Slack

This notebook walks through connecting LangChain to your Slack account.

To use this toolkit, you will need to get a token explained in the Slack API docs. Once you've received a SLACK_USER_TOKEN, you can input it as an environmental variable below.

%pip install --upgrade --quiet  slack_sdk > /dev/null
%pip install --upgrade --quiet  beautifulsoup4 > /dev/null # This is optional but is useful for parsing HTML messages
%pip install --upgrade --quiet  python-dotenv > /dev/null # This is for loading environmental variables from a .env file

[notice] A new release of pip is available: 23.2.1 -> 23.3.2
[notice] To update, run: pip install --upgrade pip
Note: you may need to restart the kernel to use updated packages.

[notice] A new release of pip is available: 23.2.1 -> 23.3.2
[notice] To update, run: pip install --upgrade pip
Note: you may need to restart the kernel to use updated packages.

[notice] A new release of pip is available: 23.2.1 -> 23.3.2
[notice] To update, run: pip install --upgrade pip
Note: you may need to restart the kernel to use updated packages.

Set Environmental Variables

The toolkit will read the SLACK_USER_TOKEN environmental variable to authenticate the user so you need to set them here. You will also need to set your OPENAI_API_KEY to use the agent later.

# Set environmental variables here
# In this example, you set environmental variables by loading a .env file.
import dotenv

dotenv.load_dotenv()

True

Create the Toolkit and Get Tools

To start, you need to create the toolkit, so you can access its tools later.

from langchain_community.agent_toolkits import SlackToolkit

toolkit = SlackToolkit()
tools = toolkit.get_tools()
tools

[SlackGetChannel(client=<slack_sdk.web.client.WebClient object at 0x11eba6a00>),
 SlackGetMessage(client=<slack_sdk.web.client.WebClient object at 0x11eba69d0>),
 SlackScheduleMessage(client=<slack_sdk.web.client.WebClient object at 0x11eba65b0>),
 SlackSendMessage(client=<slack_sdk.web.client.WebClient object at 0x11eba6790>)]

Use within an ReAct Agent

from langchain import hub
from langchain.agents import AgentExecutor, create_openai_tools_agent
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(temperature=0, model="gpt-4")
prompt = hub.pull("hwchase17/openai-tools-agent")
agent = create_openai_tools_agent(
    tools=toolkit.get_tools(),
    llm=llm,
    prompt=prompt,
)
agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)

agent_executor.invoke(
    {
        "input": "Send a greeting to my coworkers in the #general channel. Note use `channel` as key of channel id, and `message` as key of content to sent in the channel."
    }
)

agent_executor.invoke(
    {"input": "How many channels are in the workspace? Please list out their names."}
)

> Entering new AgentExecutor chain...
I need to get the list of channels in the workspace.
Action: get_channelid_name_dict
Action Input: {}[{"id": "C052SCUP4UD", "name": "general", "created": 1681297313, "num_members": 1}, {"id": "C052VBBU4M8", "name": "test-bots", "created": 1681297343, "num_members": 2}, {"id": "C053805TNUR", "name": "random", "created": 1681297313, "num_members": 2}]I now have the list of channels and their names.
Final Answer: There are 3 channels in the workspace. Their names are "general", "test-bots", and "random".

> Finished chain.

{'input': 'How many channels are in the workspace? Please list out their names.',
 'output': 'There are 3 channels in the workspace. Their names are "general", "test-bots", and "random".'}

agent_executor.invoke(
    {
        "input": "Tell me the number of messages sent in the #introductions channel from the past month."
    }
)

> Entering new AgentExecutor chain...
First, I need to identify the channel ID for the #introductions channel.
Action: get_channelid_name_dict
Action Input: None[{"id": "C052SCUP4UD", "name": "general", "created": 1681297313, "num_members": 1}, {"id": "C052VBBU4M8", "name": "test-bots", "created": 1681297343, "num_members": 2}, {"id": "C053805TNUR", "name": "random", "created": 1681297313, "num_members": 2}]The #introductions channel is not listed in the observed channels. I need to inform the user that the #introductions channel does not exist or is not accessible.
Final Answer: The #introductions channel does not exist or is not accessible.

> Finished chain.

{'input': 'Tell me the number of messages sent in the #introductions channel from the past month.',
 'output': 'The #introductions channel does not exist or is not accessible.'}