datawhalechina/llm-universe resource

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

13863 stars · 1407 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A Chinese-language open-source tutorial from Datawhale that teaches beginner developers how to build LLM applications through a hands-on personal knowledge base assistant project. It covers calling LLM APIs (with unified wrappers for providers like Baidu Wenxin, iFlytek Spark, and Zhipu AI), building vector-database-backed knowledge bases, constructing RAG pipelines with LangChain, deploying with Streamlit, and evaluation/iteration practices.

Use cases

• learn LLM application development from scratch as a Python beginner
• build a RAG chatbot over personal documents with LangChain
• call LLM APIs from multiple Chinese and international providers in a unified way
• set up a vector database knowledge base from mixed document types
• deploy an LLM question-answering app with Streamlit
• learn prompt engineering and retrieval optimization techniques
• understand how to evaluate and iterate on LLM applications

When to choose

• you have basic Python skills and want a structured, practice-first introduction to LLM app development
• you want to build a knowledge-base assistant / RAG application step by step
• you prefer API-based LLM development and have no GPU or ML background
• you learn best from Chinese-language notebooks with a guided course format

When to avoid

• you need production-ready software rather than educational material
• you want to deploy or fine-tune local open-source LLMs (the companion Self LLM project covers that)
• you seek deep theoretical foundations of large language models (see Datawhale's So Large LM)
• you need English-language instruction or a license-clarified codebase for reuse

Facets

learning-resource · maturity active

rag prompt-engineering vector-database chatbot large-language-models tutorials education python langchain streamlit llm-api knowledge-base jupyter-notebook chinese datawhale beginner-friendly fastapi course retrieval-augmented-generation natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="datawhalechina/llm-universe")