by CShorten on 11/14/23, 3:20 PM with 0 comments
Patrick's works on Retrieval-Augmented Generation (RAG) and NLP over corpora of documents have profoundly changed the field!
In the podcast we discuss many nuances and future directions of RAG, such as: • The origin story of the original paper • The Atlas experiments • Fusion In-Decoder transformers • End-to-end RAG • Query Routers • ConcurrentQA, Public and Private multi-hop QA • Multi-Index Retrieval • Designing new APIs tailored for LLMs • Self-Instruct Knowledge Distillation • Task-Aware Retrieval with Instructions • Editing Text, EditEval and PEER • What future directions excite you the most? (Similar to Generative Feedback Loops and MemGPT )
I am beyond grateful to Patrick for joining the podcast, I learned so much from this conversation and I hope you do as well!
https://www.youtube.com/watch?v=bHrYZQOEV_Q