From the blog's section on semantic search:
Under the hood, we store the embeddings in a meta.embeddings table then pass back to AI the resulting IDs for each embedding. We do this because embedding vectors are big, and sending these back and forth to the model is not only expensive, but also error prone. Instead, the language model is aware of the meta.embeddings table and simply subqueries to it when it needs access to an embedding.
1. What does it mean to "pass back to AI the resulting IDs for each embedding" but not the table rows corresponding to the matched vectors?
2. Does "the language model is aware of the meta.embedding table" mean Supabase has deployed a fine-tuned GPT-4o?