Uso de la memoria del agente con WayFlow

En este artículo, aprenderá a conectar la memoria del agente a un agente de WayFlow para que el agente pueda reutilizar hechos duraderos en las sesiones.

Consejo: para la configuración de paquetes, consulte Introducción a la memoria del agente. Si necesita una instancia local de Oracle AI Database para este ejemplo, consulte Run Oracle AI Database Locally. Para obtener más información sobre WayFlow, consulte https://github.com/oracle/wayflow.

Configuración de la memoria del agente y WayFlow

Cree un thread de memoria de agente para el usuario, exponga una herramienta search_memory a WayFlow y cree WayFlow Agent con un valor OpenAIModel. La herramienta search_memory consulta la API de memoria del agente por usuario e ID de agente para que pueda recuperar hechos duraderos de sesiones anteriores en lugar de limitarse al thread actual. El cliente de memoria del agente también utiliza su propio LLM para extraer periódicamente memorias duraderas de mensajes de thread recientes, mientras que WayFlow Agent sigue utilizando su propio OpenAIModel para respuestas y llamadas a herramientas.

from oracleagentmemory.core.embedders.embedder import Embedder
from oracleagentmemory.core.llms.llm import Llm
from oracleagentmemory.core.oracleagentmemory import OracleAgentMemory
from wayflowcore.agent import Agent
from wayflowcore.models import OpenAIModel
from wayflowcore.tools import tool

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
wayflow_llm = OpenAIModel(
    model_id="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"
memory = OracleAgentMemory(
    connection=db_pool,
    embedder=embedder,
    llm=llm,
)
memory_thread = memory.create_thread(
    thread_id="wayflow_memory_demo",
    user_id=user_id,
    agent_id=agent_id,
)

from typing import Annotated


@tool
def search_memory(
    query: Annotated[str, "Question to search in Oracle Agent Memory"],
) -> Annotated[str, "Top matching memory content"]:
    """Search Oracle Agent Memory for durable user facts relevant to the current request."""
    results = memory.search(
        query=query,
        user_id=user_id,
        agent_id=agent_id,
        max_results=1,
        record_types=["memory"],
    )
    if not results:
        return "No relevant memory found."
    return results[0].content

assistant = Agent(
    llm=wayflow_llm,
    agent_id=agent_id,
    custom_instruction=(
        "You are a support agent. When the user asks about durable facts from "
        "prior sessions, call the search_memory tool before answering."
    ),
    tools=[search_memory],
)

Conservar el contexto del usuario después de una sesión

Después de cada sesión de WayFlow, agregue los mensajes intercambiados a la memoria del agente y almacene cualquier hecho duradero que se deba volver a utilizar más adelante.

session_1 = assistant.start_conversation()
user_message = (
    "I am John, a Python developer and I need help debugging a payment service."
)
session_1.append_user_message(user_message)
session_1.execute()
assistant_reply = session_1.get_last_message().content

print(assistant_reply)
#I can help with that. What error are you seeing?

#add_messages will add messages to the DB and extract memories automatically
memory_thread.add_messages(
    [
        {"role": "user", "content": user_message},
        {"role": "assistant", "content": assistant_reply},
    ]
)
#add_memory adds memory to the DB
memory_thread.add_memory("The user is John, a Python developer.")

Reutilización de Memoria en una Nueva Sesión de WayFlow

Cuando se inicie una sesión posterior, vuelva a abrir el mismo thread de memoria de agente y permita que el agente de WayFlow llame a search_memory para recuperar el contexto de usuario anterior.

memory_thread = memory.get_thread("wayflow_memory_demo")
assistant = Agent(
    llm=wayflow_llm,
    agent_id=agent_id,
    custom_instruction=(
        "You are a support agent. When the user asks about durable facts from "
        "prior sessions, call the search_memory tool before answering."
    ),
    tools=[search_memory],
)

session_2 = assistant.start_conversation()
session_2.append_user_message("Who am I?")
session_2.execute()
remembered_reply = session_2.get_last_message().content

print(remembered_reply)

Salida:

The user is John, a Python developer.

Uso avanzado

Para una integración más estrecha, puede registrar un listener de eventos de WayFlow que almacena en buffer las entradas de ConversationMessageAddedEvent y las escribe en la memoria del agente al final de una ejecución. De esta forma, la ruta de acceso de actualización de la memoria del agente se desacopla del código de thread principal mientras se mantienen los mensajes intercambiados finales.

from wayflowcore.events.event import ConversationMessageAddedEvent
from wayflowcore.events.eventlistener import GenericEventListener, register_event_listeners

pending_messages: list[dict[str, str]] = []


def _buffer_thread_message(event: ConversationMessageAddedEvent) -> None:
    if event.streamed:
        return
    pending_messages.append(
        {
            "role": event.message.role,
            "content": event.message.content,
        }
    )


message_listener = GenericEventListener(
    [ConversationMessageAddedEvent],
    _buffer_thread_message,
)

with register_event_listeners([message_listener]):
    session_3 = assistant.start_conversation()
    session_3.append_user_message("Please remember that I prefer concise code reviews.")
    session_3.execute()

if pending_messages:
    memory_thread.add_messages(pending_messages)

Desactivar extracción automática

Si solo desea mantener mensajes y agregar memorias duraderas manualmente, cree el cliente de memoria del agente con extract_memories=False e inserte las filas de memoria duraderas usted mismo.

manual_memory = OracleAgentMemory(
    connection=db_pool,
    embedder=embedder,
    extract_memories=False,
)
manual_memory_thread = manual_memory.create_thread(
    thread_id="wayflow_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.")

