Usar a ferramenta de geração de imagem (versão prévia)

Criar um agente com a ferramenta de geração de imagem

Este exemplo cria um agente com a ferramenta de geração de imagem, gera uma imagem e a salva em um arquivo.

import base64
import os

from azure.identity import DefaultAzureCredential
from azure.ai.projects import AIProjectClient
from azure.ai.projects.models import PromptAgentDefinition, ImageGenTool

# Format: "https://resource_name.ai.azure.com/api/projects/project_name"
PROJECT_ENDPOINT = "your_project_endpoint"
IMAGE_MODEL = "gpt-image-1"

# Create clients to call Foundry API
project = AIProjectClient(
    endpoint=PROJECT_ENDPOINT,
    credential=DefaultAzureCredential(),
)
openai = project.get_openai_client()

# Create an agent with the image generation tool
agent = project.agents.create_version(
    agent_name="agent-image-generation",
    definition=PromptAgentDefinition(
        model="gpt-4.1-mini",
        instructions="Generate images based on user prompts.",
        tools=[ImageGenTool(model=IMAGE_MODEL, quality="low", size="1024x1024")],
    ),
    description="Agent for image generation.",
)
print(f"Agent created (id: {agent.id}, name: {agent.name}, version: {agent.version})")

# Generate an image using the agent
response = openai.responses.create(
    input="Generate an image of the Microsoft logo.",
    extra_headers={
        "x-ms-oai-image-generation-deployment": IMAGE_MODEL,
    },
    extra_body={"agent_reference": {"name": agent.name, "type": "agent_reference"}},
)

# Clean up the agent
project.agents.delete_version(agent_name=agent.name, agent_version=agent.version)

# Extract and save the generated image
image_data = [output.result for output in response.output if output.type == "image_generation_call"]
if image_data and image_data[0]:
    file_path = os.path.abspath("microsoft.png")
    with open(file_path, "wb") as f:
        f.write(base64.b64decode(image_data[0]))
    print(f"Image saved to: {file_path}")

Exemplo de geração de imagem em Azure. IA. Extensions.OpenAI

Neste exemplo, você gera uma imagem com base em um prompt simples. O código neste exemplo é síncrono. Para obter um exemplo assíncrono, consulte o exemplo sample code no SDK do Azure para .NET repositório no GitHub.

using System;
using Azure.AI.Projects;
using Azure.AI.Extensions.OpenAI;
using Azure.Identity;

// Format: "https://resource_name.ai.azure.com/api/projects/project_name"
var projectEndpoint = "your_project_endpoint";
var imageModel = "gpt-image-1";

// Create the AI Project client with custom header policy
AIProjectClientOptions projectOptions = new();
projectOptions.AddPolicy(new HeaderPolicy(imageModel), PipelinePosition.PerCall);

// Create the AI Project client
AIProjectClient projectClient = new(
    endpoint: new Uri(projectEndpoint),
    tokenProvider: new DefaultAzureCredential(),
    options: projectOptions
);

// Use the client to create the versioned agent object.
// To generate images, we need to provide agent with the ImageGenerationTool
// when creating this tool. The ImageGenerationTool parameters include
// the image generation model, image quality and resolution.
// Supported image generation models include gpt-image-1.
DeclarativeAgentDefinition agentDefinition = new(model: "gpt-4.1-mini")
{
Instructions = "Generate images based on user prompts.",
Tools = {
        ResponseTool.CreateImageGenerationTool(
            model: imageModel,
            quality: ImageGenerationToolQuality.Low,
            size:ImageGenerationToolSize.W1024xH1024
        )
    }
};
AgentVersion agentVersion = projectClient.AgentAdministrationClient.CreateAgentVersion(
    agentName: "myAgent",
    options: new(agentDefinition));

ProjectOpenAIClient openAIClient = projectClient.GetProjectOpenAIClient();
ProjectResponsesClient responseClient = openAIClient.GetProjectResponsesClientForAgent(new AgentReference(name: agentVersion.Name));

ResponseResult response = responseClient.CreateResponse("Generate parody of Newton with apple.");

// Parse the ResponseResult object and save the generated image.
foreach (ResponseItem item in response.OutputItems)
{
    if (item is ImageGenerationCallResponseItem imageItem)
    {
        File.WriteAllBytes("newton.png", imageItem.ImageResultBytes.ToArray());
        Console.WriteLine($"Image downloaded and saved to: {Path.GetFullPath("newton.png")}");
    }
}

// Clean up resources by deleting the Agent.
projectClient.AgentAdministrationClient.DeleteAgentVersion(agentName: agentVersion.Name, agentVersion: agentVersion.Version);

