Anleitung: OpenAIAssistantAgent Dateisuche

Verwenden Sie den dotnet Befehl, um Paketabhängigkeiten aus der Befehlszeile hinzuzufügen:

dotnet add package Azure.Identity
dotnet add package Microsoft.Extensions.Configuration
dotnet add package Microsoft.Extensions.Configuration.Binder
dotnet add package Microsoft.Extensions.Configuration.UserSecrets
dotnet add package Microsoft.Extensions.Configuration.EnvironmentVariables
dotnet add package Microsoft.SemanticKernel
dotnet add package Microsoft.SemanticKernel.Agents.OpenAI --prerelease

Die Projektdatei (.csproj) sollte die folgenden PackageReference Definitionen enthalten:

  <ItemGroup>
    <PackageReference Include="Azure.Identity" Version="<stable>" />
    <PackageReference Include="Microsoft.Extensions.Configuration" Version="<stable>" />
    <PackageReference Include="Microsoft.Extensions.Configuration.Binder" Version="<stable>" />
    <PackageReference Include="Microsoft.Extensions.Configuration.UserSecrets" Version="<stable>" />
    <PackageReference Include="Microsoft.Extensions.Configuration.EnvironmentVariables" Version="<stable>" />
    <PackageReference Include="Microsoft.SemanticKernel" Version="<latest>" />
    <PackageReference Include="Microsoft.SemanticKernel.Agents.OpenAI" Version="<latest>" />
  </ItemGroup>

Die Agent Framework ist experimentell und erfordert die Unterdrückung von Warnmeldungen. Dies kann als Eigenschaft in der Projektdatei adressiert werden (.csproj):

  <PropertyGroup>
    <NoWarn>$(NoWarn);CA2007;IDE1006;SKEXP0001;SKEXP0110;OPENAI001</NoWarn>
  </PropertyGroup>

Kopieren Sie außerdem den Inhalt Grimms-The-King-of-the-Golden-Mountain.txt, Grimms-The-Water-of-Life.txt und Grimms-The-White-Snake.txt aus dem Semantisches Kernel-ProjektLearnResources-Gemeingut. Fügen Sie diese Dateien in Ihrem Projektordner hinzu, und konfigurieren Sie sie so, dass sie in das Ausgabeverzeichnis kopiert werden:

  <ItemGroup>
    <None Include="Grimms-The-King-of-the-Golden-Mountain.txt">
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </None>
    <None Include="Grimms-The-Water-of-Life.txt">
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </None>
    <None Include="Grimms-The-White-Snake.txt">
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </None>
  </ItemGroup>

Erstellen Sie zunächst einen Ordner, der Ihr Skript (.py Datei) und die Beispielressourcen enthält. Fügen Sie die folgenden Importe am Anfang der .py Datei ein:

import asyncio
import os

from semantic_kernel.agents import AssistantAgentThread, AzureAssistantAgent
from semantic_kernel.contents import StreamingAnnotationContent

Kopieren Sie außerdem den Inhalt Grimms-The-King-of-the-Golden-Mountain.txt, Grimms-The-Water-of-Life.txt und Grimms-The-White-Snake.txt aus dem Semantisches Kernel-ProjektLearnResources-Gemeingut. Fügen Sie diese Dateien in Ihrem Projektordner hinzu.

Das Feature ist derzeit in Java nicht verfügbar.

