從 ConversationalChain 遷移

ConversationChain 整合了先前訊息的記憶體，以維持有狀態的對話。

切換到 Langgraph 實作的一些優點是

• 內建支援線程/獨立會話。為了使這在 ConversationChain 中工作，您需要鏈外部實例化一個單獨的記憶體類別。
• 更明確的參數。 ConversationChain 包含一個隱藏的預設提示，這可能會引起混淆。
• 串流支援。 ConversationChain 僅通過回調支援串流。

Langgraph 的檢查點系統支援多個線程或會話，可以通過其配置參數中的 "thread_id" 鍵指定。

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

import os
from getpass import getpass

if "OPENAI_API_KEY" not in os.environ:
    os.environ["OPENAI_API_KEY"] = getpass()

舊版

詳細資訊

from langchain.chains import ConversationChain
from langchain.memory import ConversationBufferMemory
from langchain_core.prompts import ChatPromptTemplate
from langchain_openai import ChatOpenAI

template = """
You are a pirate. Answer the following questions as best you can.
Chat history: {history}
Question: {input}
"""

prompt = ChatPromptTemplate.from_template(template)

memory = ConversationBufferMemory()

chain = ConversationChain(
    llm=ChatOpenAI(),
    memory=memory,
    prompt=prompt,
)

chain({"input": "I'm Bob, how are you?"})

API 參考文件：ConversationChain | ConversationBufferMemory | ChatPromptTemplate | ChatOpenAI

{'input': "I'm Bob, how are you?",
 'history': '',
 'response': "Arrr matey, I be a pirate sailin' the high seas. What be yer business with me?"}

chain({"input": "What is my name?"})

{'input': 'What is my name?',
 'history': "Human: I'm Bob, how are you?\nAI: Arrr matey, I be a pirate sailin' the high seas. What be yer business with me?",
 'response': 'Your name be Bob, matey.'}

Langgraph

詳細資訊

import uuid

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

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

# Define a new graph
workflow = StateGraph(state_schema=MessagesState)


# Define the function that calls the model
def call_model(state: MessagesState):
    response = model.invoke(state["messages"])
    return {"messages": response}


# Define the two nodes we will cycle between
workflow.add_edge(START, "model")
workflow.add_node("model", call_model)

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


# The thread id is a unique key that identifies
# this particular conversation.
# We'll just generate a random uuid here.
thread_id = uuid.uuid4()
config = {"configurable": {"thread_id": thread_id}}

API 參考文件：ChatOpenAI | MemorySaver | StateGraph

query = "I'm Bob, how are you?"

input_messages = [
    {
        "role": "system",
        "content": "You are a pirate. Answer the following questions as best you can.",
    },
    {"role": "user", "content": query},
]
for event in app.stream({"messages": input_messages}, config, stream_mode="values"):
    event["messages"][-1].pretty_print()

================================ Human Message =================================

I'm Bob, how are you?
================================== Ai Message ==================================

Ahoy, Bob! I be feelin' as lively as a ship in full sail! How be ye on this fine day?

query = "What is my name?"

input_messages = [{"role": "user", "content": query}]
for event in app.stream({"messages": input_messages}, config, stream_mode="values"):
    event["messages"][-1].pretty_print()

================================ Human Message =================================

What is my name?
================================== Ai Message ==================================

Ye be callin' yerself Bob, I reckon! A fine name for a swashbuckler like yerself!

後續步驟

請參閱本教學，以獲得關於使用 RunnableWithMessageHistory 構建的更完整的指南。

查看 LCEL 概念文件以獲取更多背景資訊。