使用 LangGraph 的代理程式記憶體
在本文中，您將瞭解如何以兩種方式將「代理程式記憶體」連線到 LangGraph：
- 可在需要時呼叫記憶體搜尋工具的預建 ReAct 代理程式；
- 使用
StateGraph(MessagesState)建立的自訂流程。
秘訣：如需設定套裝程式，請參閱開始使用代理程式記憶體。如果此範例需要本機 Oracle AI Database，請參閱在本機執行 Oracle AI Database 。
代理程式記憶體設定
從設定「代理程式記憶體」從屬端、LangGraph 交談模型以及可重複使用的 search_memory 工具開始。「代理程式記憶體」從屬端也會使用自己的 LLM，定期從最近的繫線訊息擷取持久的記憶體，而 LangGraph 模型則負責處理代理程式回應和工具使用。
from typing import Annotated
from langchain.agents import create_agent
from langchain_core.messages import HumanMessage
from langchain_core.tools import tool
from langchain_openai import ChatOpenAI
from langgraph.graph import END, START, MessagesState, StateGraph
from oracleagentmemory.core.embedders.embedder import Embedder
from oracleagentmemory.core.llms.llm import Llm
from oracleagentmemory.core.oracleagentmemory import OracleAgentMemory
embedder = Embedder(
model="YOUR_EMBEDDING_MODEL",
api_base="YOUR_EMBEDDING_API_BASE",
api_key="YOUR_EMBEDDING_API_KEY",
)
llm = Llm(
model="gpt-4.1-mini",
api_key="YOUR_OPENAI_API_KEY",
)
db_pool = ... #an oracledb connection or connection pool
langgraph_llm = ChatOpenAI(
model="gpt-4.1-mini",
api_key="YOUR_OPENAI_API_KEY",
)
#Keep these identifiers stable for the same assistant and end user so memory
#is scoped consistently across threads and sessions.
agent_id = "support_agent"
user_id = "user_123"
agent_memory = OracleAgentMemory(
connection=db_pool,
embedder=embedder,
llm=llm,
)
@tool
def search_memory(
query: Annotated[str, "Question to search in Oracle Agent Memory"],
) -> Annotated[str, "Top matching durable memory content"]:
"""Search Oracle Agent Memory for durable user facts relevant to the current request."""
results = agent_memory.search(
query=query,
user_id=user_id,
agent_id=agent_id,
max_results=3,
record_types=["memory"],
)
if not results:
return "No relevant memory found."
return "\n".join(result.content for result in results)
def _latest_user_message(state: MessagesState) -> str:
for message in reversed(state["messages"]):
if getattr(message, "type", None) == "human":
return str(message.content)
if getattr(message, "role", None) == "user":
return str(message.content)
return ""
def _build_memory_context(query: str) -> str:
results = agent_memory.search(
query=query,
user_id=user_id,
agent_id=agent_id,
max_results=3,
record_types=["memory"],
)
memory_context = "\n".join(f"- {result.content}" for result in results)
return memory_context or "- No relevant memory found."預建的 ReAct 專員
LangChain 在 LangGraph 執行階段上提供預先建立的 ReAct 樣式代理程式。您可以將 search_memory 顯示為其中一種工具，讓代理程式決定何時應該查詢持久性記憶體。
設定預建代理程式
react_agent = create_agent(
model=langgraph_llm,
tools=[search_memory],
system_prompt=(
"You are a support agent. When the user asks about durable facts from "
"prior sessions, call the search_memory tool before answering."
),
)
react_memory_thread = agent_memory.create_thread(
thread_id="langgraph_react_memory_demo",
user_id=user_id,
agent_id=agent_id,
)在預先建置的 ReAct 階段作業之後保存使用者相關資訊環境
第一次執行完成後，將交換的訊息附加至「代理程式記憶體」，並儲存任何稍後應重複使用的持久性事實。
react_session_1 = react_agent.invoke(
{
"messages": [
HumanMessage(
content="I am John, a Python developer and I need help debugging a payment service."
)
]
}
)
react_assistant_reply = react_session_1["messages"][-1].content
print(react_assistant_reply)
#I can help with that. What error are you seeing?
#add_messages will add messages to the DB and extract memories automatically
react_memory_thread.add_messages(
[
{
"role": "user",
"content": "I am John, a Python developer and I need help debugging a payment service.",
},
{
"role": "assistant",
"content": react_assistant_reply,
},
]
)
#add_memory adds memory to the DB
react_memory_thread.add_memory("The user is John, a Python developer.")在新的預建反應階段作業重複使用記憶體
當稍後執行開始時，請重新開啟相同的「代理程式記憶體」繫線，然後讓預建的代理程式在回答之前呼叫 search_memory。
react_memory_thread = agent_memory.get_thread("langgraph_react_memory_demo")
react_session_2 = react_agent.invoke(
{
"messages": [
HumanMessage(content="Who am I?")
