Programming

Riding the Web with WebSurferAgent

Author: Robert Jambrecic Introduction In our Adding Browsing Capabilities to AG2 guide, we explored how to build agents with basic web surfing capabilities. Now, let’s take it to the next level with WebSurferAgent—a powerful agent that comes with built-in web browsing tools right out of the box! With WebSurferAgent, your agents can seamlessly browse the web, retrieve real-time information, and interact with web pages—all with minimal setup. ​WebSurferAgent with BrowserUseTool ​Installation To get started with the Browser Use integration in AG2, follow these steps: Install AG2 with the browser-use extra: pip install ag2[browser-use] Set up Playwright: playwright install playwright install-deps For running the code in Jupyter, use nest_asyncio to allow nested event loops. pip install nest_asyncio You’re all set! Now you can start using browsing features in AG2. ​Imports import os import nest_asyncio from autogen.agentchat import UserProxyAgent from autogen.agents import WebSurferAgent nest_asyncio.apply() ​Configure WebSurferAgent with Browser Use config_list = [{"model": "gpt-4o-mini", "api_key": os.environ["OPENAI_API_KEY"]}] llm_config = { "config_list": config_list, } WebSurferAgent is the one responsible for browsing the web and retrieving information. The web_tool="browser_use" tells the agent to use the BrowserUseTool to surf the web. After creating the WebSurferAgent there are two ways to start the chat session: ​Recommended: Using the run Method The new run method simplifies the process by eliminating the need for manual UserProxyAgent creation. ✅ Easier setup – No need to manually register tools websurfer = WebSurferAgent(name="WebSurfer", llm_config=llm_config, web_tool="browser_use") websurfer.run( message="Get info from https://docs.ag2.ai/docs/Home", tools=websurfer.tools, max_turns=2, user_input=False, ) ​Manual Setup: Using initiate_chat Method This method requires manually creating a UserProxyAgent and registering tools for execution. ⚠️ More setup required ⚠️ Must manually register tools websurfer = WebSurferAgent(name="WebSurfer", llm_config=llm_config, web_tool="browser_use") user_proxy = UserProxyAgent(name="user_proxy", human_input_mode="NEVER") # WebSurferAgent has a list of tools which are registered for LLM # We need to register the tools for execution with the UserProxyAgent for tool in websurfer.tools: tool.register_for_execution(user_proxy) user_proxy.initiate_chat( recipient=websurfer, message="Get info from https://docs.ag2.ai/docs/Home", max_turns=2, ) ​Output user_proxy (to WebSurfer): Get info from https://docs.ag2.ai/docs/Home -------------------------------------------------------------------------------- >>>>>>>> USING AUTO REPLY... WebSurfer (to user_proxy): ***** Suggested tool call (call_rl777jGrOGhc68goW5142urK): browser_use ***** Arguments: {"task":"Get info from https://docs.ag2.ai/docs/Home"} **************************************************************************** -------------------------------------------------------------------------------- >>>>>>>> EXECUTING FUNCTION browser_use... Call ID: call_rl777jGrOGhc68goW5142urK Input arguments: {'task': 'Get info from https://docs.ag2.ai/docs/Home'} INFO [agent]

Feb 5, 2025 - 17:45
 0
Riding the Web with WebSurferAgent

Author: Robert Jambrecic

Introduction

In our Adding Browsing Capabilities to AG2 guide, we explored how to build agents with basic web surfing capabilities. Now, let’s take it to the next level with WebSurferAgent—a powerful agent that comes with built-in web browsing tools right out of the box!

With WebSurferAgent, your agents can seamlessly browse the web, retrieve real-time information, and interact with web pages—all with minimal setup.

WebSurferAgent

​WebSurferAgent with BrowserUseTool

​Installation

To get started with the Browser Use integration in AG2, follow these steps:

  1. Install AG2 with the browser-use extra:

    pip install ag2[browser-use]

  2. Set up Playwright:

    playwright install
playwright install-deps

  3. For running the code in Jupyter, use nest_asyncio to allow nested event loops.

    pip install nest_asyncio

You’re all set! Now you can start using browsing features in AG2.

​Imports 

import os

import nest_asyncio

from autogen.agentchat import UserProxyAgent
from autogen.agents import WebSurferAgent

nest_asyncio.apply()

​Configure WebSurferAgent with Browser Use 

config_list = [{"model": "gpt-4o-mini", "api_key": os.environ["OPENAI_API_KEY"]}]

llm_config = {
    "config_list": config_list,
}

WebSurferAgent is the one responsible for browsing the web and retrieving information. The web_tool="browser_use" tells the agent to use the BrowserUseTool to surf the web.

After creating the WebSurferAgent there are two ways to start the chat session:

​Recommended: Using the run Method

The new run method simplifies the process by eliminating the need for manual UserProxyAgent creation.

  • ✅ Easier setup – No need to manually register tools 
websurfer = WebSurferAgent(name="WebSurfer", llm_config=llm_config, web_tool="browser_use")

websurfer.run(
    message="Get info from https://docs.ag2.ai/docs/Home",
    tools=websurfer.tools,
    max_turns=2,
    user_input=False,
)

​Manual Setup: Using initiate_chat Method

This method requires manually creating a UserProxyAgent and registering tools for execution.

  • ⚠️ More setup required

  • ⚠️ Must manually register tools

websurfer = WebSurferAgent(name="WebSurfer", llm_config=llm_config, web_tool="browser_use")
user_proxy = UserProxyAgent(name="user_proxy", human_input_mode="NEVER")
# WebSurferAgent has a list of tools which are registered for LLM
# We need to register the tools for execution with the UserProxyAgent
for tool in websurfer.tools:
    tool.register_for_execution(user_proxy)

user_proxy.initiate_chat(
    recipient=websurfer,
    message="Get info from https://docs.ag2.ai/docs/Home",
    max_turns=2,
)

​Output 

user_proxy (to WebSurfer):

Get info from https://docs.ag2.ai/docs/Home

--------------------------------------------------------------------------------

>>>>>>>> USING AUTO REPLY...
WebSurfer (to user_proxy):

***** Suggested tool call (call_rl777jGrOGhc68goW5142urK): browser_use *****
Arguments:
{"task":"Get info from https://docs.ag2.ai/docs/Home"}
****************************************************************************

--------------------------------------------------------------------------------

>>>>>>>> EXECUTING FUNCTION browser_use...
Call ID: call_rl777jGrOGhc68goW5142urK
Input arguments: {'task': 'Get info from https://docs.ag2.ai/docs/Home'}
INFO     [agent]
Read More

Tags:

Previous Article

Why_--legacy-peer-deps is Better than --force in npm

Next Article

Matrices

Related Posts

How Software Engineering Enables National-Scale Product Distribution

How Software Engineering Enables National-Scale Product...

Feb 3, 2025  0

Short Story Video Generator: Streamlining Social Media Content Creation with Agent.ai

Short Story Video Generator: Streamlining Social Media ...

Jan 26, 2025  0

A new chapter, and thoughts on a pivotal year for C++

A new chapter, and thoughts on a pivotal year for C++

Jan 26, 2025  0