langgraph-architecture

SKILL.md

| Single LLM call | Direct API call | Overhead not justified | | Linear pipeline | LangChain LCEL | Simpler abstraction | | Stateless tool use | Function calling | No persistence needed | | Simple RAG | LangChain retrievers | Built-in patterns | | Batch processing | Async tasks | Different execution model |

| Lightweight, faster | Runtime validation | | Dict-like access | Attribute access | | No validation overhead | Type coercion | | Simpler serialization | Complex nested models |

Recommendation: Use TypedDict for most cases. Use Pydantic when you need validation or complex nested structures.

Guide les décisions architecturales pour les applications LangGraph. À utiliser pour choisir entre LangGraph et les alternatives, choisir des stratégies de gestion d'état, concevoir des systèmes multi-agents ou sélectionner des approches de persistance et de streaming. Source : existential-birds/beagle.

Voir l'original