本示例演示了如何使用不同的检索方法搜索用户内存

  • last_n:检索最新的 n 条内存
  • first_n:检索最早的 n 条内存
  • semantic:使用语义搜索检索内存

​
代码

cookbook/agent_concepts/memory/05_memory_search.py
from agno.memory.v2 import Memory, UserMemory
from agno.memory.v2.db.sqlite import SqliteMemoryDb
from agno.models.google.gemini import Gemini
from rich.pretty import pprint

memory_db = SqliteMemoryDb(table_name="memory", db_file="tmp/memory.db")
# 为本示例重置
memory_db.clear()

memory = Memory(model=Gemini(id="gemini-2.0-flash-exp"), db=memory_db)

john_doe_id = "john_doe@example.com"
memory.add_user_memory(
    memory=UserMemory(memory="该用户周末喜欢在山区徒步旅行"),
    user_id=john_doe_id,
)
memory.add_user_memory(
    memory=UserMemory(
        memory="该用户喜欢睡前阅读科幻小说"
    ),
    user_id=john_doe_id,
)
print("John Doe's memories:")
pprint(memory.memories)

memories = memory.search_user_memories(
    user_id=john_doe_id, limit=1, retrieval_method="last_n"
)
print("\nJohn Doe's last_n memories:")
pprint(memories)

memories = memory.search_user_memories(
    user_id=john_doe_id, limit=1, retrieval_method="first_n"
)
print("\nJohn Doe's first_n memories:")
pprint(memories)

memories = memory.search_user_memories(
    user_id=john_doe_id,
    query="用户周末喜欢做什么？",
    retrieval_method="agentic",
)
print("\nJohn Doe's memories similar to the query (agentic):")
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

安装库

pip install -U agno
3

运行示例

python cookbook/agent_concepts/memory/05_memory_search.py