跳至主要内容

Connery 工具包和工具

使用 Connery 工具包和工具，您可以将 Connery 操作集成到您的 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，您可以轻松地创建一个带有操作集的自定义插件，并将其无缝集成到您的 LangChain 代理中。Connery 将负责处理关键方面，例如运行时、授权、密钥管理、访问管理、审计日志以及其他重要功能。

此外，Connery 在社区的支持下，提供各种现成的开源插件，以提供更多便利。

了解有关 Connery 的更多信息

设置​

安装​

您需要安装 langchain_community 包才能使用 Connery 工具。

%pip install -qU langchain-community

凭据​

要在您的 LangChain 代理中使用 Connery 操作，您需要进行一些准备

  1. 使用 快速入门指南 设置 Connery 运行程序。
  2. 安装所有带有您想要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，以便工具包能够与 Connery 运行程序进行通信。
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，我们创建一个代理，使用两个 Connery 操作来总结公共网页并通过电子邮件发送摘要

  1. 来自 Summarization 插件的 **总结公共网页** 操作。
  2. 来自 Gmail 插件的 **发送电子邮件** 操作。

您可以查看此示例的 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 = "[email protected]"

# 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': '[email protected]', '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': '<[email protected]>'}I have sent the email with the summary of the webpage to [email protected]. Please check your inbox.

> Finished chain.
I have sent the email with the summary of the webpage to [email protected]. Please check your inbox.

注意: Connery 操作是一个结构化工具，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 = "[email protected]"

# 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 函数代理运行操作。

您可以查看此示例的 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': '[email protected]', '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': '<[email protected]>'}I have sent an email to [email protected] informing them that you will be late for the meeting.

> Finished chain.
I have sent an email to [email protected] informing them that you will be late for the meeting.

注意: Connery 操作是一个结构化工具，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，请前往 API 参考

此页面对您有帮助吗？


您也可以在 GitHub 上留下详细的反馈 GitHub.