#4242nd of 55 in Learning and cookbooks
llm-universe
Chinese-language course on building a RAG knowledge-base assistant with LLM APIs
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 14.2k
- License
- no license
- Last commit
- Aug 2026
- Last release
- Apr 2024
- Language
- Jupyter Notebook
Missed the latest GitHub check; these facts may be older.
Overview
A Jupyter Notebook tutorial from Datawhale that walks beginners through building a personal knowledge-base assistant. It covers calling LLM APIs (OpenAI, Baidu Wenxin, iFlytek Spark, Zhipu GLM), building a vector store, a LangChain retrieval QA chain, Streamlit deployment, and evaluation. Part 1 is complete; the advanced RAG and case-study parts are still in progress.
Who it is for: Python developers new to LLM app development, Chinese readers
Strengths
- Single worked project from API calls to Streamlit deployment and evaluation
- Wraps several LLM APIs (GPT, Wenxin, Spark, GLM) behind one calling interface
- No GPU needed; runs on a laptop or a server
- Online book and PDF release available alongside the notebooks
Weaknesses
- Written in Chinese; the README gives no English version
- Parts 2 and 3 (advanced RAG, case studies) are unfinished
- Relies on third-party model APIs rather than local models
- No license detected; last release was April 2024
What it needs
- no GPU
- Needs Python 3.8+, LangChain, Streamlit, LLM provider API keys
- Models: OpenAI GPT, Baidu Wenxin, iFlytek Spark, Zhipu GLM
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 |