本示例展示了如何使用持久化记忆与 Agent 进行交互。

每次运行后都会创建/更新用户的记忆。

要启用此功能，请在 Agent 配置中将 enable_user_memories 设置为 True。

​
代码

cookbook/agent_concepts/memory/06_agent_with_memory.py
from agno.agent.agent import Agent
from agno.memory.v2.db.sqlite import SqliteMemoryDb
from agno.memory.v2.memory import Memory
from agno.models.openai import OpenAIChat
from agno.storage.sqlite import SqliteStorage
from rich.pretty import pprint
from utils import print_chat_history

memory_db = SqliteMemoryDb(table_name="memory", db_file="tmp/memory.db")

# 无需设置模型，Agent 会自动为其设置
memory = Memory(db=memory_db)

# 重置此示例的记忆
memory.clear()

session_id = "session_1"
john_doe_id = "john_doe@example.com"

agent = Agent(
    model=OpenAIChat(id="gpt-4o-mini"),
    memory=memory,
    storage=SqliteStorage(
        table_name="agent_sessions", db_file="tmp/persistent_memory.db"
    ),
    enable_user_memories=True,
)

agent.print_response(
    "My name is John Doe and I like to hike in the mountains on weekends.",
    stream=True,
    user_id=john_doe_id,
    session_id=session_id,
)

agent.print_response(
    "What are my hobbies?", stream=True, user_id=john_doe_id, session_id=session_id
)

# -*- 打印聊天记录
session_run = memory.runs[session_id][-1]
print_chat_history(session_run)

memories = memory.get_user_memories(user_id=john_doe_id)
print("John Doe's memories:")
pprint(memories)

agent.print_response(
    "Ok i dont like hiking anymore, i like to play soccer instead.",
    stream=True,
    user_id=john_doe_id,
    session_id=session_id,
)

# -*- 打印聊天记录
session_run = memory.runs[session_id][-1]
print_chat_history(session_run)

# 你也可以从 Agent 获取用户记忆
memories = agent.get_user_memories(user_id=john_doe_id)
print("John Doe's memories:")
pprint(memories)

​
用法

1

创建虚拟环境

打开 Terminal 并创建一个 python 虚拟环境。

python3 -m venv .venv
source .venv/bin/activate
2

设置你的 API 密钥

export GOOGLE_API_KEY=xxx
3

安装库

pip install -U agno google-generativeai
4

运行示例

python cookbook/agent_concepts/memory/06_agent_with_memory.py