Prompt Engineering with LangChain
5h 22mIntermediate2024-04-18
Authors
Harpreet Sahota
Course details
This course provides a comprehensive yet concise introduction to LangChain, a powerful framework for large language model (LLM) applications. Starting with the basics of LLMs, instructor Harpreet Sahota explores the key features and capabilities of LangChain, showing you how to integrate it with various systems and gain hands-on experience in building practical applications. Whether you're a seasoned developer or a beginner, this course will equip you with a solid foundation in LangChain, setting the stage for more advanced topics and applications.
Skills covered
LangChainChatGPTNatural Language Processing (NLP)OpenAIGenerative AISoftware Development ToolsArtificial Intelligence (AI)Open SourceSoftware DevelopmentOne-Off
Concepts
0. Introduction
- 01 - Create powerful LLM driven applications
1. Introduction to Language Models
- 02 - What are language models
2. LLMs and Text Generation
- 03 - How do language models generate text
- 04 - Base LLMs vs. instruction-tuned LLMs
- 05 - Training, fine-tuning, and in-context learning
- 06 - Prompt engineering
3. Components of LangChain
- 07 - What is LangChain
- 08 - LangChain overview
- 09 - Model I O - Interface with language models
- 10 - Retrieval - Interface with application-specific data
- 11 - Chains - Construct sequences of calls
- 12 - Agents - Let chains choose tools based on high-level directives
- 13 - Memory - Persist application state between runs of a chain
4. Basics of Prompting
- 14 - Prompt basics
- 15 - Principles and tactics for prompting
5. Prompt Templates Deep Dive
- 16 - Introduction to prompt templates
- 17 - Multi-input prompt templates
- 18 - Chat prompt template
- 19 - Serializing prompts
- 20 - Zero-shot prompts
- 21 - Custom prompt templates
- 22 - Prompt pipelining
- 23 - Chat prompt pipelining
- 24 - Prompt composition
- 25 - Few-shot prompt templates
- 26 - Few-shot prompt templates for chat
- 27 - Introduction to example selectors
- 28 - Length-based example selector
- 29 - Max marginal relevance example selector
- 30 - N-gram overlap example selector
- 31 - Semantic similarity example selector
- 32 - Partial prompt templates
6. Prompting Techniques
- 33 - Chain of thought
- 34 - Self-consistency
- 35 - Self-ask
- 36 - ReAct
- 37 - RAG
- 38 - FLARE
- 39 - Plan and execute
7. Prompt Management a.k.a. PromptOps
- 40 - Prompt management
- 41 - LangSmith
- 42 - LangSmith walkthrough
- 43 - Prompt versioning in LangSmith
- 44 - LangSmith deep dive
- 45 - Managing prompt length for agents
8. The LLM Landscape
- 46 - Applications of language models
- 47 - The LLM landscape