管理代理的记忆
使用 Hugging Face smolagents 的 AI Agents
Adel Nehme
VP of AI Curriculum, DataCamp
默认无状态
每次 .run() 调用都会重新开始。
- 示例：
career_advisor.run("What career skills should I highlight?")
You should highlight Python, SQL, data visualization,
machine learning fundamentals, and communication skills tailored to business outcomes.
career_advisor.run("Can you format those skills as bullet points?")
Sorry, I'm not sure which skills you're referring to. Could you clarify?
在交互间保留记忆
career_advisor.run("What career skills should I highlight?")
You should highlight Python, SQL, data visualization,
machine learning fundamentals, and communication skills tailored to business outcomes.
- 传入
reset=False：
career_advisor.run("Can you format those skills as bullet points?", reset=False)
Sure! Here are the skills as bullet points:
- Python
- SQL
- Data visualization
...
记忆也有助于调试
User: What's the expected salary?
Agent: It's $80,000
User: Wait, that seems wrong...
Agent: Sorry, I'm not sure what you mean
检查该次运行发生了什么：
- 回看代理生成的全部代码
- 追踪其推理、动作与工具使用
- 调试错误答案或有问题的逻辑
代理运行了哪些代码？
.return_full_code() 方法可查看所有已执行代码。
executed_code = career_advisor.memory.return_full_code()
print(executed_code)
# ...other steps omitted for brevity
salary = 80000 # <- hardcoded?
# script continues...
代理在想什么？
conversation_steps = career_advisor.memory.get_succinct_steps()
print(conversation_steps[5])
{
"step_number": 5,
"tool_calls": [
{"function": {"name": "python_interpreter"}},
{"function": {"name": "web_search"}}
],
"code_action": "import requests\nskills = requests.get('api.jobsearch.com').json()",
"observations": "resume_agent found 15 relevant skills for transition",
"token_usage": {"total_tokens": 334},
...
}
保存会话以供分析
import json
def save_agent_memory(agent):
with open("agent_memory.json", "w") as f:
json.dump(agent.memory.get_succinct_steps(), f, indent=2, default=str)
# Save memory to a file
save_agent_memory(career_advisor)
日志可用于：
- 事后分析
- 回归测试
- 持续改进代理行为
修复代理失败：调整什么
- 记忆问题：使用
reset=False，或按需重置 - 推理问题：尝试更强的模型
- 行为不一致：优化 system prompt
- 工具混淆：完善工具 docstring
让我们来练习！
使用 Hugging Face smolagents 的 AI Agents
