On this video, Josh walks by the patterns for augmenting language fashions with exterior context: retrieval augmentation, chaining, and gear use.
Obtain slides from the bootcamp web site right here: https://fullstackdeeplearning.com/llm-bootcamp/spring-2023/augmented-language-models/
Intro and outro music made with Riffusion: https://github.com/riffusion/riffusion
Watch the remainder of the LLM Bootcamp movies right here: https://www.youtube.com/playlist?list=PL1T8fO7ArWleyIqOy37OVXsP4hFXymdOZ
0:00:00 Why augmented LMs?
0:06:40 Why retrieval augmentation?
0:08:25 Conventional info retrieval
0:13:05 Embeddings for retrieval
0:22:15 Embedding relevance and indexes
0:28:42 Embedding databases
0:38:50 Past naive embeddings
0:41:10 Patterns & case research
0:46:16 What are chains and why do we’d like them?
0:52:50 LangChain
0:54:55 Software use
0:59:17 Plugins
1:02:38 Suggestions for device use
1:04:07 Recap & conclusions
