Usa memoria agente con WayFlow

In questo articolo verrà descritto come connettere la memoria agente a un agente WayFlow in modo che l'agente possa riutilizzare i fact permanenti nelle varie sessioni.

Suggerimento: per l'impostazione dei package, vedere Introduzione alla memoria agente. Se hai bisogno di un Oracle AI Database locale per questo esempio, vedere Esegui Oracle AI Database localmente. Per ulteriori informazioni su WayFlow, vedere https://github.com/oracle/wayflow.

Configura memoria agente e WayFlow

Creare un thread di memoria agente per l'utente, esporre uno strumento search_memory a WayFlow e costruire WayFlow Agent con un OpenAIModel. Lo strumento search_memory esegue una query sull'API di memoria agente in base all'ID utente e agente in modo che possa recuperare i fact permanenti dalle sessioni precedenti invece di essere limitato al thread corrente. Il client Agent Memory utilizza anche il proprio LLM per estrarre periodicamente memorie durevoli dai messaggi thread recenti, mentre WayFlow Agent continua a utilizzare il proprio OpenAIModel per le risposte e le chiamate agli strumenti.

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],
)

Rendi persistente il contesto utente dopo una sessione

Dopo ogni sessione di WayFlow, aggiungere i messaggi scambiati alla memoria dell'agente e memorizzare qualsiasi fatto durevole che dovrebbe essere riutilizzato in un secondo momento.

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.")

Riutilizza memoria in una nuova sessione WayFlow

Quando si avvia una sessione successiva, riaprire lo stesso thread di memoria agente e lasciare che l'agente WayFlow chiami search_memory per recuperare il contesto utente precedente.

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)

Output:

The user is John, a Python developer.

Uso avanzato

Per un'integrazione più stretta, è possibile registrare un listener di eventi WayFlow che esegue il buffer delle voci ConversationMessageAddedEvent e le scrive nella memoria dell'agente alla fine di un'esecuzione. In questo modo, il percorso di aggiornamento della memoria dell'agente viene disaccoppiato dal codice del thread principale, continuando a rendere persistenti i messaggi scambiati finali.

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)

Disabilita estrazione automatica

Se si desidera rendere persistenti solo i messaggi e aggiungere manualmente memorie permanenti, creare il client di memoria agente con extract_memories=False e inserire le righe di memoria permanente manualmente.

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.")

Conclusione

In questo articolo abbiamo imparato a connettere la memoria agente a un agente WayFlow, a rendere persistenti i messaggi scambiati e le memorie permanenti dopo ogni sessione e a riutilizzare il contesto utente precedente nelle esecuzioni successive.

Suggerimento: dopo aver appreso come integrare la memoria dell'agente con WayFlow, potrebbe essere interessante anche Integrare la memoria dell'agente con LangGraph.

Codice 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.")