Azamat Omuraliev
Solutions Architect at Databricks.
Helping Healthcare and Life Sciences enterprises accelerate on their data+AI journey. In past lives worked as MLE at a bank, AI engineer at an early stage startup and ran a non-profit in Kyrgyzstan.
Played with GPT-3 before ChatGPT came out.
Session
09-11
13:25
30min
When RAG is not enough: Architecting for 10M+ context windows
Azamat Omuraliev
RAG is the accepted paradigm to work with knowledge bases that don't fit into a typical context window. But RAG is good at retrieving only some relevant bits; what do you do if there's 10M tokens of relevant information which your agent needs to act on? In this talk we explore tactics to deal with 1m+ context window and evaluate whether how accuracy and performance degrade at large context volumes.
Main stage