ai-agent-book 精选快照（<2MB 代码与文档，来自 github.com/bojieli/ai-agent-book）

2026-08-20 13:12:50 +00:00
commit b119135836
10275 changed files with 3284984 additions and 0 deletions
@@ -0,0 +1,111 @@
+# pyright: reportMissingImports=false
+import asyncio
+import os
+import sys
+from dataclasses import dataclass
+
+sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
+
+from dotenv import load_dotenv
+
+load_dotenv()
+
+# Third-party imports
+import gradio as gr  # type: ignore
+from rich.console import Console
+from rich.panel import Panel
+from rich.text import Text
+
+# Local module imports
+from browser_use import Agent, ChatOpenAI
+
+
+@dataclass
+class ActionResult:
+	is_done: bool
+	extracted_content: str | None
+	error: str | None
+	include_in_memory: bool
+
+
+@dataclass
+class AgentHistoryList:
+	all_results: list[ActionResult]
+	all_model_outputs: list[dict]
+
+
+def parse_agent_history(history_str: str) -> None:
+	console = Console()
+
+	# Split the content into sections based on ActionResult entries
+	sections = history_str.split('ActionResult(')
+
+	for i, section in enumerate(sections[1:], 1):  # Skip first empty section
+		# Extract relevant information
+		content = ''
+		if 'extracted_content=' in section:
+			content = section.split('extracted_content=')[1].split(',')[0].strip("'")
+
+		if content:
+			header = Text(f'Step {i}', style='bold blue')
+			panel = Panel(content, title=header, border_style='blue')
+			console.print(panel)
+			console.print()
+
+	return None
+
+
+async def run_browser_task(
+	task: str,
+	api_key: str,
+	model: str = 'gpt-4.1',
+	headless: bool = True,
+) -> str:
+	if not api_key.strip():
+		return 'Please provide an API key'
+
+	os.environ['OPENAI_API_KEY'] = api_key
+
+	try:
+		agent = Agent(
+			task=task,
+			llm=ChatOpenAI(model='gpt-4.1-mini'),
+		)
+		result = await agent.run()
+		#  TODO: The result could be parsed better
+		return str(result)
+	except Exception as e:
+		return f'Error: {str(e)}'
+
+
+def create_ui():
+	with gr.Blocks(title='Browser Use GUI') as interface:
+		gr.Markdown('# Browser Use Task Automation')
+
+		with gr.Row():
+			with gr.Column():
+				api_key = gr.Textbox(label='OpenAI API Key', placeholder='your-openai-api-key', type='password')
+				task = gr.Textbox(
+					label='Task Description',
+					placeholder='E.g., Find flights from New York to London for next week',
+					lines=3,
+				)
+				model = gr.Dropdown(choices=['gpt-4.1-mini', 'gpt-5', 'o3', 'gpt-5-mini'], label='Model', value='gpt-4.1-mini')
+				headless = gr.Checkbox(label='Run Headless', value=False)
+				submit_btn = gr.Button('Run Task')
+
+			with gr.Column():
+				output = gr.Textbox(label='Output', lines=10, interactive=False)
+
+		submit_btn.click(
+			fn=lambda *args: asyncio.run(run_browser_task(*args)),
+			inputs=[task, api_key, model, headless],
+			outputs=output,
+		)
+
+	return interface
+
+
+if __name__ == '__main__':
+	demo = create_ui()
+	demo.launch()