Building applications involving LLMs can be challenging due to the sheer number of components involved: prompts, models, vector databases, APIs, and agents. Enter LangChain! LangChain is a framework for building and orchestrating components using a single, unified syntax.
In this skill track, you'll use LangChain to master building the most common LLM applications in Python. You'll get to grips with the fundamentals of building impactful chatbots using models from Hugging Face and OpenAI.
You'll discover Retrieval Augmented Generation, or RAG, which allows you to integrate your own data into your application, so the model can go beyond its training data.
Agentic systems are one of the most exciting developments in AI and LLM application development, and you'll get a full crash course on building your own! Agents use LLMs to make decisions, in effect, deciding to take different actions based on the input. These actions could involve calling APIs, running Python code, or even performing RAG!
Along the way, you'll apply your new-found knowledge in hands-on, interactive projects. Join the Generative AI generation today!
Overview
Syllabus
- Developing LLM Applications with LangChain
- Discover how to build AI-powered applications using LLMs, prompts, chains, and agents in LangChain.
- Retrieval Augmented Generation (RAG) with LangChain
- Learn cutting-edge methods for integrating external data with LLMs using Retrieval Augmented Generation (RAG) with LangChain.
- Building RAG Chatbots for Technical Documentation
- Designing Agentic Systems with LangChain
- Get to grips with the foundational components of LangChain agents and build custom chat agents.
Taught by
Jonathan Bennion, Meri Nova, and Dilini K. Sumanapala, PhD