(no title)
raoufchebri | 2 years ago
CREATE INDEX semantic_image ON image_table USING hnsw (v dist_cos_ops) WITH (M=5, ef=30, ef_construction=30, dims=512);
raoufchebri | 2 years ago
CREATE INDEX semantic_image ON image_table USING hnsw (v dist_cos_ops) WITH (M=5, ef=30, ef_construction=30, dims=512);
ngalstyan4|2 years ago
btw, we did not create our own vector type and just use size-enforced real[] arrays to represent embeddings. However, you can use our index with pgvector's vector type. So, if you already have a table with pgvector's vector column type, you can start using Lantern by just creating an index on the same column.