Howdy, I am curious if you might elaborate on how indexes are created and queried when using an embedding and another column like in the below example. At the moment, I believe, with pgvector, there is no way to create an index on an embedding and column.
This thread in pgvector notes that it the current approach may be using a partial index but with many values in a column, that is not very feasible.
CREATE INDEX my_remote_index ON products USING pinecone (embedding, price) with (host = 'my-pinecone-index.pinecone.io');
Howdy, I am curious if you might elaborate on how indexes are created and queried when using an embedding and another column like in the below example. At the moment, I believe, with pgvector, there is no way to create an index on an embedding and column.
This thread in pgvector notes that it the current approach may be using a partial index but with many values in a column, that is not very feasible.