1e0def78df
# CrewAI Integration
crewai-arcade enables you to add Arcade tools and Arcade Auth into your
CrewAI applications. Just create an `ArcadeToolManager` and add your
tools to your CrewAI Agent/Tasks.
## Initializing the ArcadeToolManager
There are two main ways to initialize your `ArcadeToolManager`
1. Default handling of tool authorization and execution:
```py
"""
When you provide a user id to the ArcadeToolManger,
it will handle the tool authorization and tool execution for you
"""
manager = ArcadeToolManager(default_user_id="me@example.com,
api_key="...")
```
2. Custom handling of tool authorization and execution
```py
"""
Provide a callback function to the `ArcadeToolManager` that handles
tool authorization and tool execution. The callback function will be
called whenever your CrewAI
application wants to call a tool.
"""
def custom_tool_executor(
manager: ArcadeToolManager, tool_name: str, **tool_input: dict[str, Any]
) -> Any:
"""Custom tool executor for the ArcadeToolManager
ArcadeToolManager's default executor handles authorization and tool
execution.
This function overrides the default executor to handle authorization and
tool execution
in a custom way.
"""
# Your custom tool auth logic goes here
# Your custom tool execution logic goes here
...
manager = ArcadeToolManager(executor=custom_tool_executor,
api_key="...")
```
## Tool Registration
1. Initialize the tools in the manager
```py
"""
Clears any existing tools in the manager and replaces them with tools
and toolkits that are provided.
"""
manager.init_tools(tools=["Google.ListEmails"], toolkits=["Slack"])
```
2. Add tools to the manager
```py
"""
Adds tools and toolkits to the manager's internal tool list.
"""
manager.add_tools(tools=["Google.ListEmails"], toolkits=["Slack"])
```
3. Retrieve tools and toolkits from the manager
```py
"""
Retrieves the provided tools and toolkits as CrewAI StructuredTools.
"""
manager.get_tools(tools=["Google.ListEmails"], toolkits=["Slack"])
```
## Auth Helpers
The `ArcadeToolManager` provides multiple helper methods for when you
need to create
a custom auth flow.
1. `authorize_tool` handles the whole authorization flow for you. This
is used internally when a custom auth flow is not needed.
2. `requires_auth(tool_name)` checks if the provided tool has
authorization requirements.
3. `authorize(tool_name, user_id)` authorizes the use of the provided
tool for the provided user ID
4. `is_authorized(tool_name, user_id)` checks if a tool is authorized
for use by the provided user ID
5. `wait_for_auth(auth_response)` waits for an authorization process to
complete before returning
## Tool Execution Helpers
1. `execute_tool` handles the whole tool execution flow for you. This is
used internally when a custom tool execution flow is not needed.
---------
Co-authored-by: lgesuellip <lgesuellipinto@uade.edu.ar>
Co-authored-by: lpetralli <123559656+lpetralli@users.noreply.github.com>
Co-authored-by: lgesuellip <102637283+lgesuellip@users.noreply.github.com>
Co-authored-by: “lgesuellip” <“lgesuellipinto@uade.edu.ar”>
46 lines
1.4 KiB
Python
46 lines
1.4 KiB
Python
"""
|
|
This is a simple example of how to use Arcade with CrewAI.
|
|
The example authenticates into the user's Gmail account, retrieves their 5 most recent emails, and summarizes them.
|
|
|
|
The example assumes the following:
|
|
1. You have an Arcade API key and have set the ARCADE_API_KEY environment variable.
|
|
2. You have an OpenAI API key and have set the OPENAI_API_KEY environment variable.
|
|
3. You have installed the necessary dependencies in the requirements.txt file: `pip install -r requirements.txt`
|
|
|
|
"""
|
|
|
|
from crewai import Agent, Crew, Task
|
|
from crewai.llm import LLM
|
|
from crewai_arcade import ArcadeToolManager
|
|
|
|
manager = ArcadeToolManager(default_user_id="user@example.com")
|
|
tools = manager.get_tools(tools=["Google.ListEmails"])
|
|
|
|
crew_agent = Agent(
|
|
role="Main Agent",
|
|
backstory="You are a helpful assistant",
|
|
goal="Help the user with their requests",
|
|
tools=tools,
|
|
allow_delegation=False,
|
|
verbose=True,
|
|
llm=LLM(model="gpt-4o"),
|
|
)
|
|
|
|
task = Task(
|
|
description="Get the 5 most recent emails from the user's inbox and summarize them and recommend a response for each.",
|
|
expected_output="A bulleted list with a one sentence summary of each email and a recommended response to the email.",
|
|
agent=crew_agent,
|
|
tools=crew_agent.tools,
|
|
)
|
|
|
|
crew = Crew(
|
|
agents=[crew_agent],
|
|
tasks=[task],
|
|
verbose=True,
|
|
memory=True,
|
|
)
|
|
|
|
result = crew.kickoff()
|
|
|
|
print("\n\n\n ------------ Result ------------ \n\n\n")
|
|
print(result)
|