← Back to context Comment by eigenvalue 2 years ago Even if you have a lot more than that you could easily use SQLite with FAISS. It works great. 2 comments eigenvalue Reply bravura 2 years ago Bingo. This combination is underappreciated. eigenvalue 2 years ago Yes, I’ve used this approach in my Swiss Army Llama project with huge numbers of vectors and it can scale massively. Also it’s free! These vector db as a service companies charge insane prices for this! It really does feel like snake oil to me.https://github.com/Dicklesworthstone/swiss_army_llama
bravura 2 years ago Bingo. This combination is underappreciated. eigenvalue 2 years ago Yes, I’ve used this approach in my Swiss Army Llama project with huge numbers of vectors and it can scale massively. Also it’s free! These vector db as a service companies charge insane prices for this! It really does feel like snake oil to me.https://github.com/Dicklesworthstone/swiss_army_llama
eigenvalue 2 years ago Yes, I’ve used this approach in my Swiss Army Llama project with huge numbers of vectors and it can scale massively. Also it’s free! These vector db as a service companies charge insane prices for this! It really does feel like snake oil to me.https://github.com/Dicklesworthstone/swiss_army_llama
Bingo. This combination is underappreciated.
Yes, I’ve used this approach in my Swiss Army Llama project with huge numbers of vectors and it can scale massively. Also it’s free! These vector db as a service companies charge insane prices for this! It really does feel like snake oil to me.
https://github.com/Dicklesworthstone/swiss_army_llama