]
}
)
react_remembered_reply = react_session_2["messages"][-1].content
print(react_remembered_reply)輸出：
The user is John, a Python developer.自訂流程
如果您需要對協調流程進行更嚴格的控制，請建立自訂的 LangGraph 流程，然後將「代理程式記憶體」結果直接插入您的模型節點中。
設定自訂流程
def call_model(state: MessagesState):
from langchain_core.messages import SystemMessage
query = _latest_user_message(state)
memory_context = _build_memory_context(query)
response = langgraph_llm.invoke(
[
SystemMessage(
content=(
"You are a support agent. Use the durable memory below when it is "
"relevant to the current user request.\n\n"
f"Durable memory:\n{memory_context}"
)
),
*state["messages"],
]
)
return {"messages": [response]}
builder = StateGraph(MessagesState)
builder.add_node("call_model", call_model)
builder.add_edge(START, "call_model")
builder.add_edge("call_model", END)
flow_graph = builder.compile()
flow_memory_thread = agent_memory.create_thread(
thread_id="langgraph_flow_memory_demo",
user_id=user_id,
agent_id=agent_id,
)在流程階段作業之後保存使用者相關資訊環境
第一個流程執行完成後，將交換的訊息附加至「代理程式記憶體」，並儲存任何稍後應重複使用的持久性事實。
flow_session_1 = flow_graph.invoke(
{
"messages": [
HumanMessage(
content="I am John, a Python developer and I need help debugging a payment service."
)
]
}
)
flow_assistant_reply = flow_session_1["messages"][-1].content
print(flow_assistant_reply)
#I can help with that. What error are you seeing?
flow_memory_thread.add_messages(
[
{
"role": "user",
"content": "I am John, a Python developer and I need help debugging a payment service.",
},
{
"role": "assistant",
"content": flow_assistant_reply,
},
]
)
flow_memory_thread.add_memory("The user is John, a Python developer.")在新流程階段作業重複使用記憶體
當後續的流程執行開始時，請重新開啟相同的「代理程式記憶體」繫線，並讓圖表搜尋持續的記憶體，以回答先前的使用者相關資訊環境。
flow_memory_thread = agent_memory.get_thread("langgraph_flow_memory_demo")
flow_session_2 = flow_graph.invoke(
{
"messages": [
HumanMessage(content="Who am I?")
]
}
)
flow_remembered_reply = flow_session_2["messages"][-1].content
print(flow_remembered_reply)輸出：
The user is John, a Python developer.停用自動擷取
如果您只想保留訊息並手動新增持久記憶體，請使用 extract_memories=False 建立「代理程式記憶體」從屬端，然後自行寫入記憶體資料列。
manual_agent_memory = OracleAgentMemory(
connection=db_pool,
embedder=embedder,
extract_memories=False,
)
manual_memory_thread = manual_agent_memory.create_thread(
thread_id="langgraph_manual_memory_demo",
user_id=user_id,
agent_id=agent_id,
)
manual_memory_thread.add_messages(
[
{
"role": "user",
"content": "Please remember that I prefer concise code reviews.",
},
{
"role": "assistant",
"content": "Understood. I will keep responses concise.",
},
]
)
manual_memory_thread.add_memory("The user prefers concise code reviews.")結論
在本文中，我們學會如何使用預先建立的 ReAct 代理程式或自訂 StateGraph(MessagesState) 流程將代理程式記憶體連線至 LangGraph、在每個階段作業後保留執行緒訊息，以及在後續執行中重複使用持久記憶體。
提示：學習如何整合「代理程式記憶體」與 LangGraph 之後，您可能也對整合代理程式記憶體與 WayFlow 有興趣。
完整代碼
#Copyright © 2026 Oracle and/or its affiliates.
#isort:skip_file
#fmt: off
#Agent Memory Code Example - Integration with LangGraph
#-------------------------------------------------------
#How to use:
#Create a new Python virtual environment and install the latest oracleagentmemory version.
#You can now run the script
#1. As a Python file:
#```bash
#python integration_with_langgraph.py
#```
#2. As a Notebook (in VSCode):
#When viewing the file,
#- press the keys Ctrl + Enter to run the selected cell
#- or Shift + Enter to run the selected cell and move to the cell below
##Configure Oracle Memory and LangGraph setup
#%%
from typing import Annotated
from langchain.agents import create_agent
from langchain_core.messages import HumanMessage
from langchain_core.tools import tool
from langchain_openai import ChatOpenAI
from langgraph.graph import END, START, MessagesState, StateGraph
from oracleagentmemory.core.embedders.embedder import Embedder
from oracleagentmemory.core.llms.llm import Llm
from oracleagentmemory.core.oracleagentmemory import OracleAgentMemory
embedder = Embedder(
model="YOUR_EMBEDDING_MODEL",
api_base="YOUR_EMBEDDING_API_BASE",
api_key="YOUR_EMBEDDING_API_KEY",
)
llm = Llm(
model="gpt-4.1-mini",
api_key="YOUR_OPENAI_API_KEY",
)
db_pool = ... #an oracledb connection or connection pool
langgraph_llm = ChatOpenAI(
model="gpt-4.1-mini",
api_key="YOUR_OPENAI_API_KEY",
)
#Keep these identifiers stable for the same assistant and end user so memory
#is scoped consistently across threads and sessions.
