deepagents-python-quickstart

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Deep Agents Python quickstart

Deep Agents Python快速入门

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

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

Fetch that page (Docs MCP or HTTP) and implement the research-agent shape it shows (

create_deep_agent

, research system prompt, invoke with a research question like “What is LangGraph?”).

请遵循在线文档操作——不要凭记忆自行设计替代API：

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

获取该页面内容（通过Docs MCP或HTTP）并实现其中展示的research-agent结构（

create_deep_agent

、研究系统提示词、传入研究问题如“What is LangGraph?”进行调用）。

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 Deep Agents are model-agnostic. 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-3.5-flash
```
. Default if you're unsure: anthropic:claude-sonnet-5
.
We'll use that provider's built-in web search (no separate search API key).
Create a new directory (e.g.
```
deep-agent/
```
) and do all work there — do not pollute the open project.
Do not use Tavily (or any second search vendor). Replace the quickstart's
```
internet_search
```
/ Tavily tool with the chosen provider's built-in web search. Look up the current tool shape on that provider's LangChain chat docs (examples as of writing — re-check if needed):
Provider Built-in search tool
Anthropic
{"type": "web_search_20260209", "name": "web_search", "max_uses": 5}
OpenAI
{"type": "web_search"}
Google
{"google_search": {}}
Prefer Anthropic / OpenAI / Google so provider search is available. Only secret: that provider's API key in
```
.env
```
(gitignored). Skip LangSmith tracing unless they ask.
Install
```
deepagents
```
(+
```
python-dotenv
```
) and the provider package for their model — not
```
tavily-python
```
.
Run the research example, show output, then stop. Point to
```
deep-agents-core
```
/ customization / Managed Deep Agents for next steps.

Provider	Built-in search tool
Anthropic	`{"type": "web_search_20260209", "name": "web_search", "max_uses": 5}`
OpenAI	`{"type": "web_search"}`
Google	`{"google_search": {}}`

在快速入门基础上应用以下约束（这些约束可保持设置极简且与模型无关）：

询问要使用的提供商/模型。展示Deep Agents的模型无关特性。建议提示词：
该代理应使用哪个模型？请传入
```
provider:model
```
格式的字符串——例如
```
openai:gpt-5.5
```
、
```
anthropic:claude-sonnet-5
```
、
```
google_genai:gemini-3.5-flash
```
。若不确定，默认使用：anthropic:claude-sonnet-5
。
我们将使用该提供商的内置网页搜索功能（无需单独的搜索API密钥）。
创建一个新目录（例如
```
deep-agent/
```
）并在其中完成所有操作——不要污染现有项目。
不要使用Tavily（或任何其他第三方搜索供应商）。将快速入门中的
```
internet_search
```
/Tavily工具替换为所选提供商的内置网页搜索。请查阅该提供商LangChain聊天文档中的当前工具结构（撰写本文时的示例——如有需要请重新核对）：
提供商内置搜索工具
Anthropic
{"type": "web_search_20260209", "name": "web_search", "max_uses": 5}
OpenAI
{"type": "web_search"}
Google
{"google_search": {}}
优先选择Anthropic/OpenAI/Google，因为这些提供商支持内置搜索功能。唯一需要的密钥是该提供商的API密钥，需存储在
```
.env
```
文件中（已添加到git忽略列表）。除非用户要求，否则跳过LangSmith追踪。
安装
```
deepagents
```
（以及
```
python-dotenv
```
）和对应模型的提供商包——不要安装
```
tavily-python
```
。
运行研究示例，展示输出结果，然后停止。后续步骤可参考
```
deep-agents-core
```
/自定义/托管Deep Agents。