Explore patterns for augmenting language models with external context in this comprehensive video lecture. Delve into retrieval augmentation, chaining, and tool use as Josh guides you through the concepts. Learn about traditional information retrieval, embeddings for retrieval, embedding relevance and indexes, and embedding databases. Discover patterns and case studies, understand the need for chains, and get introduced to LangChain. Examine tool use, plugins, and receive recommendations for their implementation. Access downloadable slides, explore related videos in the LLM Bootcamp series, and navigate through various topics with timestamps provided.
Overview
Syllabus
Why augmented LMs?
Why retrieval augmentation?
Traditional information retrieval
Embeddings for retrieval
Embedding relevance and indexes
Embedding databases
Beyond naive embeddings
Patterns & case studies
What are chains and why do we need them?
LangChain
Tool use
Plugins
Recommendations for tool use
Recap & conclusions
Taught by
The Full Stack
Related Courses
-
Retrieval Augmented Generation (RAG) with LangChain
-
Developing LLM Applications with LangChain
-
Large Language Models: Application through Production
-
Finetuning Large Language Models
-
Large Language Models with Semantic Search
-
Development with Large Language Models Tutorial – OpenAI, Langchain, Agents, Chroma
