Provider di memoria Neo4j

Il provider di memoria Neo4j offre agli agenti di Agent Framework la memoria persistente supportata da un grafico delle conoscenze. A differenza dei provider RAG che recuperano da knowledge base statiche, il provider di memoria archivia e richiama le interazioni dell'agente, estraendo automaticamente le entità e creando un grafico delle informazioni nel tempo.

Il provider gestisce tre tipi di memoria:

• Memoria a breve termine: cronologia delle conversazioni e contesto recente
• Memoria a lungo termine: entità, preferenze e fatti estratti dalle interazioni
• Memoria di ragionamento: tracce di ragionamento passate e modelli di utilizzo degli strumenti

Perché usare Neo4j per la memoria dell'agente?

• Persistenza del grafico delle conoscenze: le memorie vengono archiviate come entità connesse, non come record flat, in modo che l'agente possa ragionare sulle relazioni tra elementi che ricorda.
• Estrazione automatica di entità: le conversazioni vengono analizzate in entità strutturate e relazioni senza progettazione manuale dello schema.
• Richiamo cross-sessione: preferenze, fatti e tracce di ragionamento persistono tra sessioni e sono visualizzati automaticamente tramite fornitori di contesto.

dotnet add package AgentMemory
dotnet add package AgentMemory.AgentFramework

using Azure.AI.OpenAI;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
using Microsoft.Extensions.DependencyInjection;
using Microsoft.Extensions.Hosting;
using AgentMemory;
using AgentMemory.Abstractions.Services;
using AgentMemory.AgentFramework;
using AgentMemory.AgentFramework.Tools;

var builder = Host.CreateApplicationBuilder(args);

// Registers Core + Neo4j infrastructure in one call (reads NEO4J_URI / NEO4J_USERNAME /
// NEO4J_PASSWORD, falling back to local-dev defaults). Passing configureLlm opts in to
// LLM-backed entity/fact/preference extraction, using the IChatClient registered below.
builder.Services.AddNeo4jAgentMemory(
    configureMemory: _ => { },
    configureNeo4j: neo4j =>
    {
        neo4j.Uri = Environment.GetEnvironmentVariable("NEO4J_URI") ?? "bolt://localhost:7687";
        neo4j.Username = Environment.GetEnvironmentVariable("NEO4J_USERNAME") ?? "neo4j";
        neo4j.Password = Environment.GetEnvironmentVariable("NEO4J_PASSWORD") ?? "password";
    },
    configureLlm: _ => { });

// Any Microsoft.Extensions.AI-compatible chat + embedding client works
var azureClient = new AzureOpenAIClient(
    new Uri(Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT")!), new DefaultAzureCredential());
builder.Services.AddSingleton(azureClient.GetChatClient("gpt-4o-mini").AsIChatClient());
builder.Services.AddSingleton(azureClient.GetEmbeddingClient("text-embedding-3-small").AsIEmbeddingGenerator());

// AutoExtractOnPersist builds the knowledge graph from every conversation turn
builder.Services.AddAgentMemoryFramework(options =>
{
    options.AutoExtractOnPersist = true;
    options.ContextFormat.IncludeEntities = true;
    options.ContextFormat.IncludeFacts = true;
    options.ContextFormat.IncludePreferences = true;
});

using var host = builder.Build();
await using var scope = host.Services.CreateAsyncScope();
var services = scope.ServiceProvider;

// Bootstraps Neo4j schema/indexes on first run (idempotent)
await services.GetRequiredService<ISchemaBootstrapper>().BootstrapAsync();

var memoryProvider = services.GetRequiredService<Neo4jMemoryContextProvider>();
var memoryTools = services.GetRequiredService<MemoryToolFactory>().CreateAIFunctions();

// WithMemoryOwnerScoping wraps the whole invocation — recall, the tool-calling loop, and
// persistence — in the owner scope set by WithMemoryIdentity below, so no manual
// BeginOwnerScope call is needed around RunAsync.
AIAgent agent = services.GetRequiredService<IChatClient>().AsAIAgent(new ChatClientAgentOptions
{
    ChatOptions = new ChatOptions
    {
        Instructions = "You are a helpful assistant with persistent memory.",
        Tools = [.. memoryTools],
    },
    AIContextProviders = [memoryProvider],
}).WithMemoryOwnerScoping(services);

var session = (await agent.CreateSessionAsync())
    .WithMemoryIdentity(userId: "user-123", sessionId: "session-1", applicationId: "my-app");

var response = await agent.RunAsync("Remember that I prefer window seats on flights.", session);

pip install neo4j-agent-memory[microsoft-agent]

import os
from pydantic import SecretStr
from agent_framework import Agent
from agent_framework.foundry import FoundryChatClient
from azure.identity.aio import AzureCliCredential
from neo4j_agent_memory import MemoryClient, MemorySettings
from neo4j_agent_memory.integrations.microsoft_agent import (
    Neo4jMicrosoftMemory,
    create_memory_tools,
)

# Pass Neo4j and embedding configuration directly via constructor arguments.
# MemorySettings also supports loading from environment variables or .env files
# using the NAM_ prefix (e.g. NAM_NEO4J__URI, NAM_EMBEDDING__MODEL).
settings = MemorySettings(
    neo4j={
        "uri": os.environ["NEO4J_URI"],
        "username": os.environ.get("NEO4J_USERNAME", "neo4j"),
        "password": SecretStr(os.environ["NEO4J_PASSWORD"]),
    },
    embedding={
        "provider": "openai",
        "model": "text-embedding-3-small",
    },
)

memory_client = MemoryClient(settings)

async with memory_client:
    memory = Neo4jMicrosoftMemory.from_memory_client(
        memory_client=memory_client,
        session_id="user-123",
    )
    tools = create_memory_tools(memory)

    async with AzureCliCredential() as credential, Agent(
            client=FoundryChatClient(
            credential=credential,
            project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
            model=os.environ["FOUNDRY_MODEL"],
        ),
        instructions="You are a helpful assistant with persistent memory.",
        tools=tools,
        context_providers=[memory.context_provider],
    ) as agent:
        session = agent.create_session()
        response = await agent.run("Remember that I prefer window seats on flights.", session=session)

Passaggi successivi