Get exclusive access to AI resources and project ideas: https://the-data-entrepreneurs.kit.com/shaw
This is the 4th video in a series on using large language models (LLMs) in practice. Here, I review Prompt Engineering, 7 prompting tricks, and walk through example code that uses LangChain to build an AI application.
▶️ Series Playlist: https://www.youtube.com/playlist?list=PLz-ep5RbHosU2hnz5ejezwaYpdMutMVB0
📰 Read more: https://medium.com/towards-data-science/prompt-engineering-how-to-trick-ai-into-solving-your-problems-7ce1ed3b553f?sk=c92e4bb4b026bdc263f01a9310c8ec11
💻 Example code: https://github.com/ShawhinT/YouTube-Blog/tree/main/LLMs/langchain-example
References
[1] arXiv:2302.11382 [cs.SE]
[2] arXiv:2106.09685 [cs.CL]
[3] State of GPT by Andrej Karpathy at Microsoft Build 2023
[4] arXiv:2206.07682 [cs.CL]
[5] ChatGPT Prompt Engineering for Developers by deeplearning.ai
[6] arXiv:2005.14165 [cs.CL]
[7] arXiv:2201.11903 [cs.CL]
[8] arXiv:2210.03493 [cs.CL]
--
Homepage: https://shawhintalebi.com/
Intro -
0:00
Agenda -
1:23
What is Prompt Engineering? -
1:52
Two Levels of Prompt Engineering -
4:31
Building AI Apps w/ Prompt Engineering -
5:41
7 Tricks for Prompt Engineering -
9:43
Trick 1: Be Descriptive -
12:00
Trick 2: Give Examples -
13:31
Trick 3: Use Structured Text -
15:13
Trick 4: Chain of Thought -
17:00
Trick 5: Chatbot Personas -
18:31
Trick 6: Flipped Approach -
19:55
Trick 7: Reflect, Review, and Refine -
21:24
Example Code: Automatic Grader with LangChain -
22:39
Limitations -
28:19