Ajout de mémoire et de conversation

Concevoir des systèmes agentiques avec LangChain

Dilini K. Sumanapala, PhD

Founder & AI Engineer, Genverv, Ltd.

Tester l’usage d’outils

Schéma complet du chatbot avec nœud d’outils ajouté.

Tester l’usage d’outils

# Produire le graphe du chatbot
display(Image(app.get_graph().draw_mermaid_png()))


# Définir une fonction pour exécuter le chatbot et diffuser chaque message
def stream_tool_responses(user_input: str):
    for event in graph.stream({"messages": [("user", user_input)]}):


        # Renvoyer la dernière réponse de l'agent
        for value in event.values():
            print("Agent:", value["messages"])


# Définir la requête et lancer le chatbot
user_query = "House of Lords"
stream_tool_responses(user_query)

Visualiser le diagramme

Diagramme du chatbot LangGraph avec nœud d’outil

Diffuser la sortie

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')]

Ajouter de la mémoire

# Importer les modules pour sauvegarder la mémoire
from langgraph.checkpoint.memory import MemorySaver


# Modifier le graphe avec pointage de mémoire
memory = MemorySaver()


# Compiler le graphe en passant la mémoire
graph = graph_builder.compile(checkpointer=memory)

Diffuser des sorties avec mémoire

# Configure une fonction de streaming pour un utilisateur
def stream_memory_responses(user_input: str):

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


    # Diffuser les événements du graphe
    for event in graph.stream({"messages": [("user", user_input)]}, config):


        # Renvoyer la dernière réponse de l'agent
        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?")

Générer une sortie avec mémoire

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-...', ...')]

Générer une sortie avec mémoire

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 !

Concevoir des systèmes agentiques avec LangChain