Thanks to visit codestin.com
Credit goes to www.scribd.com

Scribd
Upload
13 views2 pages

Browser Use Tool

The document defines a BrowserUseTool class for automating browser actions, including content extraction from web pages. It utilizes asynchronous programming and integrates with a language model (LLM) to process and extract relevant information based on specified goals. The class includes methods for executing actions, cleaning up resources, and managing browser context and services.

Uploaded by

gmpintus
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
13 views2 pages

Browser Use Tool

The document defines a BrowserUseTool class for automating browser actions, including content extraction from web pages. It utilizes asynchronous programming and integrates with a language model (LLM) to process and extract relevant information based on specified goals. The class includes methods for executing actions, cleaning up resources, and managing browser context and services.

Uploaded by

gmpintus
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
You are on page 1/ 2

import asyncio

import base64
import json
from typing import Generic, Optional, TypeVar

from browser_use import Browser as BrowserUseBrowser


from browser_use import BrowserConfig
from browser_use.browser.context import BrowserContext, BrowserContextConfig
from browser_use.dom.service import DomService
from pydantic import Field, field_validator
from pydantic_core.core_schema import ValidationInfo

from app.config import config


from app.llm import LLM
from app.tool.base import BaseTool, ToolResult
from app.tool.web_search import WebSearch

Context = TypeVar("Context")

class BrowserUseTool(BaseTool, Generic[Context]):


name: str = "browser_use"
description: str = "A powerful browser automation tool"
parameters: dict = {...} # Keeping full parameters intact

lock: asyncio.Lock = Field(default_factory=asyncio.Lock)


browser: Optional[BrowserUseBrowser] = Field(default=None, exclude=True)
context: Optional[BrowserContext] = Field(default=None, exclude=True)
dom_service: Optional[DomService] = Field(default=None, exclude=True)
web_search_tool: WebSearch = Field(default_factory=WebSearch, exclude=True)
llm: Optional[LLM] = Field(default_factory=LLM)

async def extract_content(self, goal: str, page_content: str) -> ToolResult:


"""Extract specific information from a webpage based on a goal."""
messages = [{"role": "system", "content": f"Extract relevant information
for: {goal}"}]

response = await self.llm.ask(messages) # Updated from ask_tool

extracted_content = json.loads(response.content) if response else {}


return ToolResult(output=f"Extracted from page:\n{extracted_content}\n")

async def execute(self, action: str, **kwargs) -> ToolResult:


"""Execute browser action."""
async with self.lock:
context = await self._ensure_browser_initialized()

if action == "extract_content":
return await self.extract_content(kwargs.get("goal", ""),
kwargs.get("page_content", ""))

# Other browser interactions remain unchanged...

async def cleanup(self):


"""Clean up browser resources."""
async with self.lock:
if self.context is not None:
await self.context.close()
self.context = None
self.dom_service = None
if self.browser is not None:
await self.browser.close()
self.browser = None

You might also like