Skip to main content
Open In ColabOpen on GitHub

Connery 工具包和工具

使用Connery工具包和工具，您可以将Connery Actions集成到您的LangChain代理中。

什么是Connery？​

Connery 是一个用于 AI 的开源插件基础设施。

使用Connery，您可以轻松创建一组操作的自定义插件，并无缝集成到您的LangChain代理中。 Connery将负责关键方面，如运行时、授权、秘密管理、访问管理、审计日志和其他重要功能。

此外，Connery 在我们的社区支持下，提供了多样化的现成开源插件，以增加便利性。

了解更多关于Connery的信息：

设置​

安装​

你需要安装langchain_community包来使用Connery工具。

%pip install -qU langchain-community

凭证​

要在您的LangChain代理中使用Connery Actions，您需要进行一些准备工作：

  1. 使用快速入门指南设置Connery运行器。
  2. 安装所有包含您想在代理中使用的操作的插件。
  3. 设置环境变量 CONNERY_RUNNER_URL 和 CONNERY_RUNNER_API_KEY，以便工具包可以与 Connery Runner 进行通信。
import getpass
import os

for key in ["CONNERY_RUNNER_URL", "CONNERY_RUNNER_API_KEY"]:
    if key not in os.environ:
        os.environ[key] = getpass.getpass(f"Please enter the value for {key}: ")

工具包​

在下面的示例中，我们创建了一个代理，该代理使用两个Connery Actions来总结一个公共网页并通过电子邮件发送摘要：

  1. 总结公共网页 动作来自 Summarization 插件。
  2. 发送电子邮件 动作来自 Gmail 插件。

你可以查看这个例子的LangSmith跟踪这里。

import os

from langchain.agents import AgentType, initialize_agent
from langchain_community.agent_toolkits.connery import ConneryToolkit
from langchain_community.tools.connery import ConneryService
from langchain_openai import ChatOpenAI

# Specify your Connery Runner credentials.
os.environ["CONNERY_RUNNER_URL"] = ""
os.environ["CONNERY_RUNNER_API_KEY"] = ""

# Specify OpenAI API key.
os.environ["OPENAI_API_KEY"] = ""

# Specify your email address to receive the email with the summary from example below.
recepient_email = "test@example.com"

# Create a Connery Toolkit with all the available actions from the Connery Runner.
connery_service = ConneryService()
connery_toolkit = ConneryToolkit.create_instance(connery_service)

# Use OpenAI Functions agent to execute the prompt using actions from the Connery Toolkit.
llm = ChatOpenAI(temperature=0)
agent = initialize_agent(
    connery_toolkit.get_tools(), llm, AgentType.OPENAI_FUNCTIONS, verbose=True
)
result = agent.run(
    f"""Make a short summary of the webpage http://www.paulgraham.com/vb.html in three sentences
and send it to {recepient_email}. Include the link to the webpage into the body of the email."""
)
print(result)


> Entering new AgentExecutor chain...

Invoking: `CA72DFB0AB4DF6C830B43E14B0782F70` with `{'publicWebpageUrl': 'http://www.paulgraham.com/vb.html'}`


{'summary': 'The author reflects on the concept of life being short and how having children made them realize the true brevity of life. They discuss how time can be converted into discrete quantities and how limited certain experiences are. The author emphasizes the importance of prioritizing and eliminating unnecessary things in life, as well as actively pursuing meaningful experiences. They also discuss the negative impact of getting caught up in online arguments and the need to be aware of how time is being spent. The author suggests pruning unnecessary activities, not waiting to do things that matter, and savoring the time one has.'}
Invoking: `CABC80BB79C15067CA983495324AE709` with `{'recipient': 'test@example.com', 'subject': 'Summary of the webpage', 'body': 'Here is a short summary of the webpage http://www.paulgraham.com/vb.html:\n\nThe author reflects on the concept of life being short and how having children made them realize the true brevity of life. They discuss how time can be converted into discrete quantities and how limited certain experiences are. The author emphasizes the importance of prioritizing and eliminating unnecessary things in life, as well as actively pursuing meaningful experiences. They also discuss the negative impact of getting caught up in online arguments and the need to be aware of how time is being spent. The author suggests pruning unnecessary activities, not waiting to do things that matter, and savoring the time one has.\n\nYou can find the full webpage [here](http://www.paulgraham.com/vb.html).'}`


{'messageId': '<2f04b00e-122d-c7de-c91e-e78e0c3276d6@gmail.com>'}I have sent the email with the summary of the webpage to test@example.com. Please check your inbox.

> Finished chain.
I have sent the email with the summary of the webpage to test@example.com. Please check your inbox.

注意：Connery Action 是一个结构化工具，因此您只能在支持结构化工具的代理中使用它。

工具​

import os

from langchain.agents import AgentType, initialize_agent
from langchain_community.tools.connery import ConneryService
from langchain_openai import ChatOpenAI

# Specify your Connery Runner credentials.
os.environ["CONNERY_RUNNER_URL"] = ""
os.environ["CONNERY_RUNNER_API_KEY"] = ""

# Specify OpenAI API key.
os.environ["OPENAI_API_KEY"] = ""

# Specify your email address to receive the emails from examples below.
recepient_email = "test@example.com"

# Get the SendEmail action from the Connery Runner by ID.
connery_service = ConneryService()
send_email_action = connery_service.get_action("CABC80BB79C15067CA983495324AE709")

手动运行操作。

manual_run_result = send_email_action.run(
    {
        "recipient": recepient_email,
        "subject": "Test email",
        "body": "This is a test email sent from Connery.",
    }
)
print(manual_run_result)

使用OpenAI Functions代理运行操作。

你可以查看这个例子的LangSmith跟踪这里。

llm = ChatOpenAI(temperature=0)
agent = initialize_agent(
    [send_email_action], llm, AgentType.OPENAI_FUNCTIONS, verbose=True
)
agent_run_result = agent.run(
    f"Send an email to the {recepient_email} and say that I will be late for the meeting."
)
print(agent_run_result)


> Entering new AgentExecutor chain...

Invoking: `CABC80BB79C15067CA983495324AE709` with `{'recipient': 'test@example.com', 'subject': 'Late for Meeting', 'body': 'Dear Team,\n\nI wanted to inform you that I will be late for the meeting today. I apologize for any inconvenience caused. Please proceed with the meeting without me and I will join as soon as I can.\n\nBest regards,\n[Your Name]'}`


{'messageId': '<d34a694d-50e0-3988-25da-e86b4c51d7a7@gmail.com>'}I have sent an email to test@example.com informing them that you will be late for the meeting.

> Finished chain.
I have sent an email to test@example.com informing them that you will be late for the meeting.

注意：Connery Action 是一个结构化工具，因此您只能在支持结构化工具的代理中使用它。

API参考​

有关所有Connery功能和配置的详细文档，请参阅API参考：

这个页面有帮助吗？