langgraph-python-quickstart

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

LangGraph Python quickstart

LangGraph Python快速入门

Follow the live docs — do not invent an alternate API from memory:

https://docs.langchain.com/oss/python/langgraph/quickstart

Fetch that page (Docs MCP or HTTP) and implement what it shows (calculator / math agent with the Graph API). Prefer the Graph API path over the Functional API unless the user asks otherwise. Skip IPython graph visualization.

请遵循在线文档——不要凭记忆自行编写替代API：

https://docs.langchain.com/oss/python/langgraph/quickstart

获取该页面内容（通过Docs MCP或HTTP）并实现其中展示的功能（使用Graph API构建计算器/数学Agent）。除非用户另有要求，否则优先使用Graph API而非Functional API。跳过IPython图表可视化步骤。

Local setup constraints

本地设置约束

Apply these on top of the quickstart (they keep setup minimal and model-agnostic):

Ask which provider/model to use. Showcase that LangGraph works with any LangChain chat model. Suggested prompt:
Which model should this agent use? Pass a
```
provider:model
```
string — e.g.
```
openai:gpt-5.5
```
,
```
anthropic:claude-sonnet-5
```
,
```
google_genai:gemini-2.5-flash-lite
```
. Default if you're unsure: anthropic:claude-sonnet-5
.
The docs often hardcode Anthropic — replace with
```
init_chat_model("<MODEL>")
```
(or equivalent) using their choice. If using Claude Sonnet 5+, omit
```
temperature
```
/
```
top_p
```
/
```
top_k
```
(unsupported).
Create a new directory (e.g.
```
langgraph-agent/
```
) and do all work there — do not pollute the open project.
Only secret: the provider API key in
```
.env
```
(gitignored). No LangSmith / Tavily unless they ask. Prefer they edit
```
.env
```
themselves — don't paste keys into chat.
Install packages from the quickstart plus the provider package for their model.
Run the example (e.g. “Add 3 and 4.”), show output, then stop. Point to
```
langgraph-fundamentals
```
for next steps. For a higher-level agent API, use LangChain
```
create_agent
```
instead.

在快速入门基础上应用以下规则（这些规则可确保设置极简且与模型无关）：

询问要使用的提供商/模型。展示LangGraph可与任意LangChain聊天模型配合使用。建议提示语：
该Agent应使用哪个模型？请传入
```
provider:model
```
格式的字符串——例如
```
openai:gpt-5.5
```
、
```
anthropic:claude-sonnet-5
```
、
```
google_genai:gemini-2.5-flash-lite
```
。如果不确定，默认使用：anthropic:claude-sonnet-5
。
文档中通常硬编码使用Anthropic——请替换为用户选择的
```
init_chat_model("<MODEL>")
```
（或等效代码）。如果使用Claude Sonnet 5+，请省略
```
temperature
```
/
```
top_p
```
/
```
top_k
```
参数（该模型不支持这些参数）。
创建一个新目录（例如
```
langgraph-agent/
```
）并在该目录中完成所有操作——不要污染现有项目。
仅需保密的内容：
```
.env
```
文件中的提供商API密钥（已添加到git忽略列表）。除非用户要求，否则不使用LangSmith / Tavily。优先让用户自行编辑
```
.env
```
文件——不要将密钥粘贴到聊天框中。
安装快速入门指南中提到的包，加上对应模型提供商的包。
运行示例（例如“计算3加4”），展示输出结果后停止。后续步骤可参考
```
langgraph-fundamentals
```
。如果需要更高级的Agent API，请使用LangChain
```
create_agent
```
。",