docs: make Chinese README the default

This commit is contained in:
wehub-resource-sync
2026-07-13 10:47:40 +00:00
parent 7851716730
commit ca72a93cbd
+67 -60
View File
@@ -1,3 +1,9 @@
<!-- 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/cloudwego/eino) · [上游 README](https://github.com/cloudwego/eino/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。
# Eino
![coverage](https://raw.githubusercontent.com/cloudwego/eino/badges/.badges/main/coverage.svg)
@@ -10,25 +16,25 @@
![Stars](https://img.shields.io/github/stars/cloudwego/eino)
![Forks](https://img.shields.io/github/forks/cloudwego/eino)
English | [中文](README.zh_CN.md)
[English](README.md) | 中文
# Overview
# 简介
**Eino['aino]** is an LLM application development framework in Golang. It draws from LangChain, Google ADK, and other open-source frameworks, and is designed to follow Golang conventions.
**Eino['aino]** 是一个 Go 语言的 LLM 应用开发框架,借鉴了 LangChainGoogle ADK 等开源项目,按照 Go 的惯例设计。
Eino provides:
- **[Components](https://github.com/cloudwego/eino-ext)**: reusable building blocks like `ChatModel`, `Tool`, `Retriever`, and `ChatTemplate`, with official implementations for OpenAI, Ollama, and more.
- **Agent Development Kit (ADK)**: build AI agents with tool use, multi-agent coordination, context management, interrupt/resume for human-in-the-loop, and ready-to-use agent patterns.
- **Composition**: connect components into graphs and workflows that can run standalone or be exposed as tools for agents.
- **[Examples](https://github.com/cloudwego/eino-examples)**: working code for common patterns and real-world use cases.
Eino 提供:
- **[组件](https://github.com/cloudwego/eino-ext)**`ChatModel``Tool``Retriever``ChatTemplate` 等可复用模块,官方实现覆盖 OpenAIOllama
- **智能体开发套件(ADK)**:支持工具调用、多智能体协同、上下文管理、中断/恢复等人机交互,以及开箱即用的智能体模式
- **编排**:把组件组装成图或工作流,既能独立运行,也能作为工具给智能体调用
- **[示例](https://github.com/cloudwego/eino-examples)**:常见模式和实际场景的可运行代码
![](.github/static/img/eino/eino_concept.jpeg)
# Quick Start
# 快速上手
## ChatModelAgent
Configure a ChatModel, optionally add tools, and you have a working agent:
配置好 ChatModel,加上工具(可选),就能跑起来:
```Go
chatModel, _ := openai.NewChatModel(ctx, &openai.ChatModelConfig{
@@ -51,7 +57,7 @@ for {
}
```
Add tools to give the agent capabilities:
加工具让智能体有更多能力:
```Go
agent, _ := adk.NewChatModelAgent(ctx, &adk.ChatModelAgentConfig{
@@ -64,13 +70,13 @@ agent, _ := adk.NewChatModelAgent(ctx, &adk.ChatModelAgentConfig{
})
```
The agent handles the ReAct loop internally — it decides when to call tools and when to respond.
智能体内部自动处理 ReAct 循环,自己判断什么时候调工具、什么时候回复。
→ [ChatModelAgent examples](https://github.com/cloudwego/eino-examples/tree/main/adk/intro) · [docs](https://www.cloudwego.io/docs/eino/core_modules/eino_adk/agent_implementation/chat_model/)
→ [ChatModelAgent 示例](https://github.com/cloudwego/eino-examples/tree/main/adk/intro) · [文档](https://www.cloudwego.io/zh/docs/eino/core_modules/eino_adk/agent_implementation/chat_model/)
## DeepAgent
For complex tasks, use DeepAgent. It breaks down problems into steps, delegates to sub-agents, and tracks progress:
复杂任务用 DeepAgent,它会把问题拆成步骤,分派给子智能体,并追踪进度:
```Go
deepAgent, _ := deep.New(ctx, &deep.Config{
@@ -87,13 +93,13 @@ runner := adk.NewRunner(ctx, adk.RunnerConfig{Agent: deepAgent})
iter := runner.Query(ctx, "Analyze the sales data in report.csv and generate a summary chart")
```
DeepAgent can be configured to coordinate multiple specialized agents, run shell commands, execute Python code, and search the web.
