Feature request: Index based on embeddings

[jeremieamstutz]

LibSQL is amazing! I love how easy it is to save and retrieve a vector in the database.

However for semantic search, I don't care about the vector. I just want to see the most similar values.

Also, if we want to do semantic search on multiple columns, we need to add many columns.

My proposition would be to be able to define an embedding function as an index and use it as well for the retrieval.

That way, the embedding, storage, and retrieval of the vectors can be abstracted away from the user.

What do you think?