LiteLLM

This guide explains how to use Integry with LiteLLM to post a message on Slack.

1. Install Required Libraries

First, you need to install the necessary packages:

Integry requires Python version 3.12 or higher

• Integry enables seamless integration of structured tools and functions from over 300 apps

• LiteLLM is an AI orchestration framework that simplifies model access, spend tracking, and fallbacks across 100+ LLMs in the OpenAI format

pip install integry litellm

2. Initialize Integry & Agent

Import the necessary Libraries

import litellm
from integry import Integry
from integry import handle_litellm_tool_calls

user_id is how you define users in your app or agent. By default, your email used during your Integry signup can act as a user_id as well. Function Calls and Integrations are linked to this id.

For example:

user_id = "[email protected]" #replace with your email used during sign up

Below code snippet initializes the Integry class to interact with the Integry API using the App-Key and App-Secret.

You can view and copy your App-Key and App-Secret from the Workspace Settings.

Workspace Settings

To begin using Integry, you first set the App Key and App Secret as environment variables. Here is a quick way

os.environ["INTEGRY_APP_KEY"] = "your_app_key_here"
os.environ["INTEGRY_APP_SECRET"] = "your_app_secret_here"

Initializing the Integry object

integry = Integry(
    app_key=os.environ.get("INTEGRY_APP_KEY"),
    app_secret=os.environ.get("INTEGRY_APP_SECRET"),
)

Now retrieving the Open AI API Key from the enviroment. You can get the API Key from the OpenAI Platform

os.environ.get("OPENAI_API_KEY")

3. Register the Integry Function as a Tool

Perfect! Before you can use the functions available in Integry, you need to add the app to Integry. Slack, however, is pre-added to your Integry account, so there’s no need to add it manually.

To enable the assistant to call the function, we register it with the LiteLLM agents. Now that everything is set up, we will send a message in Slack using the Integry slack-post-message function.

slack_post_message = await integry.functions.get("slack-post-message", user_id)

messages = [{"role": "user", "content": "Say hello to my team on slack."}]

response = await litellm.acompletion(
    model="gpt-3.5-turbo-1106",
    messages=messages,
    tools=[slack_post_message.get_litellm_tool()],
    tool_choice="auto",
)

4. Connect Your Slack Account

To allow the agent to send a message on Slack on your user's behalf, the user must connect their Slack account. To connect a Slack account against the provided user ID, execute the following snippet.

slack = await integry.apps.get("slack", user_id)
print(slack.login_url)

This will print a URL which can be opened in a web browser to connect Slack.

5. Execute Agent

This will execute the agent and send a Hello message to the Slack channel.

await handle_litellm_tool_calls(response, user_id, [slack_post_message])

This will send the message to the slack channel. Here is reference image.

The message has been sent successfully in slack #random channel. You can verify the successful message delivery by checking the highlighted content in the response below.

[ True, 'channel': 'C086GCY1J9E', 'ts': '1741104288.244099', 'message': {'user': 'U086GBQHLG0', 'type': 'message', 'ts': '1741104288.244099', 'bot_id': 'B086E311JTB', 'app_id': 'A6FQL4KQC', 'text': 'Hello team! Just wanted to say hi from the assistant bot.', 'team': 'T086682UW57', 'bot_profile': {'id': 'B086E311JTB', 'app_id': 'A6FQL4KQC', 'name': 'Integry', 'icons': {'image_36': 'https://slack-files2.s3-us-west-2.amazonaws.com/avatars/2017-08-09/225182834294_8020ddc74d7822b48ea1_36.png', 'image_48': 'https://slack-files2.s3-us-west-2.amazonaws.com/avatars/2017-08-09/225182834294_8020ddc74d7822b48ea1_48.png', 'image_72': 'https://slack-files2.s3-us-west-2.amazonaws.com/avatars/2017-08-09/225182834294_8020ddc74d7822b48ea1_72.png'}, 'deleted': False, 'updated': 1734709233, 'team_id': 'T086682UW57'}, 'blocks': [{'type': 'rich_text', 'block_id': '12W', 'elements': [{'type': 'rich_text_section', 'elements': [{'type': 'text', 'text': 'Hello team! Just wanted to say hi from the assistant bot.'}]}]}]}})]