# OpenAI
dotnet user-secrets set "OpenAISettings:ApiKey" "<api-key>"
dotnet user-secrets set "OpenAISettings:ChatModel" "gpt-4o"

# Azure OpenAI
dotnet user-secrets set "AzureOpenAISettings:ApiKey" "<api-key>" # Not required if using token-credential
dotnet user-secrets set "AzureOpenAISettings:Endpoint" "https://lightspeed-team-shared-openai-eastus.openai.azure.com/"
dotnet user-secrets set "AzureOpenAISettings:ChatModelDeployment" "gpt-4o"

Die folgende Klasse wird in allen Agent-Beispielen verwendet. Achten Sie darauf, sie in Ihr Projekt einzuschließen, um die ordnungsgemäße Funktionalität sicherzustellen. Diese Klasse dient als grundlegende Komponente für die folgenden Beispiele.

using System.Reflection;
using Microsoft.Extensions.Configuration;

namespace AgentsSample;

public class Settings
{
    private readonly IConfigurationRoot configRoot;

    private AzureOpenAISettings azureOpenAI;
    private OpenAISettings openAI;

    public AzureOpenAISettings AzureOpenAI => this.azureOpenAI ??= this.GetSettings<Settings.AzureOpenAISettings>();
    public OpenAISettings OpenAI => this.openAI ??= this.GetSettings<Settings.OpenAISettings>();

    public class OpenAISettings
    {
        public string ChatModel { get; set; } = string.Empty;
        public string ApiKey { get; set; } = string.Empty;
    }

    public class AzureOpenAISettings
    {
        public string ChatModelDeployment { get; set; } = string.Empty;
        public string Endpoint { get; set; } = string.Empty;
        public string ApiKey { get; set; } = string.Empty;
    }

    public TSettings GetSettings<TSettings>() =>
        this.configRoot.GetRequiredSection(typeof(TSettings).Name).Get<TSettings>()!;

    public Settings()
    {
        this.configRoot =
            new ConfigurationBuilder()
                .AddEnvironmentVariables()
                .AddUserSecrets(Assembly.GetExecutingAssembly(), optional: true)
                .Build();
    }
}

Die schnellste Möglichkeit, mit der richtigen Konfiguration zu beginnen, um den Beispielcode auszuführen, besteht darin, eine .env Datei im Stammverzeichnis Ihres Projekts zu erstellen (wo Ihr Skript ausgeführt wird).

Konfigurieren Sie die folgenden Einstellungen in Ihrer .env Datei für Azure OpenAI oder OpenAI:

AZURE_OPENAI_API_KEY="..."
AZURE_OPENAI_ENDPOINT="https://<resource-name>.openai.azure.com/"
AZURE_OPENAI_CHAT_DEPLOYMENT_NAME="..."
AZURE_OPENAI_API_VERSION="..."

OPENAI_API_KEY="sk-..."
OPENAI_ORG_ID=""
OPENAI_CHAT_MODEL_ID=""

Nach der Konfiguration werden die entsprechenden KI-Dienstklassen die erforderlichen Variablen abholen und während der Instanziierung verwenden.

Das Feature ist derzeit in Java nicht verfügbar.

Instanziieren Sie die Klasse, auf die Settings im vorherigen Konfigurationsabschnitt verwiesen wird. Verwenden Sie die Einstellungen, um ein AzureOpenAIClient zu erstellen, das für die Agentendefinition sowie für Datei-Upload und die Erstellung eines VectorStore verwendet wird.

Settings settings = new();

AzureOpenAIClient client = OpenAIAssistantAgent.CreateAzureOpenAIClient(new AzureCliCredential(), new Uri(settings.AzureOpenAI.Endpoint));

Die statische Methode create_client() für den Assistenten-Agent behandelt das Erstellen des Clients und gibt ihn basierend auf der gewünschten Konfiguration zurück. Pydantische Einstellungen werden verwendet, um Umgebungsvariablen zuerst aus Umgebungsvariablen oder aus der datei .env zu laden. Eine kann die api_key, api_version, deployment_name oder endpointübergeben, die Vorrang vor allen konfigurierten Umgebungsvariablen hat.

# Create the client using Azure OpenAI resources and configuration
client = AzureAssistantAgent.create_client()

Das Feature ist derzeit in Java nicht verfügbar.

Verwenden Sie AzureOpenAIClient, um auf ein VectorStoreClient zuzugreifen und ein VectorStore zu erstellen.