DeepAgent 可以配置成:协调多个专业智能体、跑 shell 命令、执行 Python、搜索网络。
→ [DeepAgent example](https://github.com/cloudwego/eino-examples/tree/main/adk/multiagent/deep) · [docs](https://www.cloudwego.io/docs/eino/core_modules/eino_adk/agent_implementation/deepagents/)
→ [DeepAgent 示例](https://github.com/cloudwego/eino-examples/tree/main/adk/multiagent/deep) · [文档](https://www.cloudwego.io/zh/docs/eino/core_modules/eino_adk/agent_implementation/deepagents/)
## Composition
## 编排
When you need precise control over execution flow, use `compose` to build graphs and workflows:
需要精确控制执行流程时,用 `compose` 搭图或工作流:
```Go
graph := compose.NewGraph[*Input, *Output]()
@@ -110,7 +116,7 @@ runnable, _ := graph.Compile(ctx)
result, _ := runnable.Invoke(ctx, input)
```
Compositions can be exposed as tools for agents, bridging deterministic workflows with autonomous behavior:
编排出来的流程可以包装成工具给智能体用,把确定性流程和自主决策结合起来:
```Go
tool, _ := graphtool.NewInvokableGraphTool(graph, "data_pipeline", "Process and validate data")
@@ -125,85 +131,86 @@ agent, _ := adk.NewChatModelAgent(ctx, &adk.ChatModelAgentConfig{
})
```
This lets you build domain-specific pipelines with exact control, then let agents decide when to use them.
这样你可以写出精确可控的业务流程,再让智能体决定什么时候调用。
→ [GraphTool examples](https://github.com/cloudwego/eino-examples/tree/main/adk/common/tool/graphtool) · [compose docs](https://www.cloudwego.io/docs/eino/core_modules/chain_and_graph_orchestration/)
→ [GraphTool 示例](https://github.com/cloudwego/eino-examples/tree/main/adk/common/tool/graphtool) · [编排文档](https://www.cloudwego.io/zh/docs/eino/core_modules/chain_and_graph_orchestration/)
# Key Features
# 主要特性
## Component Ecosystem
## 组件生态
Eino defines component abstractions (ChatModel, Tool, Retriever, Embedding, etc.) with official implementations for OpenAI, Claude, Gemini, Ark, Ollama, Elasticsearch, and more.
Eino 定义了组件抽象(ChatModelToolRetrieverEmbedding 等),官方实现覆盖 OpenAIClaudeGeminiArkOllamaElasticsearch 等。
→ [eino-ext](https://github.com/cloudwego/eino-ext)
## Stream Processing
## 流式处理
Eino automatically handles streaming throughout orchestration: concatenating, boxing, merging, and copying streams as data flows between nodes. Components only implement the streaming paradigms that make sense for them; the framework handles the rest.
Eino 在编排中自动处理流式:拼接、装箱、合并、复制。组件只需实现有业务意义的流式范式,框架处理剩下的。
→ [docs](https://www.cloudwego.io/docs/eino/core_modules/chain_and_graph_orchestration/stream_programming_essentials/)
→ [文档](https://www.cloudwego.io/zh/docs/eino/core_modules/chain_and_graph_orchestration/stream_programming_essentials/)
## Callback Aspects
## 回调切面
Inject logging, tracing, and metrics at fixed points (OnStart, OnEnd, OnError, OnStartWithStreamInput, OnEndWithStreamOutput) across components, graphs, and agents.
在固定切点(OnStartOnEndOnErrorOnStartWithStreamInputOnEndWithStreamOutput)注入日志、追踪、指标,适用于组件、图、智能体。
→ [docs](https://www.cloudwego.io/docs/eino/core_modules/chain_and_graph_orchestration/callback_manual/)
→ [文档](https://www.cloudwego.io/zh/docs/eino/core_modules/chain_and_graph_orchestration/callback_manual/)
## Interrupt/Resume
## 中断/恢复
Any agent or tool can pause execution for human input and resume from checkpoint. The framework handles state persistence and routing.
