Getting Started with LangChain
Published by O'Reilly Media, Inc.
Build your own LLM agents
Course outcomes
- Understand the basic components of LangChain from prompt templates to LLM-based agents
- Learn how to build prompt workflows with LangChain
- Learn how to automate research workflows with LangChain
- Understand how to build simple LLM-based agents with LangChain
Join expert Lucas Soares to unlock the full potential of large language models with LangChain. You’ll embark on a comprehensive journey covering the basics of LangChain, from working with LLMs and crafting prompt templates to more advanced applications like creating chain pipelines and LLM agents. Through a mix of presentations, Q&A sessions, and hands-on labs, you’ll learn how to build simple yet effective Q&A systems, automate research and work-related workflows, and work with conversational memory in LLM agents. Whether you're new to large language models or looking to deepen your understanding, you’ll come away with the skills to get started working with LangChain for real-world solutions.
What you’ll learn and how you can apply it
- Build custom LLM agents using LangChain
- Build LLM agents for research using LangChain
- Build a learning assistant agent
This live event is for you because...
- You’re a software engineer or developer, data scientist, or machine learning engineer
- You’re interested in learning about large language models, specifically ChatGPT, and understanding how to build applications
Prerequisites
- Familiarity with Python programming
- Some knowledge of machine learning concepts
- Basic understanding of natural language processing
Recommended preparation:
- Read chapters 1, 6, and 7 in Natural Language Processing with Transformers (book)
Recommended follow-up:
- Read _Language Models in Plain English _(report)
- Read Developing Apps with GPT-4 and ChatGPT (book)
- Read Generative AI on AWS (book)
- Read Hands-On Large Language Models (book)
Schedule
The time frames are only estimates and may vary according to how the class is progressing.
LangChain for working with LLMs (60 minutes)
- Presentation: Introduction to large language models and their applications; introduction to LangChain
- Hands-on exercise: Explore LangChain basics (LLMs, prompt templates, chains, and memory)
- Q&A
- Break
Composing chain pipelines with LangChain LLM agents (60 minutes)
- Presentation: Composing chain pipelines; custom chains
- Hands-on exercises: Explore chain prompts; automate workflows
- Q&A
- Break
Question answering over documents (65 minutes)
- Presentation: Retrieval basics from document loaders to indexing; framework for building composable pipelines
- Hands-on exercises: Build a simple Q&A system for machine learning papers; automate research workflows
- Q&A
- Break
Conversational memory and LLM agents (55 minutes)
- Presentation: Conversational memory and LLM agents
- Hands-on exercise: Build an LLM agent
- Q&A
Your Instructor
Lucas Soares
Lucas Soares is an AI engineer who worked as a research assistant at the Champalimaud Neuroscience Institute where he finished his masters working on an application of generative adversarial networks to predict mouse behavior. He switched his focus to industry and worked as a machine learning engineer for K1 Digital and Biometrid, developing computer vision and NLP based applications and gaining experience working with Pytorch. More recently over the last 2 years he has developed expertise working with LLM models, developing applications for his current employer Otovo as well as developing courses for OReilly Media and periodically making technical content about AI for Medium and Youtube.