如何为聊天机器人添加记忆

%pip install --upgrade --quiet langchain langchain-openai langgraph

import getpass
import os

if not os.environ.get("OPENAI_API_KEY"):
    os.environ["OPENAI_API_KEY"] = getpass.getpass("OpenAI API Key:")

from langchain_openai import ChatOpenAI

model = ChatOpenAI(model="gpt-4o-mini")

from langchain_core.messages import AIMessage, HumanMessage, SystemMessage
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder

prompt = ChatPromptTemplate.from_messages(
    [
        SystemMessage(
            content="You are a helpful assistant. Answer all questions to the best of your ability."
        ),
        MessagesPlaceholder(variable_name="messages"),
    ]
)

chain = prompt | model

ai_msg = chain.invoke(
    {
        "messages": [
            HumanMessage(
                content="Translate from English to French: I love programming."
            ),
            AIMessage(content="J'adore la programmation."),
            HumanMessage(content="What did you just say?"),
        ],
    }
)
print(ai_msg.content)

from langgraph.checkpoint.memory import MemorySaver
from langgraph.graph import START, MessagesState, StateGraph

workflow = StateGraph(state_schema=MessagesState)


# Define the function that calls the model
def call_model(state: MessagesState):
    system_prompt = (
        "You are a helpful assistant. "
        "Answer all questions to the best of your ability."
    )
    messages = [SystemMessage(content=system_prompt)] + state["messages"]
    response = model.invoke(messages)
    return {"messages": response}


# Define the node and edge
workflow.add_node("model", call_model)
workflow.add_edge(START, "model")

# Add simple in-memory checkpointer
memory = MemorySaver()
app = workflow.compile(checkpointer=memory)

app.invoke(
    {"messages": [HumanMessage(content="Translate to French: I love programming.")]},
    config={"configurable": {"thread_id": "1"}},
)

app.invoke(
    {"messages": [HumanMessage(content="What did I just ask you?")]},
    config={"configurable": {"thread_id": "1"}},
)

demo_ephemeral_chat_history = [
    HumanMessage(content="Hey there! I'm Nemo."),
    AIMessage(content="Hello!"),
    HumanMessage(content="How are you today?"),
    AIMessage(content="Fine thanks!"),
]

app.invoke(
    {
        "messages": demo_ephemeral_chat_history
        + [HumanMessage(content="What's my name?")]
    },
    config={"configurable": {"thread_id": "2"}},
)

from langchain_core.messages import trim_messages
from langgraph.checkpoint.memory import MemorySaver
from langgraph.graph import START, MessagesState, StateGraph

# Define trimmer
# count each message as 1 "token" (token_counter=len) and keep only the last two messages
trimmer = trim_messages(strategy="last", max_tokens=2, token_counter=len)

workflow = StateGraph(state_schema=MessagesState)


# Define the function that calls the model
def call_model(state: MessagesState):
    trimmed_messages = trimmer.invoke(state["messages"])
    system_prompt = (
        "You are a helpful assistant. "
        "Answer all questions to the best of your ability."
    )
    messages = [SystemMessage(content=system_prompt)] + trimmed_messages
    response = model.invoke(messages)
    return {"messages": response}


# Define the node and edge
workflow.add_node("model", call_model)
workflow.add_edge(START, "model")

# Add simple in-memory checkpointer
memory = MemorySaver()
app = workflow.compile(checkpointer=memory)

app.invoke(
    {
        "messages": demo_ephemeral_chat_history
        + [HumanMessage(content="What is my name?")]
    },
    config={"configurable": {"thread_id": "3"}},
)

demo_ephemeral_chat_history = [
    HumanMessage(content="Hey there! I'm Nemo."),
    AIMessage(content="Hello!"),
    HumanMessage(content="How are you today?"),
    AIMessage(content="Fine thanks!"),
]

from langchain_core.messages import HumanMessage, RemoveMessage
from langgraph.checkpoint.memory import MemorySaver
from langgraph.graph import START, MessagesState, StateGraph

workflow = StateGraph(state_schema=MessagesState)


# Define the function that calls the model
def call_model(state: MessagesState):
    system_prompt = (
        "You are a helpful assistant. "
        "Answer all questions to the best of your ability. "
        "The provided chat history includes a summary of the earlier conversation."
    )
    system_message = SystemMessage(content=system_prompt)
    message_history = state["messages"][:-1]  # exclude the most recent user input
    # Summarize the messages if the chat history reaches a certain size
    if len(message_history) >= 4:
        last_human_message = state["messages"][-1]
        # Invoke the model to generate conversation summary
        summary_prompt = (
            "Distill the above chat messages into a single summary message. "
            "Include as many specific details as you can."
        )
        summary_message = model.invoke(
            message_history + [HumanMessage(content=summary_prompt)]
        )

        # Delete messages that we no longer want to show up
        delete_messages = [RemoveMessage(id=m.id) for m in state["messages"]]
        # Re-add user message
        human_message = HumanMessage(content=last_human_message.content)
        # Call the model with summary & response
        response = model.invoke([system_message, summary_message, human_message])
        message_updates = [summary_message, human_message, response] + delete_messages
    else:
        message_updates = model.invoke([system_message] + state["messages"])

    return {"messages": message_updates}


# Define the node and edge
workflow.add_node("model", call_model)
workflow.add_edge(START, "model")

# Add simple in-memory checkpointer
memory = MemorySaver()
app = workflow.compile(checkpointer=memory)

app.invoke(
    {
        "messages": demo_ephemeral_chat_history
        + [HumanMessage("What did I say my name was?")]
    },
    config={"configurable": {"thread_id": "4"}},
)