任何智能体或工具都能暂停等待人工输入,从检查点恢复。框架处理状态持久化和路由。
→ [docs](https://www.cloudwego.io/docs/eino/core_modules/eino_adk/agent_hitl/) · [examples](https://github.com/cloudwego/eino-examples/tree/main/adk/human-in-the-loop)
→ [文档](https://www.cloudwego.io/zh/docs/eino/core_modules/eino_adk/agent_hitl/) · [示例](https://github.com/cloudwego/eino-examples/tree/main/adk/human-in-the-loop)
# Framework Structure
# 框架结构
![](.github/static/img/eino/eino_framework.jpeg)
The Eino framework consists of:
Eino 框架包含:
- Eino (this repo): Type definitions, streaming mechanism, component abstractions, orchestration, agent implementations, aspect mechanisms
- Eino(本仓库):类型定义、流处理机制、组件抽象、编排、智能体实现、切面机制
- [EinoExt](https://github.com/cloudwego/eino-ext): Component implementations, callback handlers, usage examples, evaluators, prompt optimizers
- [EinoExt](https://github.com/cloudwego/eino-ext):组件实现、回调处理器、使用示例、评估器、提示优化器
- [Eino Devops](https://github.com/cloudwego/eino-ext/tree/main/devops): Visualized development and debugging
- [Eino Devops](https://github.com/cloudwego/eino-ext/tree/main/devops):可视化开发和调试
- [EinoExamples](https://github.com/cloudwego/eino-examples): Example applications and best practices
- [EinoExamples](https://github.com/cloudwego/eino-examples):示例应用和最佳实践
## Documentation
## 文档
- [Eino User Manual](https://www.cloudwego.io/zh/docs/eino/)
- [Eino: Quick Start](https://www.cloudwego.io/zh/docs/eino/quick_start/)
- [Eino 用户手册](https://www.cloudwego.io/zh/docs/eino/)
- [Eino: 快速开始](https://www.cloudwego.io/zh/docs/eino/quick_start/)
## Dependencies
- Go 1.18 and above.
## 依赖
- Go 1.18 及以上
## Code Style
## 代码规范
This repo uses `golangci-lint`. Check locally with:
本仓库使用 `golangci-lint`,本地检查:
```bash
golangci-lint run ./...
```
Rules enforced:
- Exported functions, interfaces, packages, etc. should have GoDoc comments
- Code should be formatted with `gofmt -s`
- Import order should follow `goimports` (std -> third party -> local)
规则:
- 导出的函数、接口、package 等需要 GoDoc 注释
- 代码格式符合 `gofmt -s`
- import 顺序符合 `goimports`std -> third party -> local
## Security
## 安全
If you discover a potential security issue in this project, or think you may
have discovered a security issue, we ask that you notify Bytedance Security via our [security center](https://security.bytedance.com/src) or [vulnerability reporting email](mailto:sec@bytedance.com?subject=Feedback%20On%20Eino).
如果你在该项目中发现潜在的安全问题,或你认为可能发现了安全问题,请通过我们的[安全中心](https://security.bytedance.com/src)
或[漏洞报告邮箱](mailto:sec@bytedance.com?subject=关于Eino的反馈)通知字节跳动安全团队。
Do **not** create a public GitHub issue.
## Contact
- Membership: [COMMUNITY MEMBERSHIP](https://github.com/cloudwego/community/blob/main/COMMUNITY_MEMBERSHIP.md)
- Issues: [Issues](https://github.com/cloudwego/eino/issues)
- Lark: Scan the QR code below with [Feishu](https://www.feishu.cn/en/) to join the CloudWeGo/eino user group.
请**不要**创建公开的 GitHub Issue。
## 联系我们
- 成为 member[COMMUNITY MEMBERSHIP](https://github.com/cloudwego/community/blob/main/COMMUNITY_MEMBERSHIP.md)
- Issues[Issues](https://github.com/cloudwego/eino/issues)
- 飞书:扫码加入 CloudWeGo/eino 用户群
&ensp;&ensp;&ensp; <img src=".github/static/img/eino/lark_group_zh.png" alt="LarkGroup" width="200"/>
## License
## 开源许可证
This project is licensed under the [Apache-2.0 License](LICENSE-APACHE).
本项目基于 [Apache-2.0 许可证](LICENSE-APACHE) 开源。