LangChain Architecture: Models, Prompts, Chains
The three building blocks: ChatModels, PromptTemplates, and chains that compose them.
Why LangChain?
LangChain is the most popular Python framework for building LLM apps. It provides:
- Adapters for every major LLM provider
- Loaders and parsers for many data sources
- Memory, agents, and chains primitives
- Vector store integrations
Critics call it bloated; supporters love its breadth. We focus on the core that has stabilised: LCEL.
Three Core Concepts
- Models — LLMs and ChatModels you call
- Prompts — templates that produce messages
- Chains — compositions that pipe prompts -> models -> parsers
All lessons in this course
- LangChain Architecture: Models, Prompts, Chains
- Loaders, Splitters and Vector Stores
- LCEL (LangChain Expression Language)
- Building a RAG Chain End-to-End