This is awesome, and the low cost is especially impressive. I rarely have the motivation after working on a side project to actually document all the decisions made along the way, much less in such a thorough way. Regarding your CoreNN library, Clearview has a blog post [1] on how they index 30 billion face embeddings that you may find interesting. They combine RocksDB with faiss.

[1] https://www.clearview.ai/post/how-we-store-and-search-30-bil...