feat: support async generate images

core/src/main/java/ai/z/openapi/api/chat/ChatApi.java

@@ -15,23 +15,20 @@
 import java.util.Map;
 
 /**
- * Chat Completions API for advanced GLM-4 series models Provides synchronous,
- * asynchronous, and streaming chat completion capabilities Supports complex reasoning,
- * long context processing (up to 128K tokens), and ultra-fast inference Features
- * GLM-4-Plus, GLM-4-Air, GLM-4-Flash, and GLM-4-AllTools with specialized capabilities
- * Optimized for Chinese and multilingual conversations with superior performance
+ * Chat Completions API for advanced GLM series models Provides synchronous, asynchronous,
+ * and streaming chat completion capabilities Supports complex reasoning, long context
+ * processing and ultra-fast inference Features
  */
 public interface ChatApi {
 
 	/**
 	 * Create a streaming chat completion with real-time response Returns response content
 	 * incrementally through Server-Sent Events (SSE) for immediate user feedback
 	 * Optimized for interactive applications requiring low latency and progressive
-	 * content delivery Supports all GLM-4 models with configurable streaming parameters
-	 * and token-by-token generation
-	 * @param request Chat completion parameters including model selection (glm-4-plus,
-	 * glm-4-air, glm-4-flash), messages, temperature, top_p, max_tokens, and streaming
-	 * settings
+	 * content delivery Supports all GLM models with configurable streaming parameters and
+	 * token-by-token generation
+	 * @param request Chat completion parameters including model selection messages,
+	 * temperature, top_p, max_tokens, and streaming settings
 	 * @return Streaming response body with incremental content, usage statistics, and
 	 * completion indicators
 	 */
@@ -43,8 +40,8 @@ public interface ChatApi {
 	 * Create a streaming chat completion with custom headers support Returns response
 	 * content incrementally through Server-Sent Events (SSE) for immediate user feedback
 	 * Optimized for interactive applications requiring low latency and progressive
-	 * content delivery Supports all GLM-4 models with configurable streaming parameters
-	 * and custom HTTP headers
+	 * content delivery Supports all GLM models with configurable streaming parameters and
+	 * custom HTTP headers
 	 * @param request Chat completion parameters including model selection, messages, and
 	 * streaming settings
 	 * @param headers Custom HTTP headers to be added to the request
@@ -70,7 +67,7 @@ Call<ResponseBody> createChatCompletionStream(@Body ChatCompletionCreateParams r
 	Single<ModelData> createChatCompletionAsync(@Body ChatCompletionCreateParams request);
 
 	/**
-	 * Create a synchronous chat completion with immediate response Waits for the GLM-4
+	 * Create a synchronous chat completion with immediate response Waits for the GLM
 	 * model to complete execution and returns the final result Supports complex
 	 * reasoning, tool calling, function execution, and multi-modal understanding Features
 	 * advanced capabilities like web search integration, code interpretation, and image
@@ -85,11 +82,11 @@ Call<ResponseBody> createChatCompletionStream(@Body ChatCompletionCreateParams r
 	Single<ModelData> createChatCompletion(@Body ChatCompletionCreateParams request);
 
 	/**
-	 * Create a synchronous chat completion with custom headers support Waits for the
-	 * GLM-4 model to complete execution and returns the final result with custom HTTP
-	 * headers Supports complex reasoning, tool calling, function execution, and
-	 * multi-modal understanding Features advanced capabilities like web search
-	 * integration, code interpretation, and image analysis
+	 * Create a synchronous chat completion with custom headers support Waits for the GLM
+	 * models to complete execution and returns the final result with custom HTTP headers
+	 * Supports complex reasoning, tool calling, function execution, and multi-modal
+	 * understanding Features advanced capabilities like web search integration, code
+	 * interpretation, and image analysis
 	 * @param request Chat completion parameters including model selection, conversation
 	 * messages, generation settings, tools configuration, and response format
 	 * @param headers Custom HTTP headers to be added to the request

core/src/main/java/ai/z/openapi/api/images/ImagesApi.java

@@ -1,17 +1,20 @@
 package ai.z.openapi.api.images;
 
+import ai.z.openapi.service.image.AsyncImageResult;
 import ai.z.openapi.service.image.CreateImageRequest;
 import ai.z.openapi.service.image.ImageResult;
 import io.reactivex.rxjava3.core.Single;
 import retrofit2.http.Body;
+import retrofit2.http.GET;
 import retrofit2.http.POST;
+import retrofit2.http.Path;
 
 /**
- * Images API for AI-powered image generation Powered by CogView-3-Plus models using
- * advanced Transformer architecture Delivers high-quality text-to-image generation with
- * performance comparable to industry leaders Features optimized diffusion model with
- * enhanced noise planning for superior image quality Supports various image styles,
- * sizes, and generation parameters with Chinese text rendering capabilities
+ * Images API for AI-powered image generation models using advanced Transformer
+ * architecture Delivers high-quality text-to-image generation with performance comparable
+ * to industry leaders Features optimized diffusion model with enhanced noise planning for
+ * superior image quality Supports various image styles, sizes, and generation parameters
+ * with Chinese text rendering capabilities
  */
 public interface ImagesApi {
 
