All the Links That Fit to Print
A few friends have requested more information on x. Hence, here are my bookmarks from…
Using Full-Scale LLMs for Embeddings
Unlike static embedding models, the effective "embeddings" in an LLM are contextual, as they're influenced by the entire input sequence through self-attention mechanisms.
Arrendy’s Next Chapter
Dear Valued Customers, Partners, and Supporters, We have some exciting news to share with you.…
Implementing Advanced RAG: A Dynamic, Performance-Focused Approach
RAG is still very much the Wild West. We're allowing ourselves creativity as we chart this territory.