top | item 46081446 (no title) kbrisso | 3 months ago I built this for local RAG https://github.com/kbrisso/byte-vision it uses llama.cpp and Elasticsearch. On a laptop with 8 GB GPU it can handle a 30K token size and summarize a fairly large PDF. discuss order hn newest busssard|3 months ago elasticsearch is the true limitation of rag systems... kbrisso|3 months ago The vector search works great once you figure it out. I wanted to focus on writing the application and not have to rewrite a document store.
busssard|3 months ago elasticsearch is the true limitation of rag systems... kbrisso|3 months ago The vector search works great once you figure it out. I wanted to focus on writing the application and not have to rewrite a document store.
kbrisso|3 months ago The vector search works great once you figure it out. I wanted to focus on writing the application and not have to rewrite a document store.
busssard|3 months ago
kbrisso|3 months ago