wehub-resource-sync
2f46e31723
CI / changes (push) Has been cancelled
CI / Check SDK methods matching (push) Has been cancelled
CI / Check CLI schema hasn't changed #3.13 (push) Has been cancelled
CI / CLI integration test (push) Has been cancelled
CI / sdk-py integration test (push) Has been cancelled
CI / CI Success (push) Has been cancelled
CI / cd libs/langgraph (push) Has been cancelled
CI / cd libs/checkpoint (push) Has been cancelled
CI / cd libs/checkpoint-conformance (push) Has been cancelled
CI / cd libs/checkpoint-postgres (push) Has been cancelled
CI / cd libs/checkpoint-sqlite (push) Has been cancelled
CI / cd libs/cli (push) Has been cancelled
CI / cd libs/prebuilt (push) Has been cancelled
CI / cd libs/sdk-py (push) Has been cancelled
89 lines
6.4 KiB
Markdown
89 lines
6.4 KiB
Markdown
<!-- WEHUB_ZH_README -->
|
||
> [!NOTE]
|
||
> 本文档由 WeHub 基于上游 README 翻译整理，属于社区翻译，非官方中文文档。
|
||
> [English](./README.en.md) · [原始项目](https://github.com/langchain-ai/langgraph) · [上游 README](https://github.com/langchain-ai/langgraph/blob/HEAD/README.md)
|
||
> 原作者、版权与许可证归属以原始项目及本仓库 LICENSE 文件为准。
|
||
|
||
<div align="center">
|
||
<a href="https://www.langchain.com/langgraph">
|
||
<picture>
|
||
<source media="(prefers-color-scheme: dark)" srcset=".github/images/logo-dark.svg">
|
||
<source media="(prefers-color-scheme: light)" srcset=".github/images/logo-light.svg">
|
||
<img alt="LangGraph Logo" src=".github/images/logo-dark.svg" width="50%">
|
||
</picture>
|
||
</a>
|
||
</div>
|
||
|
||
<div align="center">
|
||
<h3>用于构建有状态智能体的底层编排框架。</h3>
|
||
</div>
|
||
|
||
<div align="center">
|
||
<a href="https://opensource.org/licenses/MIT" target="_blank"><img src="https://img.shields.io/pypi/l/langgraph" alt="PyPI - License"></a>
|
||
<a href="https://pypistats.org/packages/langgraph" target="_blank"><img src="https://img.shields.io/pepy/dt/langgraph" alt="PyPI - Downloads"></a>
|
||
<a href="https://pypi.org/project/langgraph/" target="_blank"><img src="https://img.shields.io/pypi/v/langgraph.svg?label=%20" alt="Version"></a>
|
||
<a href="https://x.com/langchain_oss" target="_blank"><img src="https://img.shields.io/twitter/url/https/twitter.com/langchain_oss.svg?style=social&label=Follow%20%40LangChain" alt="Twitter / X"></a>
|
||
</div>
|
||
|
||
<br>
|
||
|
||
受到 Klarna、Replit、Elastic 等正在塑造智能体未来格局的企业的信赖，LangGraph 是一款用于构建、管理和部署长时间运行、有状态智能体的底层编排框架。
|
||
|
||
```bash
|
||
pip install -U langgraph
|
||
```
|
||
|
||
> [!TIP]
|
||
> 如果你想快速构建智能体，可以查看 **[Deep Agents](https://docs.langchain.com/oss/python/deepagents/overview)** — 基于 LangGraph 构建的更高级别包，适用于能够规划、使用子智能体并利用文件系统处理复杂任务的智能体。
|
||
|
||
如需等价的 JS/TS 库，请查看 [LangGraph.js](https://github.com/langchain-ai/langgraphjs) 以及 [JS 文档](https://docs.langchain.com/oss/javascript/langgraph/overview).
