explaingit

datawhalechina/llm-cookbook

24,052Jupyter NotebookAudience · developerComplexity · 2/5QuietSetup · moderate

TLDR

Chinese-language learning resource with interactive notebooks teaching developers how to build practical LLM applications, from prompt engineering to chat systems to AI agents.

Mindmap

mindmap
  root((repo))
    What it does
      LLM app tutorials
      Interactive notebooks
      Chinese language
    Core topics
      Prompt engineering
      ChatGPT API
      LangChain basics
    Advanced topics
      RAG systems
      Model fine-tuning
      AI agents
    Tech stack
      Python
      Jupyter Notebooks
      LangChain
    Use cases
      Build chatbots
      Q&A systems
      Document search
    Audience
      Chinese developers
      LLM beginners

Things people build with this

USE CASE 1

Build a chatbot that answers questions using your own documents with RAG techniques.

USE CASE 2

Create a question-answering system powered by the ChatGPT API.

USE CASE 3

Develop an AI agent that can use tools to complete multi-step tasks.

USE CASE 4

Learn prompt engineering best practices through hands-on coding exercises.

Tech stack

PythonJupyter NotebookLangChainOpenAI API

Getting it running

Difficulty · moderate Time to first run · 30min

Requires OpenAI API key and Python environment setup with dependencies.

License could not be detected automatically. Check the repository's LICENSE file before use.

In plain English

This repository is a Chinese-language learning resource for developers who want to get started building applications with large language models (LLMs). The project is based on a series of courses by Andrew Ng (published in collaboration with OpenAI) and has been translated and adapted into Chinese so that Mandarin-speaking developers can access the material directly, without the access restrictions that apply to the original English versions in some regions. The curriculum covers the full practical workflow of LLM development, from writing effective prompts to building complete chat systems to more advanced topics. Core required courses include prompt engineering for developers, building question-answering systems using the ChatGPT API, and developing applications with LangChain. Optional elective courses extend into RAG (retrieval-augmented generation, a technique for letting a model answer questions based on your own documents), model fine-tuning, and building AI agents with tools. All content is delivered as interactive Jupyter Notebooks. You would use this if you are a Chinese-speaking developer with basic Python skills who wants a structured, hands-on path into practical LLM application development.

Copy-paste prompts

Prompt 1
Show me how to set up a basic LLM application using LangChain with the ChatGPT API.
Prompt 2
How do I implement retrieval-augmented generation (RAG) to let an LLM answer questions about my own documents?
Prompt 3
Walk me through building a simple chatbot using the code examples in this repository.
Prompt 4
Explain how to fine-tune an LLM model using the techniques covered in these notebooks.
Prompt 5
Help me create an AI agent that can use multiple tools to solve problems step-by-step.
Open on GitHub → Explain another repo

Generated 2026-05-18 · Model: sonnet-4-6 · Verify against the repo before relying on details.