// To use image generation, provide the custom header to web requests,
// which contain the model deployment name, for example:
// `x-ms-oai-image-generation-deployment: gpt-image-1`.
// To implement it, create a custom header policy.
internal class HeaderPolicy(string image_deployment) : PipelinePolicy
{
    private const string image_deployment_header = "x-ms-oai-image-generation-deployment";

    public override void Process(PipelineMessage message, IReadOnlyList<PipelinePolicy> pipeline, int currentIndex)
    {
        message.Request.Headers.Add(image_deployment_header, image_deployment);
        ProcessNext(message, pipeline, currentIndex);
    }

    public override async ValueTask ProcessAsync(PipelineMessage message, IReadOnlyList<PipelinePolicy> pipeline, int currentIndex)
    {
        // Add your desired header name and value
        message.Request.Headers.Add(image_deployment_header, image_deployment);
        await ProcessNextAsync(message, pipeline, currentIndex);
    }
}

Saída esperada

Ao executar o exemplo, você verá a seguinte saída:

Agent created (id: <agent-id>, name: myAgent, version: 1)
Image downloaded and saved to: /path/to/newton.png
Agent deleted

Criar um agente com a ferramenta de geração de imagem

Obtenha um token de acesso:

export AGENT_TOKEN=$(az account get-access-token --scope "https://ai.azure.com/.default" --query accessToken -o tsv)

O exemplo a seguir cria um agente que usa a ferramenta de geração de imagem.

curl -X POST "$FOUNDRY_PROJECT_ENDPOINT/agents?api-version=v1" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AGENT_TOKEN" \
  -d '{
    "name": "image-gen-agent",
    "description": "Test agent for image generation capabilities",
    "definition": {
      "kind": "prompt",
      "model": "'$FOUNDRY_MODEL_DEPLOYMENT_NAME'",
      "tools": [
        {
          "type": "image_generation"
        }
      ],
      "instructions": "You are a creative assistant that generates images when requested. Please respond to image generation requests clearly and concisely."
    }
  }'

Criar uma resposta

curl -X POST "$FOUNDRY_PROJECT_ENDPOINT/openai/v1/responses" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AGENT_TOKEN" \
  -H "x-ms-oai-image-generation-deployment: $IMAGE_GENERATION_MODEL_DEPLOYMENT_NAME" \
  -d '{
    "agent": {
      "type": "agent_reference",
      "name": "image-gen-agent"
    },
    "input": [{
      "type": "message",
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "Please generate small image of a sunset over a mountain lake."
        }
      ]
    }],
    "stream": false
  }'

Saída esperada

O JSON de resposta inclui um image_generation_call item de saída com um result campo que contém dados de imagem codificados em base64:

{
  "id": "resp_<id>",
  "status": "completed",
  "output": [
    {
      "type": "image_generation_call",
      "result": "<base64-encoded-image-data>",
      "status": "completed"
    },
    {
      "type": "message",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "Here is the image of a sunset over a mountain lake."
        }
      ]
    }
  ]
}

Para extrair e salvar a imagem, encaminhe a resposta através de jq e base64:

RESPONSE=$(curl -s -X POST "$FOUNDRY_PROJECT_ENDPOINT/openai/v1/responses" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AGENT_TOKEN" \
  -H "x-ms-oai-image-generation-deployment: $IMAGE_GENERATION_MODEL_DEPLOYMENT_NAME" \
  -d '{ ... }')

echo "$RESPONSE" | jq -r '.output[] | select(.type=="image_generation_call") | .result' \
  | base64 --decode > generated_image.png

Criar um agente com a ferramenta de geração de imagem

Este exemplo demonstra como criar um agente de IA com recursos de geração de imagem usando o cliente Azure projetos de IA. O agente gera imagens com base em prompts de texto e as salva em arquivos. Para obter um exemplo de JavaScript, consulte o código sample no repositório SDK do Azure para JavaScript em GitHub.

import { DefaultAzureCredential } from "@azure/identity";
import { AIProjectClient } from "@azure/ai-projects";
import * as fs from "fs";
import * as path from "path";
import { fileURLToPath } from "url";

// Format: "https://resource_name.ai.azure.com/api/projects/project_name"
const PROJECT_ENDPOINT = "your_project_endpoint";
const IMAGE_MODEL = "gpt-image-1";

export async function main(): Promise<void> {
  // Create clients to call Foundry API
  const project = new AIProjectClient(PROJECT_ENDPOINT, new DefaultAzureCredential());
  const openai = project.getOpenAIClient();

