Skip to main content
本文帮助您快速上手 Gmail 工具包。该工具包与 Gmail API 交互，支持读取邮件、起草和发送邮件等操作。关于 GmailToolkit 所有功能和配置的详细文档，请访问 API 参考。

​
配置

使用此工具包需要按照 Gmail API 文档中的说明设置凭据。下载 credentials.json 文件后，即可开始使用 Gmail API。

​
安装

此工具包位于 langchain-google-community 包中，需要安装 gmail 扩展： 
pip install -qU langchain-google-community\[gmail\]
要启用单个工具的自动追踪，请设置您的 LangSmith API 密钥： 
os.environ["LANGSMITH_TRACING"] = "true"
os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")

​
实例化

默认情况下，工具包会读取本地的 credentials.json 文件。您也可以手动提供 Credentials 对象。 
from langchain_google_community import GmailToolkit

toolkit = GmailToolkit()

​
自定义身份验证

在底层，系统会使用以下方法创建 googleapi 资源。 您可以手动构建 googleapi 资源以获得更多身份验证控制。 
from langchain_google_community.gmail.utils import (
    build_resource_service,
    get_gmail_credentials,
)

# 可在此处查看权限范围：https://developers.google.com/gmail/api/auth/scopes
# 例如，只读权限范围为 'https://www.googleapis.com/auth/gmail.readonly'
credentials = get_gmail_credentials(
    token_file="token.json",
    scopes=["https://mail.google.com/"],
    client_secrets_file="credentials.json",
)
api_resource = build_resource_service(credentials=credentials)
toolkit = GmailToolkit(api_resource=api_resource)

​
工具

查看可用工具： 
tools = toolkit.get_tools()
tools

[GmailCreateDraft(api_resource=<googleapiclient.discovery.Resource object at 0x1094509d0>),
 GmailSendMessage(api_resource=<googleapiclient.discovery.Resource object at 0x1094509d0>),
 GmailSearch(api_resource=<googleapiclient.discovery.Resource object at 0x1094509d0>),
 GmailGetMessage(api_resource=<googleapiclient.discovery.Resource object at 0x1094509d0>),
 GmailGetThread(api_resource=<googleapiclient.discovery.Resource object at 0x1094509d0>)]

​
在 Agent 中使用

以下演示如何将工具包集成到 Agent 中。 需要一个 LLM 或聊天模型： 
# | output: false
# | echo: false

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(model="gpt-4.1-mini", temperature=0)

from langchain.agents import create_agent


agent_executor = create_agent(llm, tools)

example_query = "Draft an email to fake@fake.com thanking them for coffee."

events = agent_executor.stream(
    {"messages": [("user", example_query)]},
    stream_mode="values",
)
for event in events:
    event["messages"][-1].pretty_print()

================================ Human Message =================================

Draft an email to fake@fake.com thanking them for coffee.
================================== Ai Message ==================================
Tool Calls:
  create_gmail_draft (call_slGkYKZKA6h3Mf1CraUBzs6M)
 Call ID: call_slGkYKZKA6h3Mf1CraUBzs6M
  Args:
    message: Dear Fake,

I wanted to take a moment to thank you for the coffee yesterday. It was a pleasure catching up with you. Let's do it again soon!

Best regards,
[Your Name]
    to: ['fake@fake.com']
    subject: Thank You for the Coffee
================================= Tool Message =================================
Name: create_gmail_draft

Draft created. Draft Id: r-7233782721440261513
================================== Ai Message ==================================

I have drafted an email to fake@fake.com thanking them for the coffee. You can review and send it from your email draft with the subject "Thank You for the Coffee".

​
API 参考

关于 GmailToolkit 所有功能和配置的详细文档，请访问 API 参考。
Edit this page on GitHub or file an issue.
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.