Conclusión

En este artículo hemos aprendido a conectar la memoria del agente a un agente de WayFlow, a mantener los mensajes intercambiados y las memorias duraderas después de cada sesión y a reutilizar el contexto de usuario anterior en ejecuciones posteriores.

Consejo: después de haber aprendido a integrar la memoria del agente con WayFlow, puede que también le interese Integrar memoria del agente con LangGraph.

Código Completo

#Copyright © 2026 Oracle and/or its affiliates.
#isort:skip_file
#fmt: off
#Agent Memory Code Example - Integration with WayFlow
#-----------------------------------------------------

#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_wayflow.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 WayFlow

#%%
from oracleagentmemory.core.embedders.embedder import Embedder
from oracleagentmemory.core.llms.llm import Llm
from oracleagentmemory.core.oracleagentmemory import OracleAgentMemory
from wayflowcore.agent import Agent
from wayflowcore.models import OpenAIModel
from wayflowcore.tools import tool

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
wayflow_llm = OpenAIModel(
    model_id="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"
memory = OracleAgentMemory(
    connection=db_pool,
    embedder=embedder,
    llm=llm,
)
memory_thread = memory.create_thread(
    thread_id="wayflow_memory_demo",
    user_id=user_id,
    agent_id=agent_id,
)

from typing import Annotated


@tool
def search_memory(
    query: Annotated[str, "Question to search in Oracle Agent Memory"],
) -> Annotated[str, "Top matching memory content"]:
    """Search Oracle Agent Memory for durable user facts relevant to the current request."""
    results = memory.search(
        query=query,
        user_id=user_id,
        agent_id=agent_id,
        max_results=1,
        record_types=["memory"],
    )
    if not results:
        return "No relevant memory found."
    return results[0].content

assistant = Agent(
    llm=wayflow_llm,
    agent_id=agent_id,
    custom_instruction=(
        "You are a support agent. When the user asks about durable facts from "
        "prior sessions, call the search_memory tool before answering."
    ),
    tools=[search_memory],
)


##Persist user context after a session

#%%
session_1 = assistant.start_conversation()
user_message = (
    "I am John, a Python developer and I need help debugging a payment service."
)
session_1.append_user_message(user_message)
session_1.execute()
assistant_reply = session_1.get_last_message().content

print(assistant_reply)
#I can help with that. What error are you seeing?

memory_thread.add_messages(
    [
        {"role": "user", "content": user_message},
        {"role": "assistant", "content": assistant_reply},
    ]
)
memory_thread.add_memory("The user is John, a Python developer.")


##Reuse memory in a new WayFlow session

#%%
memory_thread = memory.get_thread("wayflow_memory_demo")
assistant = Agent(
    llm=wayflow_llm,
    agent_id=agent_id,
    custom_instruction=(
        "You are a support agent. When the user asks about durable facts from "
        "prior sessions, call the search_memory tool before answering."
    ),
    tools=[search_memory],
)

session_2 = assistant.start_conversation()
session_2.append_user_message("Who am I?")
session_2.execute()
remembered_reply = session_2.get_last_message().content

print(remembered_reply)
#The user is John, a Python developer.


##Advanced use event listeners

#%%
from wayflowcore.events.event import ConversationMessageAddedEvent
from wayflowcore.events.eventlistener import GenericEventListener, register_event_listeners

pending_messages: list[dict[str, str]] = []


def _buffer_thread_message(event: ConversationMessageAddedEvent) -> None:
    if event.streamed:
        return
    pending_messages.append(
        {
            "role": event.message.role,
            "content": event.message.content,
        }
    )


message_listener = GenericEventListener(
    [ConversationMessageAddedEvent],
    _buffer_thread_message,
)

with register_event_listeners([message_listener]):
    session_3 = assistant.start_conversation()
    session_3.append_user_message("Please remember that I prefer concise code reviews.")
    session_3.execute()

if pending_messages:
    memory_thread.add_messages(pending_messages)


##Disable automatic memory extraction

#%%
manual_memory = OracleAgentMemory(
    connection=db_pool,
    embedder=embedder,
    extract_memories=False,
)
manual_memory_thread = manual_memory.create_thread(
    thread_id="wayflow_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.")