本页还没有译文
本页 6 段还没译成简体中文，下面显示的是英文原文。Store integrations
还没翻译译自英文（docs.langchain.com）本页 6 段都还没译
Stores enable long-term memory in LangGraph, allowing agents to persist and retrieve information across threads.
To implement your own store for a custom storage backend, see Build a custom store.
Integration components
- Typical retrieval flow: Document loaders → Text splitters → Embedding models → Vector stores → Retrievers → Chat models
- Agent capabilities: Tools, Middleware
- Execution and state: Sandboxes, Backends, Checkpointers, Stores (this page)
AI 翻译查看英文原文