Closed legaltextai closed 2 months ago
an indexing maximum of 2k dimensions is a restriction of pgvector
for performance reasons you most likely would not want embeddings of that size In some cases, like OpenAI models you can make use of them being matryoshka embeddings to reduce the dimensionality with very little loss of accuracy
Here's a link to the blog post about that
Thank you Oliver
Is it possible? the default indexing with hnsw does not permit more than 2k dimensions. thank you