Building the Future with LLMs, LangChain, & Pinecone

Explore the future of AI development in this comprehensive workshop featuring Harrison Chase, creator of LangChain, and James Briggs from Pinecone. Dive into the world of Large Language Models (LLMs), vector databases, and the LangChain library to understand how these tools are revolutionizing AI-powered applications. Learn about the history of NLP, transformers, and the challenges faced by large language models. Discover the key components of LangChain, including chains, prompt templates, agents, and memory. Gain insights into building with language models, focusing on retrievable augmentation, indexing, and vector databases. Explore practical applications through Python text splitters and embedding tools. Access accompanying slides and a notebook to enhance your learning experience and start creating cutting-edge AI applications.

Intro
Pinecone
History of NLP
Transformers
NLP
Screenshots
Problems with Large Language Models
Growth of Large Language Models
LangChain
LangChain Overview
Modular Components
Chains
Prompt Templates
Agents
Memory
Building with Language Models
Deep Dive
The Problem
Retrievable Augmentation
Indexing
Vector Database
LangChain Components
LangChain Variants
Process Overview
Training Models on Proprietary Data
Python Text Splitter
Embedding Tools