Slack工具包

class langchain_community.agent_toolkits.slack.toolkit.SlackToolkit

基础类：BaseToolkit

用于与Slack交互的工具包。

Parameters:

client – Slack客户端。

Setup:

安装 slack_sdk 并设置环境变量 SLACK_USER_TOKEN。

pip install -U slack_sdk
export SLACK_USER_TOKEN="your-user-token"

Key init args:

client: slack_sdk.WebClient

Slack 客户端。

Instantiate:

from langchain_community.agent_toolkits import SlackToolkit

toolkit = SlackToolkit()

Tools:

tools = toolkit.get_tools()
tools

[SlackGetChannel(client=<slack_sdk.web.client.WebClient object at 0x113caa8c0>),
SlackGetMessage(client=<slack_sdk.web.client.WebClient object at 0x113caa4d0>),
SlackScheduleMessage(client=<slack_sdk.web.client.WebClient object at 0x113caa440>),
SlackSendMessage(client=<slack_sdk.web.client.WebClient object at 0x113caa410>)]

Use within an agent:

from langchain_openai import ChatOpenAI
from langgraph.prebuilt import create_react_agent

llm = ChatOpenAI(model="gpt-4o-mini")
agent_executor = create_react_agent(llm, tools)

example_query = "When was the #general channel created?"

events = agent_executor.stream(
    {"messages": [("user", example_query)]},
    stream_mode="values",
)
for event in events:
    message = event["messages"][-1]
    if message.type != "tool":  # mask sensitive information
        event["messages"][-1].pretty_print()

 ================================[1m Human Message [0m=================================

When was the #general channel created?
==================================[1m Ai Message [0m==================================
Tool Calls:
get_channelid_name_dict (call_NXDkALjoOx97uF1v0CoZTqtJ)
Call ID: call_NXDkALjoOx97uF1v0CoZTqtJ
Args:
==================================[1m Ai Message [0m==================================

The #general channel was created on timestamp 1671043305.

通过解析和验证来自关键字参数的输入数据来创建一个新模型。

如果输入数据无法验证以形成有效模型，则引发 [ValidationError][pydantic_core.ValidationError]。

self 被显式地设为仅位置参数，以允许 self 作为字段名称。

param client: WebClient [Optional]

get_tools() → List[BaseTool]

获取工具包中的工具。

Return type:

列表[BaseTool]

使用 SlackToolkit 的示例

• Slack

• Slack Toolkit