  // Create Agent with image generation tool
  const agent = await project.agents.createVersion("agent-image-generation", {
    kind: "prompt",
    model: "gpt-4.1-mini",
    instructions: "Generate images based on user prompts",
    tools: [
      {
        type: "image_generation",
        quality: "low",
        size: "1024x1024",
      },
    ],
  });
  console.log(`Agent created (id: ${agent.id}, name: ${agent.name}, version: ${agent.version})`);

  // Generate image using the agent
  const response = await openai.responses.create(
    {
      input: "Generate an image of Microsoft logo.",
    },
    {
      body: { agent: { name: agent.name, type: "agent_reference" } },
      headers: { "x-ms-oai-image-generation-deployment": IMAGE_MODEL },
    },
  );

  // Extract and save the generated image
  const imageData = response.output?.filter((output) => output.type === "image_generation_call");

  if (imageData && imageData.length > 0 && imageData[0].result) {
    const __filename = fileURLToPath(import.meta.url);
    const __dirname = path.dirname(__filename);
    const filename = "microsoft.png";
    const filePath = path.join(__dirname, filename);

    // Decode base64 and save to file
    const imageBuffer = Buffer.from(imageData[0].result, "base64");
    fs.writeFileSync(filePath, imageBuffer);

    console.log(`Image downloaded and saved to: ${path.resolve(filePath)}`);
  } else {
    console.log("No image data found in the response.");
  }

  // Clean up resources
  await project.agents.deleteVersion(agent.name, agent.version);
}

main().catch((err) => {
  console.error("The sample encountered an error:", err);
});

Saída esperada

Ao executar o exemplo, você verá a seguinte saída:

Agent created (id: <agent-id>, name: agent-image-generation, version: 1)
Image downloaded and saved to: /path/to/microsoft.png

Usar a geração de imagem em um agente de Java

Adicione a dependência ao seu pom.xml:

<dependency>
    <groupId>com.azure</groupId>
    <artifactId>azure-ai-agents</artifactId>
    <version>2.0.0</version>
</dependency>

Criar um agente com geração de imagem

import com.azure.ai.agents.AgentsClient;
import com.azure.ai.agents.AgentsClientBuilder;
import com.azure.ai.agents.ResponsesClient;
import com.azure.ai.agents.models.*;
import com.azure.identity.DefaultAzureCredentialBuilder;
import com.openai.models.responses.Response;
import com.openai.models.responses.ResponseCreateParams;

import java.util.Collections;

public class ImageGenerationExample {
    public static void main(String[] args) {
        // Format: "https://resource_name.ai.azure.com/api/projects/project_name"
        String projectEndpoint = "your_project_endpoint";
        String imageModel = "gpt-image-1";

        AgentsClientBuilder builder = new AgentsClientBuilder()
            .credential(new DefaultAzureCredentialBuilder().build())
            .endpoint(projectEndpoint);

        AgentsClient agentsClient = builder.buildAgentsClient();
        ResponsesClient responsesClient = builder.buildResponsesClient();

        // Create image generation tool with model, quality, and size
        ImageGenTool imageGenTool = new ImageGenTool()
            .setModel(ImageGenToolModel.fromString(imageModel))
            .setQuality(ImageGenToolQuality.LOW)
            .setSize(ImageGenToolSize.fromString("1024x1024"));

        // Create agent with image generation tool
        PromptAgentDefinition agentDefinition = new PromptAgentDefinition("gpt-4.1-mini")
            .setInstructions("You are a creative assistant that can generate images based on descriptions.")
            .setTools(Collections.singletonList(imageGenTool));

        AgentVersionDetails agent = agentsClient.createAgentVersion("image-gen-agent", agentDefinition);
        System.out.printf("Agent created: %s (version %s)%n", agent.getName(), agent.getVersion());

        // Create a response
        AgentReference agentReference = new AgentReference(agent.getName())
            .setVersion(agent.getVersion());

        Response response = responsesClient.createAzureResponse(
            new AzureCreateResponseOptions().setAgentReference(agentReference),
            ResponseCreateParams.builder()
                .input("Generate an image of a sunset over a mountain range"));

        // The response output includes image_generation_call items with base64-encoded image data.
        // Extract and save the image using the response output items.
        System.out.println("Response status: " + response.status().map(Object::toString).orElse("unknown"));
        System.out.println("Output items: " + response.output().size());

        // Clean up
        agentsClient.deleteAgentVersion(agent.getName(), agent.getVersion());
    }
}

Saída esperada

Agent created: image-gen-agent (version 1)
Response status: completed
Output items: 2