启动速度

pip install fastapi uvicorn langchain langchain-openai langchain-anthropic psutil

mkdir -p work/code/agents/langchain/basic-agent
cd work/code/agents/langchain/basic-agent

vi main.py

import os
import time
import psutil
from langchain.agents import create_agent
from langchain_openai import ChatOpenAI

# 记录启动时间
start_time = time.perf_counter()

def get_weather(city: str) -> str:
    """Get weather for a given city."""
    return f"It's always sunny in {city}!"

# 从通用环境变量读取配置
llm = ChatOpenAI(
    model="openai/gpt-5-mini",
    api_key=os.getenv("OPENAI_API_KEY"),
    base_url="https://openrouter.ai/api/v1",
)

# 创建 Agent —— 注意这里传的是 llm 对象
agent = create_agent(
    model=llm,
    tools=[get_weather],
    system_prompt="You are a helpful assistant",
)

# 计算启动耗时和内存占用
elapsed = (time.perf_counter() - start_time) * 1000  # 毫秒
process = psutil.Process()
mem = process.memory_info().rss / (1024 * 1024)  # MB

print(f"Agent 启动完成: {elapsed:.0f} ms, 内存占用 {mem:.2f} MB")

# 运行 Agent
result = agent.invoke(
    {"messages": [{"role": "user", "content": "what is the weather in sf"}]}
)
print(result)

export OPENAI_API_KEY="sk-or-v1-8b367db75f582bxxxxx"

cd ~/work/code/agents/langchain/basic-agent

python main.py

Agent 启动完成: 133 ms, 内存占用 82.59 MB

{'messages': [HumanMessage(content='what is the weather in sf', additional_kwargs={}, response_metadata={}, id='8104aa20-7052-48a2-bfdc-8ca56fe8ab0e'), AIMessage(content='', additional_kwargs={'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 85, 'prompt_tokens': 61, 'total_tokens': 146, 'completion_tokens_details': {'accepted_prediction_tokens': None, 'audio_tokens': None, 'reasoning_tokens': 64, 'rejected_prediction_tokens': None}, 'prompt_tokens_details': None}, 'model_provider': 'openai', 'model_name': 'openai/gpt-5-mini', 'system_fingerprint': None, 'id': 'gen-1763626368-7nC7HDrc2SUlvwBTJ1qL', 'finish_reason': 'tool_calls', 'logprobs': None}, id='lc_run--7c2d184f-8b13-410d-9270-c145cf361d9f-0', tool_calls=[{'name': 'get_weather', 'args': {'city': 'San Francisco'}, 'id': 'call_gXwuk067eb5j2JUuC20HKcf3', 'type': 'tool_call'}], usage_metadata={'input_tokens': 61, 'output_tokens': 85, 'total_tokens': 146, 'input_token_details': {}, 'output_token_details': {'reasoning': 64}}), ToolMessage(content="It's always sunny in San Francisco!", name='get_weather', id='9e490eb6-2be0-442b-8d9e-5220894b83c9', tool_call_id='call_gXwuk067eb5j2JUuC20HKcf3'), AIMessage(content='According to the weather service: "It\'s always sunny in San Francisco!" \n\nWould you like current temperature, an hourly forecast, or a 7-day outlook?', additional_kwargs={'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 166, 'prompt_tokens': 96, 'total_tokens': 262, 'completion_tokens_details': {'accepted_prediction_tokens': None, 'audio_tokens': None, 'reasoning_tokens': 128, 'rejected_prediction_tokens': None}, 'prompt_tokens_details': None}, 'model_provider': 'openai', 'model_name': 'openai/gpt-5-mini', 'system_fingerprint': None, 'id': 'gen-1763626375-XJVfCoGQ0ddWXdiAhwjm', 'finish_reason': 'stop', 'logprobs': None}, id='lc_run--f2e476bd-e193-4df8-b066-fd6f345a6bb1-0', usage_metadata={'input_tokens': 96, 'output_tokens': 166, 'total_tokens': 262, 'input_token_details': {}, 'output_token_details': {'reasoning': 128}})]}