dimensions from 1999 to 2000?

SlaveRHNH commented 3 weeks ago

Hello! I wanted to kindly check if there might be any updates on this issue. Thank you very much!

cevian commented 1 week ago

@SlaveRHNH this should go out in the next release