|
||
|
||
## 为何使用 LangGraph？
|
||
|
||
LangGraph 为*任意*长时间运行、有状态的工作流或智能体提供底层支撑基础设施：
|
||
|
||
- **[持久执行（Durable execution）](https://docs.langchain.com/oss/python/langgraph/durable-execution)** — 构建能够经受故障、可长时间运行，并在中断后从准确位置自动恢复的智能体。
|
||
- **[人机协同（Human-in-the-loop）](https://docs.langchain.com/oss/python/langgraph/interrupts)** — 通过在执行过程中随时检查和修改智能体状态，无缝融入人工监督。
|
||
- **[全面记忆（Comprehensive memory）](https://docs.langchain.com/oss/python/langgraph/memory)** — 创建真正有状态的智能体，同时具备用于持续推理的短期工作记忆，以及跨会话的长期持久记忆。
|
||
- **[使用 LangSmith 调试](https://www.langchain.com/langsmith)** — 借助可视化工具深入了解复杂智能体行为，追踪执行路径、捕获状态转换，并提供详细的运行时指标。
|
||
- **[生产级部署（Production-ready deployment）](https://docs.langchain.com/langsmith/deployments)** — 借助专为有状态、长时间运行工作流独特挑战而设计的可扩展基础设施，自信地部署复杂的智能体系统。
|
||
|
||
> [!TIP]
|
||
> 如需开发、调试和部署 AI 智能体与 LLM 应用，请参阅 [LangSmith](https://docs.langchain.com/langsmith/home).
|
||
|
||
## LangGraph 生态系统
|
||
|
||
LangGraph 可独立使用，也能与任何 LangChain 产品无缝集成，为开发者提供构建智能体的全套工具。
|
||
|
||
为提升 LLM 应用开发效率，可将 LangGraph 与以下产品搭配使用：
|
||
|
||
- [Deep Agents](https://docs.langchain.com/oss/python/deepagents/overview) – 构建能够规划、使用子智能体并利用文件系统处理复杂任务的智能体。
|
||
- [LangChain](https://docs.langchain.com/oss/python/langchain/overview) – 提供集成与可组合组件，简化 LLM 应用开发。
|
||
- [LangSmith](https://www.langchain.com/langsmith) – 有助于智能体评估与可观测性。调试表现不佳的 LLM 应用运行、评估智能体轨迹、获得生产环境可见性，并随时间提升性能。
|
||
- [LangSmith Deployment](https://docs.langchain.com/langsmith/deployments) – 借助专为长时间运行、有状态工作流打造的部署平台，轻松部署和扩展智能体。在团队间发现、复用、配置和共享智能体——并通过 [LangSmith Studio](https://docs.langchain.com/langsmith/studio). 中的可视化原型设计快速迭代。
|
||
|
||
---
|
||
|
||
## 文档
|
||
|
||
- [docs.langchain.com](https://docs.langchain.com/oss/python/langgraph/overview) – 全面文档，包括概念概览与指南
|
||
- [reference.langchain.com/python/langgraph](https://reference.langchain.com/python/langgraph) – LangGraph 软件包的 API 参考文档
|
||
- [LangGraph Quickstart](https://docs.langchain.com/oss/python/langgraph/quickstart) – 开始使用 LangGraph 进行构建
|
||
- [Chat LangChain](https://chat.langchain.com/) – 与 LangChain 文档对话，获取问题解答
|
||
|
||
**讨论**：访问 [LangChain Forum](https://forum.langchain.com) 与社区交流，分享你的技术问题、想法与反馈。
|
||
|
||
## 更多资源
|
||
|
||
- **[指南（Guides）](https://docs.langchain.com/oss/python/learn)** – 针对流式传输、添加记忆与持久化、设计模式（如分支、子图等）等主题的快速、可操作的代码片段。
|
||
- **[LangChain Academy](https://academy.langchain.com/courses/intro-to-langgraph)** – 在我们的免费结构化课程中学习 LangGraph 基础知识。
|
||
- **[案例研究（Case studies）](https://www.langchain.com/built-with-langgraph)** – 了解行业领导者如何借助 LangGraph 大规模交付 AI 应用。
|
||
- [Contributing Guide](https://docs.langchain.com/oss/python/contributing/overview) – 了解如何为 LangChain 项目做贡献，并找到适合新手的议题。
|
||
- [Code of Conduct](https://github.com/langchain-ai/langchain/?tab=coc-ov-file) – 我们的社区准则与参与标准。
|
||
|
||
---
|
||
|
||
## 致谢
|
||
|
||
LangGraph 的灵感来自 [Pregel](https://research.google/pubs/pub37252/) 和 [Apache Beam](https://beam.apache.org/). 公共接口的设计借鉴了 [NetworkX](https://networkx.org/documentation/latest/). LangGraph 由 LangChain 的创建者 LangChain Inc 构建，但无需 LangChain 亦可使用。
|