メモリと会話の追加

LangChainで設計するエージェント型システム

Dilini K. Sumanapala, PhD

Founder & AI Engineer, Genverv, Ltd.

ツール使用のテスト

ツールノードを追加した完全なチャットボット図。

ツール使用のテスト

# チャットボットのグラフを生成
display(Image(app.get_graph().draw_mermaid_png()))


# 各メッセージをストリーミングして実行する関数を定義
def stream_tool_responses(user_input: str):
    for event in graph.stream({"messages": [("user", user_input)]}):


        # エージェントの最新応答を返す
        for value in event.values():
            print("Agent:", value["messages"])


# クエリを定義して実行
user_query = "House of Lords"
stream_tool_responses(user_query)

ダイアグラムの可視化

ツールノード付きのLangGraphチャットボット図

出力のストリーミング

Agent: [AIMessage(content='', additional_kwargs={'tool_calls': [{'function': {'arguments': 
'{"query":"House of Lords"}', 'name': 'wikipedia'}, 'type': 'function'}]},
response_metadata={'...'}])]

Agent: [ToolMessage(content='Page: House of Lords\nSummary: The House of Lords is the upper 
house of the Parliament of the United Kingdom. Like the lower house...The House of Lords 
also has a Church of England role...', name='wikipedia', id='...',')]

Agent: [AIMessage(content='The House of Lords is the upper house of the Parliament 
of the United Kingdom, located in the Palace of Westminster in London. It is one 
of the oldest institutions in the world..., additional_kwargs={},

response_metadata=
{'finish_reason': 'stop', 'model_name': 'gpt-4o-mini-2024-07-18', 'system_fingerprint': 
'fp_0ba0d124f1'}, id='run-ae3a0b4f-5b42-4f4e-9409-7c191af0b9c9-0')]

メモリの追加

# メモリ保存用のモジュールをインポート
from langgraph.checkpoint.memory import MemorySaver


# メモリのチェックポイントを使うようグラフを変更
memory = MemorySaver()


# メモリを渡してグラフをコンパイル
graph = graph_builder.compile(checkpointer=memory)

メモリ付きの出力ストリーミング

# 単一ユーザー用のストリーミング関数を設定
def stream_memory_responses(user_input: str):

    config = {"configurable": {"thread_id": "single_session_memory"}}


    # グラフ内のイベントをストリーミング
    for event in graph.stream({"messages": [("user", user_input)]}, config):


        # エージェントの最新応答を返す
        for value in event.values():
            if "messages" in value and value["messages"]:
                print("Agent:", value["messages"])


stream_memory_responses("What is the Colosseum?")
stream_memory_responses("Who built it?")

メモリで出力を生成

stream_memory_responses("What is the Colosseum?")

Agent: [AIMessage(content='', additional_kwargs={'tool_calls': [{'index': 0, 
'id': '...', 'function': {'arguments': '
{"query":"Colosseum"}', 'name': 'wikipedia'}, ...])]

Agent: [ToolMessage(content='Page: Colosseum\nSummary: The Colosseum is an ancient
amphitheatre in Rome, Italy. It is the largest standing amphitheatre 
in the world..)]

Agent: [AIMessage(content='The Colosseum, located in Rome, is the largest ancient 
amphitheatre still standing. Built under Emperor Vespasian and completed by his son 
Titus, it hosted gladiatorial games and public events. It is also known as the Flavian 
Amphitheatre due to its association with the Flavian dynasty.', additional_kwargs={}, 
response_metadata={'finish_reason': 'stop', 'model_name': 'gpt-4o-mini-...', ...')]

メモリで出力を生成

stream_memory_responses("Who built it?")

Agent: [AIMessage(content='The Colosseum was built by Emperor Vespasian around 
72 AD and completed by his successor, Emperor Titus. Later modifications were 
made by Emperor Domitian...')]

Passons à la pratique !

LangChainで設計するエージェント型システム