Console.WriteLine("Creating store...");
VectorStoreClient storeClient = client.GetVectorStoreClient();
CreateVectorStoreOperation operation = await storeClient.CreateVectorStoreAsync(waitUntilCompleted: true);
string storeId = operation.VectorStoreId;

# Upload the files to the client
file_ids: list[str] = []
for path in [get_filepath_for_filename(filename) for filename in filenames]:
    with open(path, "rb") as file:
        file = await client.files.create(file=file, purpose="assistants")
        file_ids.append(file.id)

vector_store = await client.vector_stores.create(
    name="assistant_search",
    file_ids=file_ids,
)

# Get the file search tool and resources
file_search_tools, file_search_tool_resources = AzureAssistantAgent.configure_file_search_tool(
    vector_store_ids=vector_store.id
)

Das Feature ist derzeit in Java nicht verfügbar.

private static readonly string[] _fileNames =
    [
        "Grimms-The-King-of-the-Golden-Mountain.txt",
        "Grimms-The-Water-of-Life.txt",
        "Grimms-The-White-Snake.txt",
    ];

filenames = [
    "Grimms-The-King-of-the-Golden-Mountain.txt",
    "Grimms-The-Water-of-Life.txt",
    "Grimms-The-White-Snake.txt",
]

Das Feature ist derzeit in Java nicht verfügbar.

Laden Sie diese Dateien jetzt hoch, und fügen Sie sie zum Vector Store hinzu, indem Sie die zuvor erstellten VectorStoreClient Clients verwenden, um jede Datei mit einer OpenAIFileClient hochzuladen und sie dem Vector Store hinzuzufügen, wobei die resultierenden Dateiverweise erhalten bleiben.

Dictionary<string, OpenAIFile> fileReferences = [];

Console.WriteLine("Uploading files...");
OpenAIFileClient fileClient = client.GetOpenAIFileClient();
foreach (string fileName in _fileNames)
{
    OpenAIFile fileInfo = await fileClient.UploadFileAsync(fileName, FileUploadPurpose.Assistants);
    await storeClient.AddFileToVectorStoreAsync(storeId, fileInfo.Id, waitUntilCompleted: true);
    fileReferences.Add(fileInfo.Id, fileInfo);
}

Das Feature ist derzeit in Java nicht verfügbar.

Wir werden das AzureOpenAIClient wieder als Teil der Erstellung des OpenAIAssistantAgent nutzen.

Console.WriteLine("Defining assistant...");
Assistant assistant =
    await assistantClient.CreateAssistantAsync(
        settings.AzureOpenAI.ChatModelDeployment,
        name: "SampleAssistantAgent",
        instructions:
                """
                The document store contains the text of fictional stories.
                Always analyze the document store to provide an answer to the user's question.
                Never rely on your knowledge of stories not included in the document store.
                Always format response using markdown.
                """,
        enableFileSearch: true,
        vectorStoreId: storeId);

// Create agent
OpenAIAssistantAgent agent = new(assistant, assistantClient);

# Create the assistant definition
definition = await client.beta.assistants.create(
    model=AzureOpenAISettings().chat_deployment_name,
    instructions="""
        The document store contains the text of fictional stories.
        Always analyze the document store to provide an answer to the user's question.
        Never rely on your knowledge of stories not included in the document store.
        Always format response using markdown.
        """,
    name="SampleAssistantAgent",
    tools=file_search_tools,
    tool_resources=file_search_tool_resources,
)

# Create the agent using the client and the assistant definition
agent = AzureAssistantAgent(
    client=client,
    definition=definition,
)

Das Feature ist derzeit in Java nicht verfügbar.

