Neo4j

Neo4j stöder två distinkta Agent Framework-kontextprovidermönster. De delar en grafdatabas men använder separata paket och dataflöden.

GraphRAG från ett befintligt kunskapsdiagram

Neo4j GraphRAG-kontextprovidern lägger till RAG-funktioner (Retrieval Augmented Generation) till Agent Framework-agenter med hjälp av ett Neo4j-kunskapsdiagram. Den stöder vektor-, fulltext- och hybridsöklägen, med valfri grafbläddering för att utöka resultat med relaterade entiteter via anpassade Cypher-frågor.

Andra hanterade hämtningstjänster finns i Azure AI-sökning och Microsoft Foundry.

För kunskapsgrafscenarier där relationer mellan entiteter är viktiga hämtar den här providern relevanta undergrafer i stället för isolerade textsegment, vilket ger agenter ett bättre sammanhang för att generera svar.

Varför ska du använda Neo4j för GraphRAG?

• Förbättrad hämtning av diagram: Standardvektorsökning returnerar isolerade segment; graph traversal följer anslutningar till ytrelaterade entiteter, vilket ger agenter ett bättre sammanhang.
• Flexibla söklägen: Kombinera vektorlikhet, nyckelord/BM25 och grafbläddering i en enda fråga.
• Anpassade hämtningsfrågor: Med Cypher-frågor kan du styra exakt vilka relationer som ska passeras och vilken kontext som ska returneras.

dotnet add package Neo4j.AgentFramework.GraphRAG

using Azure.AI.OpenAI;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Agents.AI.OpenAI;
using Microsoft.Extensions.AI;
using Neo4j.AgentFramework.GraphRAG;
using Neo4j.Driver;

// Read connection details from environment variables
var neo4jSettings = new Neo4jSettings();
var azureEndpoint = Environment.GetEnvironmentVariable("AZURE_AI_SERVICES_ENDPOINT")!;

// Create embedding generator
var credential = new DefaultAzureCredential();
var azureClient = new AzureOpenAIClient(new Uri(azureEndpoint), credential);

IEmbeddingGenerator<string, Embedding<float>> embedder = azureClient
    .GetEmbeddingClient("text-embedding-3-small")
    .AsIEmbeddingGenerator();

// Create Neo4j driver
await using var driver = GraphDatabase.Driver(
    neo4jSettings.Uri, AuthTokens.Basic(neo4jSettings.Username, neo4jSettings.Password!));

// Create the Neo4j context provider
await using var provider = new Neo4jContextProvider(driver, new Neo4jContextProviderOptions
{
    IndexName = "chunkEmbeddings",
    IndexType = IndexType.Vector,
    EmbeddingGenerator = embedder,
    TopK = 5,
    RetrievalQuery = """
        MATCH (node)-[:FROM_DOCUMENT]->(doc:Document)
        OPTIONAL MATCH (doc)<-[:FILED]-(company:Company)
        RETURN node.text AS text, score, doc.title AS title, company.name AS company
        ORDER BY score DESC
        """,
});

// Create an agent with the provider
AIAgent agent = azureClient
    .GetChatClient("gpt-4o")
    .AsIChatClient()
    .AsBuilder()
    .UseAIContextProviders(provider)
    .BuildAIAgent(new ChatClientAgentOptions
    {
        ChatOptions = new ChatOptions
        {
            Instructions = "You are a financial analyst assistant.",
        },
    });

var session = await agent.CreateSessionAsync();
Console.WriteLine(await agent.RunAsync("What risks does Acme Corp face?", session));

pip install agent-framework-neo4j

import os

from agent_framework import Agent
from agent_framework.foundry import FoundryChatClient
from agent_framework_neo4j import Neo4jContextProvider, Neo4jSettings, AzureAISettings, AzureAIEmbedder
from azure.identity import DefaultAzureCredential
from azure.identity.aio import AzureCliCredential

# Reads NEO4J_URI, NEO4J_USERNAME, NEO4J_PASSWORD from environment variables
neo4j_settings = Neo4jSettings()

# Reads FOUNDRY_PROJECT_ENDPOINT, AZURE_AI_EMBEDDING_NAME from environment variables
azure_settings = AzureAISettings()

sync_credential = DefaultAzureCredential()
embedder = AzureAIEmbedder(
    endpoint=azure_settings.inference_endpoint,
    credential=sync_credential,
    model=azure_settings.embedding_model,
)

neo4j_provider = Neo4jContextProvider(
    uri=neo4j_settings.uri,
    username=neo4j_settings.username,
    password=neo4j_settings.get_password(),
    index_name=neo4j_settings.vector_index_name,
    index_type="vector",
    embedder=embedder,
    top_k=5,
    retrieval_query="""
        MATCH (node)-[:FROM_DOCUMENT]->(doc:Document)
        OPTIONAL MATCH (doc)<-[:FILED]-(company:Company)
        RETURN node.text AS text, score, doc.title AS title, company.name AS company
        ORDER BY score DESC
    """,
)

async with (
    neo4j_provider,
    AzureCliCredential() as credential,
    Agent(
        client=FoundryChatClient(
            credential=credential,
            project_endpoint=azure_settings.project_endpoint,
            model=os.environ["FOUNDRY_MODEL"],
        ),
        instructions="You are a financial analyst assistant.",
        context_providers=[neo4j_provider],
    ) as agent,
):
    session = agent.create_session()
    response = await agent.run("What risks does Acme Corp face?", session=session)

Beständigt agentminne

Neo4j-minnesintegrering lagrar och återkallar agentinteraktioner, extraherar automatiskt entiteter och skapar ett kunskapsdiagram över tid.

Leverantörerna hanterar:

• Kortsiktigt minne: Konversationshistorik och aktuell kontext.
• Långtidsminne: Entiteter, inställningar och fakta som extraherats från interaktioner.
• Resonemangsminne: Tidigare resonemangsspårningar och användningsmönster för verktyg.

Varför använda Neo4j för agentminne?

• Kunskapsdiagramspersistens: Minnen lagras som anslutna entiteter, inte platta poster, så agenten kan resonera om relationer mellan ihågkommen information.
• Automatisk entitetsextrahering: Konversationer parsas i strukturerade entiteter och relationer utan ett manuellt definierat schema.
• Minne mellan sessioner: Inställningar, fakta och resonemangsspår sparas mellan sessioner och visas via kontextleverantörer.

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)

Nästa steg