#2525th of 55 in Learning and cookbooks
prompt_engineering
22 Jupyter notebooks teaching prompt engineering with OpenAI and LangChain
- Stars
- 7.9k
- License
- custom license
- Last commit
- Oct 2026
- Language
- Jupyter Notebook
7,246 on 1 Apr 20267,913 on 21 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
A set of 22 Jupyter notebooks covering prompt engineering, from basic prompt structures and Jinja2 templates to chain-of-thought, self-consistency, prompt chaining, optimization, prompt security and evaluation. Examples use OpenAI models and LangChain. The README also promotes a paid course ($199), a book and a newsletter by the author.
Who it is for: Developers learning prompt engineering through runnable notebooks
Strengths
- 22 notebooks ordered from fundamentals to optimization, security and evaluation
- Covers named techniques: zero-shot, few-shot, CoT, self-consistency, prompt chaining
- Runnable code in notebooks rather than prose-only guides
- Includes a Jinja2 templating notebook and a prompt security notebook
Weaknesses
- Examples rely on OpenAI and LangChain; local model use is not described
- README is heavy with promotion for a paid course, book and newsletter
- License is reported as NOASSERTION, so reuse terms are unclear
- No release tags and no setup or version requirements in the visible README
What it needs
- no GPU
- Needs OpenAI API, LangChain, Jinja2
- Models: OpenAI GPT
Also in Learning and cookbooks
See all 55| Rank | Project | Score |
|---|---|---|
| 1 | ai-engineering-from-scratchHands-on AI engineering curriculum with 542 lessons across 20 phases | 90 out of 100 |
| 2 | generative-ai-for-beginners21-lesson course on building generative AI apps in Python and TypeScript | 81 out of 100 |
| 3 | ai-agents-for-beginners18-lesson course on building AI agents with Microsoft Agent Framework | 79 out of 100 |
| #4 | cs249r_bookOpen textbook and course materials for machine learning systems engineering | 79 out of 100 |
| #5 | llms-from-scratchCode for the book on building a GPT-style LLM in PyTorch | 77 out of 100 |