Console.WriteLine("Creating thread...");
OpenAIAssistantAgent agentThread = new();

Console.WriteLine("Ready!");

try
{
    bool isComplete = false;
    do
    {
        // Processing occurs here
    } while (!isComplete);
}
finally
{
    Console.WriteLine();
    Console.WriteLine("Cleaning-up...");
    await Task.WhenAll(
        [
            agentThread.DeleteAsync();
            assistantClient.DeleteAssistantAsync(assistant.Id),
            storeClient.DeleteVectorStoreAsync(storeId),
            ..fileReferences.Select(fileReference => fileClient.DeleteFileAsync(fileReference.Key))
        ]);
}

# If no thread is provided, a new thread will be
# created and returned with the initial response
thread: AssistantAgentThread = None

try:
    is_complete: bool = False
    while not is_complete:
        # Processing occurs here

finally:
    print("\nCleaning up resources...")
    [await client.files.delete(file_id) for file_id in file_ids]
    await client.vector_stores.delete(vector_store.id)
    await thread.delete() if thread else None
    await client.beta.assistants.delete(agent.id)

Das Feature ist derzeit in Java nicht verfügbar.

Console.WriteLine();
Console.Write("> ");
string input = Console.ReadLine();
if (string.IsNullOrWhiteSpace(input))
{
    continue;
}
if (input.Trim().Equals("EXIT", StringComparison.OrdinalIgnoreCase))
{
    isComplete = true;
    break;
}

var message = new ChatMessageContent(AuthorRole.User, input);
Console.WriteLine();

user_input = input("User:> ")
if not user_input:
    continue

if user_input.lower() == "exit":
    is_complete = True
    break

Das Feature ist derzeit in Java nicht verfügbar.

private static string ReplaceUnicodeBrackets(this string content) =>
    content?.Replace('【', '[').Replace('】', ']');

# No special handling required.

Das Feature ist derzeit in Java nicht verfügbar.

List<StreamingAnnotationContent> footnotes = [];
await foreach (StreamingChatMessageContent chunk in agent.InvokeStreamingAsync(message, agentThread))
{
    // Capture annotations for footnotes
    footnotes.AddRange(chunk.Items.OfType<StreamingAnnotationContent>());

    // Render chunk with replacements for unicode brackets.
    Console.Write(chunk.Content.ReplaceUnicodeBrackets());
}

Console.WriteLine();

// Render footnotes for captured annotations.
if (footnotes.Count > 0)
{
    Console.WriteLine();
    foreach (StreamingAnnotationContent footnote in footnotes)
    {
        Console.WriteLine($"#{footnote.Quote.ReplaceUnicodeBrackets()} - {fileReferences[footnote.FileId!].Filename} (Index: {footnote.StartIndex} - {footnote.EndIndex})");
    }
}

footnotes: list[StreamingAnnotationContent] = []
async for response in agent.invoke_stream(messages=user_input, thread=thread):
    thread = response.thread
    footnotes.extend([item for item in response.items if isinstance(item, StreamingAnnotationContent)])

    print(f"{response.content}", end="", flush=True)

print()

if len(footnotes) > 0:
    for footnote in footnotes:
        print(
            f"\n`{footnote.quote}` => {footnote.file_id} "
            f"(Index: {footnote.start_index} - {footnote.end_index})"
        )

Das Feature ist derzeit in Java nicht verfügbar.

using Azure.AI.OpenAI;
using Azure.Identity;
using Microsoft.SemanticKernel;
using Microsoft.SemanticKernel.Agents;
using Microsoft.SemanticKernel.Agents.OpenAI;
using Microsoft.SemanticKernel.ChatCompletion;
using OpenAI.Assistants;
using OpenAI.Files;
using OpenAI.VectorStores;
using System;
using System.Collections.Generic;
using System.Linq;
using System.Threading.Tasks;

namespace AgentsSample;

public static class Program
{
    private static readonly string[] _fileNames =
        [
            "Grimms-The-King-of-the-Golden-Mountain.txt",
            "Grimms-The-Water-of-Life.txt",
            "Grimms-The-White-Snake.txt",
        ];

    /// <summary>
    /// The main entry point for the application.
    /// </summary>
    /// <returns>A <see cref="Task"/> representing the asynchronous operation.</returns>
    public static async Task Main()
    {
        // Load configuration from environment variables or user secrets.
        Settings settings = new();