agent_id = "support_agent"
user_id = "user_123"
agent_memory = OracleAgentMemory(
connection=db_pool,
embedder=embedder,
llm=llm,
)
@tool
def search_memory(
query: Annotated[str, "Question to search in Oracle Agent Memory"],
) -> Annotated[str, "Top matching durable memory content"]:
"""Search Oracle Agent Memory for durable user facts relevant to the current request."""
results = agent_memory.search(
query=query,
user_id=user_id,
agent_id=agent_id,
max_results=3,
record_types=["memory"],
)
if not results:
return "No relevant memory found."
return "\n".join(result.content for result in results)
def _latest_user_message(state: MessagesState) -> str:
for message in reversed(state["messages"]):
if getattr(message, "type", None) == "human":
return str(message.content)
if getattr(message, "role", None) == "user":
return str(message.content)
return ""
def _build_memory_context(query: str) -> str:
results = agent_memory.search(
query=query,
user_id=user_id,
agent_id=agent_id,
max_results=3,
record_types=["memory"],
)
memory_context = "\n".join(f"- {result.content}" for result in results)
return memory_context or "- No relevant memory found."
##Configure a prebuilt LangGraph ReAct agent
#%%
react_agent = create_agent(
model=langgraph_llm,
tools=[search_memory],
system_prompt=(
"You are a support agent. When the user asks about durable facts from "
"prior sessions, call the search_memory tool before answering."
),
)
react_memory_thread = agent_memory.create_thread(
thread_id="langgraph_react_memory_demo",
user_id=user_id,
agent_id=agent_id,
)
##Persist user context after a prebuilt ReAct session
#%%
react_session_1 = react_agent.invoke(
{
"messages": [
HumanMessage(
content="I am John, a Python developer and I need help debugging a payment service."
)
]
}
)
react_assistant_reply = react_session_1["messages"][-1].content
print(react_assistant_reply)
#I can help with that. What error are you seeing?
react_memory_thread.add_messages(
[
{
"role": "user",
"content": "I am John, a Python developer and I need help debugging a payment service.",
},
{
"role": "assistant",
"content": react_assistant_reply,
},
]
)
react_memory_thread.add_memory("The user is John, a Python developer.")
##Reuse memory in a new prebuilt ReAct session
#%%
react_memory_thread = agent_memory.get_thread("langgraph_react_memory_demo")
react_session_2 = react_agent.invoke(
{
"messages": [
HumanMessage(content="Who am I?")
]
}
)
react_remembered_reply = react_session_2["messages"][-1].content
print(react_remembered_reply)
#The user is John, a Python developer.
##Configure a custom LangGraph flow
#%%
def call_model(state: MessagesState):
from langchain_core.messages import SystemMessage
query = _latest_user_message(state)
memory_context = _build_memory_context(query)
response = langgraph_llm.invoke(
[
SystemMessage(
content=(
"You are a support agent. Use the durable memory below when it is "
"relevant to the current user request.\n\n"
f"Durable memory:\n{memory_context}"
)
),
*state["messages"],
]
)
return {"messages": [response]}
builder = StateGraph(MessagesState)
builder.add_node("call_model", call_model)
builder.add_edge(START, "call_model")
builder.add_edge("call_model", END)
flow_graph = builder.compile()
flow_memory_thread = agent_memory.create_thread(
thread_id="langgraph_flow_memory_demo",
user_id=user_id,
agent_id=agent_id,
)
##Persist user context after a flow session
#%%
flow_session_1 = flow_graph.invoke(
{
"messages": [
HumanMessage(
content="I am John, a Python developer and I need help debugging a payment service."
)
]
}
)
flow_assistant_reply = flow_session_1["messages"][-1].content
print(flow_assistant_reply)
#I can help with that. What error are you seeing?
flow_memory_thread.add_messages(
[
{
"role": "user",
"content": "I am John, a Python developer and I need help debugging a payment service.",
},
{
"role": "assistant",
"content": flow_assistant_reply,
},
]
)
flow_memory_thread.add_memory("The user is John, a Python developer.")
##Reuse memory in a new flow session
#%%
flow_memory_thread = agent_memory.get_thread("langgraph_flow_memory_demo")
flow_session_2 = flow_graph.invoke(
{
"messages": [
HumanMessage(content="Who am I?")
]
}
)
flow_remembered_reply = flow_session_2["messages"][-1].content
print(flow_remembered_reply)
#The user is John, a Python developer.
##Disable automatic memory extraction
#%%
manual_agent_memory = OracleAgentMemory(
connection=db_pool,
embedder=embedder,
extract_memories=False,
)
manual_memory_thread = manual_agent_memory.create_thread(
thread_id="langgraph_manual_memory_demo",
user_id=user_id,
agent_id=agent_id,
)
manual_memory_thread.add_messages(
[
{
"role": "user",
"content": "Please remember that I prefer concise code reviews.",
},
{
"role": "assistant",
"content": "Understood. I will keep responses concise.",
},
]
)
manual_memory_thread.add_memory("The user prefers concise code reviews.")