diff --git a/src/crewai_tools/__init__.py b/src/crewai_tools/__init__.py index a9c9a4168..aaca3396e 100644 --- a/src/crewai_tools/__init__.py +++ b/src/crewai_tools/__init__.py @@ -16,6 +16,7 @@ from .tools import ( JSONSearchTool, LlamaIndexTool, MDXSearchTool, + MultiOnTool, PDFSearchTool, PGSearchTool, RagTool, diff --git a/src/crewai_tools/tools/__init__.py b/src/crewai_tools/tools/__init__.py index 17d289832..c9ddb3444 100644 --- a/src/crewai_tools/tools/__init__.py +++ b/src/crewai_tools/tools/__init__.py @@ -15,6 +15,7 @@ from .github_search_tool.github_search_tool import GithubSearchTool from .json_search_tool.json_search_tool import JSONSearchTool from .llamaindex_tool.llamaindex_tool import LlamaIndexTool from .mdx_seach_tool.mdx_search_tool import MDXSearchTool +from .multion_tool.multion_tool import MultiOnTool from .pdf_search_tool.pdf_search_tool import PDFSearchTool from .pg_seach_tool.pg_search_tool import PGSearchTool from .rag.rag_tool import RagTool diff --git a/src/crewai_tools/tools/multion_tool/README.md b/src/crewai_tools/tools/multion_tool/README.md new file mode 100644 index 000000000..ea530037f --- /dev/null +++ b/src/crewai_tools/tools/multion_tool/README.md @@ -0,0 +1,54 @@ +# MultiOnTool Documentation + +## Description +The MultiOnTool, integrated within the crewai_tools package, empowers CrewAI agents with the capability to navigate and interact with the web through natural language instructions. Leveraging the Multion API, this tool facilitates seamless web browsing, making it an essential asset for projects requiring dynamic web data interaction. + +## Installation +Ensure the `crewai[tools]` package is installed in your environment to use the MultiOnTool. If it's not already installed, you can add it using the command below: +```shell +pip install 'crewai[tools]' +``` + +## Example +The following example demonstrates how to initialize the tool and execute a search with a given query: + +```python +from crewai import Agent, Task, Crew +from crewai_tools import MultiOnTool + +# Initialize the tool from a MultiOn Tool +multion_tool = MultiOnTool(api_key= "YOUR_MULTION_API_KEY", local=False) + +Browser = Agent( + role="Browser Agent", + goal="control web browsers using natural language ", + backstory="An expert browsing agent.", + tools=[multion_remote_tool], + verbose=True, +) + +# example task to search and summarize news +browse = Task( + description="Summarize the top 3 trending AI News headlines", + expected_output="A summary of the top 3 trending AI News headlines", + agent=Browser, +) + +crew = Crew(agents=[Browser], tasks=[browse]) + +crew.kickoff() +``` + +## Arguments + +- `api_key`: Specifies Browserbase API key. Defaults is the `BROWSERBASE_API_KEY` environment variable. +- `local`: Use the local flag set as "true" to run the agent locally on your browser. Make sure the multion browser extension is installed and API Enabled is checked. +- `max_steps`: Optional. Set the max_steps the multion agent can take for a command + +## Steps to Get Started +To effectively use the `MultiOnTool`, follow these steps: + +1. **Install CrewAI**: Confirm that the `crewai[tools]` package is installed in your Python environment. +2. **Install and use MultiOn**: Follow MultiOn documentation for installing the MultiOn Browser Extension (https://docs.multion.ai/learn/browser-extension). +3. **Enable API Usage**: Click on the MultiOn extension in the extensions folder of your browser (not the hovering MultiOn icon on the web page) to open the extension configurations. Click the API Enabled toggle to enable the API + diff --git a/src/crewai_tools/tools/multion_tool/example.py b/src/crewai_tools/tools/multion_tool/example.py new file mode 100644 index 000000000..ec69e5cdf --- /dev/null +++ b/src/crewai_tools/tools/multion_tool/example.py @@ -0,0 +1,29 @@ +import os + +from crewai import Agent, Crew, Task +from multion_tool import MultiOnTool + +os.environ["OPENAI_API_KEY"] = "Your Key" + +multion_browse_tool = MultiOnTool(api_key="Your Key") + +# Create a new agent +Browser = Agent( + role="Browser Agent", + goal="control web browsers using natural language ", + backstory="An expert browsing agent.", + tools=[multion_browse_tool], + verbose=True, +) + +# Define tasks +browse = Task( + description="Summarize the top 3 trending AI News headlines", + expected_output="A summary of the top 3 trending AI News headlines", + agent=Browser, +) + + +crew = Crew(agents=[Browser], tasks=[browse]) + +crew.kickoff() diff --git a/src/crewai_tools/tools/multion_tool/multion_tool.py b/src/crewai_tools/tools/multion_tool/multion_tool.py new file mode 100644 index 000000000..2dc944f23 --- /dev/null +++ b/src/crewai_tools/tools/multion_tool/multion_tool.py @@ -0,0 +1,65 @@ +"""Multion tool spec.""" + +from typing import Any, Optional + +from crewai_tools.tools.base_tool import BaseTool + + +class MultiOnTool(BaseTool): + """Tool to wrap MultiOn Browse Capabilities.""" + + name: str = "Multion Browse Tool" + description: str = """Multion gives the ability for LLMs to control web browsers using natural language instructions. + If the status is 'CONTINUE', reissue the same instruction to continue execution + """ + multion: Optional[Any] = None + session_id: Optional[str] = None + local: bool = False + max_steps: int = 3 + + def __init__( + self, + api_key: Optional[str] = None, + local: bool = False, + max_steps: int = 3, + **kwargs, + ): + super().__init__(**kwargs) + try: + from multion.client import MultiOn # type: ignore + except ImportError: + raise ImportError( + "`multion` package not found, please run `pip install multion`" + ) + self.session_id = None + self.local = local + self.multion = MultiOn(api_key=api_key) + self.max_steps = max_steps + + def _run( + self, + cmd: str, + *args: Any, + **kwargs: Any, + ) -> str: + """ + Run the Multion client with the given command. + + Args: + cmd (str): The detailed and specific natural language instructrion for web browsing + + *args (Any): Additional arguments to pass to the Multion client + **kwargs (Any): Additional keyword arguments to pass to the Multion client + """ + + browse = self.multion.browse( + cmd=cmd, + session_id=self.session_id, + local=self.local, + max_steps=self.max_steps, + *args, + **kwargs, + ) + self.session_id = browse.session_id + + return browse.message + "\n\n STATUS: " + browse.status