        // Initialize the clients
        AzureOpenAIClient client = OpenAIAssistantAgent.CreateAzureOpenAIClient(new AzureCliCredential(), new Uri(settings.AzureOpenAI.Endpoint));
        //OpenAIClient client = OpenAIAssistantAgent.CreateOpenAIClient(new ApiKeyCredential(settings.OpenAI.ApiKey)));
        AssistantClient assistantClient = client.GetAssistantClient();
        OpenAIFileClient fileClient = client.GetOpenAIFileClient();
        VectorStoreClient storeClient = client.GetVectorStoreClient();

        // Create the vector store
        Console.WriteLine("Creating store...");
        CreateVectorStoreOperation operation = await storeClient.CreateVectorStoreAsync(waitUntilCompleted: true);
        string storeId = operation.VectorStoreId;

        // Upload files and retain file references.
        Console.WriteLine("Uploading files...");
        Dictionary<string, OpenAIFile> fileReferences = [];
        foreach (string fileName in _fileNames)
        {
            OpenAIFile fileInfo = await fileClient.UploadFileAsync(fileName, FileUploadPurpose.Assistants);
            await storeClient.AddFileToVectorStoreAsync(storeId, fileInfo.Id, waitUntilCompleted: true);
            fileReferences.Add(fileInfo.Id, fileInfo);
        }

        // Define assistant
        Console.WriteLine("Defining assistant...");
        Assistant assistant =
            await assistantClient.CreateAssistantAsync(
                settings.AzureOpenAI.ChatModelDeployment,
                name: "SampleAssistantAgent",
                instructions:
                        """
                        The document store contains the text of fictional stories.
                        Always analyze the document store to provide an answer to the user's question.
                        Never rely on your knowledge of stories not included in the document store.
                        Always format response using markdown.
                        """,
                enableFileSearch: true,
                vectorStoreId: storeId);

        // Create agent
        OpenAIAssistantAgent agent = new(assistant, assistantClient);

        // Create the conversation thread
        Console.WriteLine("Creating thread...");
        AssistantAgentThread agentThread = new();

        Console.WriteLine("Ready!");

        try
        {
            bool isComplete = false;
            do
            {
                Console.WriteLine();
                Console.Write("> ");
                string input = Console.ReadLine();
                if (string.IsNullOrWhiteSpace(input))
                {
                    continue;
                }
                if (input.Trim().Equals("EXIT", StringComparison.OrdinalIgnoreCase))
                {
                    isComplete = true;
                    break;
                }

                var message = new ChatMessageContent(AuthorRole.User, input);
                Console.WriteLine();

                List<StreamingAnnotationContent> footnotes = [];
                await foreach (StreamingChatMessageContent chunk in agent.InvokeStreamingAsync(message, agentThread))
                {
                    // Capture annotations for footnotes
                    footnotes.AddRange(chunk.Items.OfType<StreamingAnnotationContent>());

                    // Render chunk with replacements for unicode brackets.
                    Console.Write(chunk.Content.ReplaceUnicodeBrackets());
                }

                Console.WriteLine();

                // Render footnotes for captured annotations.
                if (footnotes.Count > 0)
                {
                    Console.WriteLine();
                    foreach (StreamingAnnotationContent footnote in footnotes)
                    {
                        Console.WriteLine($"#{footnote.Quote.ReplaceUnicodeBrackets()} - {fileReferences[footnote.FileId!].Filename} (Index: {footnote.StartIndex} - {footnote.EndIndex})");
                    }
                }
            } while (!isComplete);
        }
        finally
        {
            Console.WriteLine();
            Console.WriteLine("Cleaning-up...");
            await Task.WhenAll(
                [
                    agentThread.DeleteAsync(),
                    assistantClient.DeleteAssistantAsync(assistant.Id),
                    storeClient.DeleteVectorStoreAsync(storeId),
                    ..fileReferences.Select(fileReference => fileClient.DeleteFileAsync(fileReference.Key))
                ]);
        }
    }

    private static string ReplaceUnicodeBrackets(this string content) =>
        content?.Replace('【', '[').Replace('】', ']');
}

