> For the complete documentation index, see [llms.txt](https://docs.integry.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.integry.ai/functions/agent-frameworks/crewai.md).

# CrewAI

## 1. Install Required Libraries

First, you need to install the necessary packages:

{% hint style="info" %}
Integry requires Python version 3.12 or higher
{% endhint %}

* **Integry** is used to integrate structured tools and functions.
* **CrewAI** integrate tools and automate workflows using large language models.

```python
pip install integry crewai
```

## 2. Initialize Integry & Agent

Import the necessary Libraries

```python
import os
from integry import Integry
from crewai import Agent, Task, Crew, LLM
from crewai.tools.structured_tool import CrewStructuredTool
```

`User-ID` is a unique string identifier for a user in your app or agent. Function Calls and Integrations are associated to a user ID. It will be the email address you used during the signup process on Integry.

For example:

```python
user_id = "joe@example.com"
```

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](https://app.integry.io/platform/workspace/security/).

<figure><img src="/files/pcp6NUKDK0SQB174gbFM" alt=""><figcaption><p>Workspace Setting</p></figcaption></figure>

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

Now initializing the instance of the **ChatOpenAI** class to interact with OpenAI's GPT-4o model. You can get the API Key from the [OpenAI Platform](https://platform.openai.com/api-keys)

```python
llm = LLM(
    model="gpt-4o",
    temperature=0,
    base_url="https://api.openai.com/v1",
    api_key=os.environ.get("OPENAI_API_KEY"),
)
```

## 3. Initialize Agent with an 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 Integry by default, so there’s no need to add it manually.

Now that we've set everything up, we will proceed to send a message in Slack using the **slack-post-message** function from [Integry](https://app.integry.io/platform/functions). You can copy the function ID from the dropdown.

For example

In this case the function ID is <mark style="color:blue;">slack-post-message</mark>

<figure><img src="/files/fZytT105zjfl0IjM7KQI" alt=""><figcaption></figcaption></figure>

After getting the function ID, we then registers it with the Crew AI agents to enable the assistant to call the function.

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

tools = [
    slack_post_message.get_langchain_tool(CrewStructuredTool.from_function, user_id)
]

crewai_agent = Agent(
    role="Integration Assistant",
    goal="Help users achieve their goal by performing their required task in various apps",
    backstory="You are a virtual assistant with access to various apps and services. You are known for your ability to connect to any app and perform any task.",
    verbose=True,
    tools=tools,
    llm=llm,
)
```

## 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.

```python
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 from crewai to the team** message in the Slack random channel.

```python
task = Task(
    description="Say hello from crewai to my team on slack in #random channel.",
    agent=crewai_agent,
    expected_output="Result of the task",
)

crew = Crew(agents=[crewai_agent], tasks=[task])

result = crew.kickoff()
```


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.integry.ai/functions/agent-frameworks/crewai.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.