Artificial Intelligence
Third-party frameworks, tools, and platforms. 12 topics across 4 chapters.
Frameworks & Platforms
4 topicsLangChain
The most-used LLM application framework — scaffolding that standardises 'call model + call tools + orchestrate flow'.
LlamaIndex
A framework that specialises in 'data ingestion + RAG' — the fastest way to feed your private content to an LLM.
LangGraph
The de-facto standard for expressing agents / workflows as code-defined state machines.
Dify / Coze (visual agent platforms)
Drag-and-drop platforms that turn RAG / Workflow / Skills into a no-code AI app builder.
Inference & Local Runtimes
3 topicsAPIs & Providers
3 topicsOpenAI-Compatible API (the de-facto standard)
Why almost every model platform pretends to be OpenAI — one API powers the whole industry.
Chinese API Providers (DeepSeek / Qwen / GLM / Kimi)
Cheap, strong, locally compliant — the LLM services Chinese developers use most.
OpenRouter (model aggregation)
One key, many vendors — unified billing, automatic routing, automatic fallback.