# Copyright (c) Microsoft. All rights reserved.

import asyncio
import os

from semantic_kernel.agents import AssistantAgentThread, AzureAssistantAgent
from semantic_kernel.connectors.ai.open_ai import AzureOpenAISettings
from semantic_kernel.contents import StreamingAnnotationContent

"""
The following sample demonstrates how to create a simple,
OpenAI assistant agent that utilizes the vector store
to answer questions based on the uploaded documents.

This is the full code sample for the Semantic Kernel Learn Site: How-To: Open AI Assistant Agent File Search

https://learn.microsoft.com/semantic-kernel/frameworks/agent/examples/example-assistant-search?pivots=programming-language-python
"""


def get_filepath_for_filename(filename: str) -> str:
    base_directory = os.path.join(
        os.path.dirname(os.path.dirname(os.path.realpath(__file__))),
        "resources",
    )
    return os.path.join(base_directory, filename)


filenames = [
    "Grimms-The-King-of-the-Golden-Mountain.txt",
    "Grimms-The-Water-of-Life.txt",
    "Grimms-The-White-Snake.txt",
]


async def main():
    # Create the client using Azure OpenAI resources and configuration
    client = AzureAssistantAgent.create_client()

    # Upload the files to the client
    file_ids: list[str] = []
    for path in [get_filepath_for_filename(filename) for filename in filenames]:
        with open(path, "rb") as file:
            file = await client.files.create(file=file, purpose="assistants")
            file_ids.append(file.id)

    vector_store = await client.vector_stores.create(
        name="assistant_search",
        file_ids=file_ids,
    )

    # Get the file search tool and resources
    file_search_tools, file_search_tool_resources = AzureAssistantAgent.configure_file_search_tool(
        vector_store_ids=vector_store.id
    )

    # Create the assistant definition
    definition = await client.beta.assistants.create(
        model=AzureOpenAISettings().chat_deployment_name,
        instructions="""
            The document store contains the text of fictional stories.
            Always analyze the document store to provide an answer to the user's question.
            Never rely on your knowledge of stories not included in the document store.
            Always format response using markdown.
            """,
        name="SampleAssistantAgent",
        tools=file_search_tools,
        tool_resources=file_search_tool_resources,
    )

    # Create the agent using the client and the assistant definition
    agent = AzureAssistantAgent(
        client=client,
        definition=definition,
    )

    thread: AssistantAgentThread | None = None

    try:
        is_complete: bool = False
        while not is_complete:
            user_input = input("User:> ")
            if not user_input:
                continue

            if user_input.lower() == "exit":
                is_complete = True
                break

            footnotes: list[StreamingAnnotationContent] = []
            async for response in agent.invoke_stream(messages=user_input, thread=thread):
                footnotes.extend([item for item in response.items if isinstance(item, StreamingAnnotationContent)])

                print(f"{response.content}", end="", flush=True)
                thread = response.thread

            print()

            if len(footnotes) > 0:
                for footnote in footnotes:
                    print(
                        f"\n`{footnote.quote}` => {footnote.file_id} "
                        f"(Index: {footnote.start_index} - {footnote.end_index})"
                    )

    finally:
        print("\nCleaning up resources...")
        [await client.files.delete(file_id) for file_id in file_ids]
        await client.vector_stores.delete(vector_store.id)
        await thread.delete() if thread else None
        await client.beta.assistants.delete(agent.id)


if __name__ == "__main__":
    asyncio.run(main())

Möglicherweise finden Sie den vollständigen Code, wie oben gezeigt, in unserem Repository.

Das Feature ist derzeit in Java nicht verfügbar.