@@ -28,4 +31,23 @@ public interface ImagesApi {
 	@POST("images/generations")
 	Single<ImageResult> createImage(@Body CreateImageRequest request);
 
+	/**
+	 * Asynchronously generate images from text prompts. Submits an image generation task
+	 * and returns immediately with a task ID. Use queryAsyncResult to poll for completion
+	 * status and retrieve results.
+	 * @param request Image generation parameters including prompt, size, style, quality,
+	 * and model selection
+	 * @return Async task information including task ID and initial status
+	 */
+	@POST("async/images/generations")
+	Single<AsyncImageResult> createImageAsync(@Body CreateImageRequest request);
+
+	/**
+	 * Query the status and result of an async image generation task.
+	 * @param id The async task ID returned by createImageAsync
+	 * @return Task status and generated image URLs when completed
+	 */
+	@GET("async-result/{id}")
+	Single<AsyncImageResult> queryAsyncResult(@Path("id") String id);
+
 }

core/src/main/java/ai/z/openapi/api/videos/VideosApi.java

@@ -9,7 +9,7 @@
 import retrofit2.http.Path;
 
 /**
- * Videos API for AI-powered video generation Powered by CogVideoX models using advanced
+ * Videos API for AI-powered video generation Powered by CogVideo models using advanced
  * Transformer and 3D Causal VAE architecture Supports both text-to-video and
  * image-to-video generation with exceptional quality Features natural camera movements,
  * semantic coherence, and photorealistic visual output Configurable parameters include

core/src/main/java/ai/z/openapi/service/image/AsyncImageResponse.java

@@ -0,0 +1,39 @@
+package ai.z.openapi.service.image;
+
+import ai.z.openapi.core.model.ClientResponse;
+import ai.z.openapi.service.model.ChatError;
+import lombok.Data;
+
+/**
+ * Response wrapper for async image generation API calls. Contains the result of async
+ * image generation operations along with status information.
+ */
+@Data
+public class AsyncImageResponse implements ClientResponse<AsyncImageResult> {
+
+	/**
+	 * Response status code.
+	 */
+	private int code;
+
+	/**
+	 * Response message.
+	 */
+	private String msg;
+
+	/**
+	 * Indicates whether the request was successful.
+	 */
+	private boolean success;
+
+	/**
+	 * The async image generation result data.
+	 */
+	private AsyncImageResult data;
+
+	/**
+	 * Error information if the request failed.
+	 */
+	private ChatError error;
+
+}

core/src/main/java/ai/z/openapi/service/image/AsyncImageResult.java

@@ -0,0 +1,53 @@
+package ai.z.openapi.service.image;
+
+import com.fasterxml.jackson.annotation.JsonFormat;
+import com.fasterxml.jackson.annotation.JsonProperty;
+import lombok.AllArgsConstructor;
+import lombok.Builder;
+import lombok.Data;
+import lombok.NoArgsConstructor;
+
+import java.util.List;
+
+/**
+ * Result object for async image generation API. Contains task status and image results
+ * when completed.
+ */
+@Data
+@NoArgsConstructor
+@AllArgsConstructor
+@Builder
+public class AsyncImageResult {
+
+	/**
+	 * The unique identifier for the async task.
+	 */
+	@JsonProperty("id")
+	private String id;
+
+	/**
+	 * The model used for image generation.
+	 */
+	@JsonProperty("model")
+	private String model;
+
+	/**
+	 * The request ID for tracking.
+	 */
+	@JsonProperty("request_id")
+	private String requestId;
+
+	/**
+	 * The status of the async task. Possible values: PROCESSING, SUCCESS, FAIL
+	 */
+	@JsonProperty("task_status")
+	private String taskStatus;
+
+	/**
+	 * List of generated images. Available when task_status is SUCCESS.
+	 */
+	@JsonProperty("image_result")
+	@JsonFormat(with = JsonFormat.Feature.ACCEPT_SINGLE_VALUE_AS_ARRAY)
+	private List<Image> imageResult;
+
+}

core/src/main/java/ai/z/openapi/service/image/CreateImageRequest.java

@@ -12,8 +12,7 @@
 import lombok.experimental.SuperBuilder;
 
 /**
- * A request for ZAi to create an image based on a prompt All fields except prompt are
- * optional
+ * A request to create an image based on a prompt All fields except prompt are optional
  */
 @EqualsAndHashCode(callSuper = true)
 @SuperBuilder
@@ -29,15 +28,23 @@ public class CreateImageRequest extends CommonRequest implements ClientRequest<C
 	private String prompt;
 
 	/**
-	 * The model to use for image generation. Defaults to "dall-e-2".
+	 * The model to use for image generation.
 	 */
 	private String model;
 
 	/**
-	 * The size of the image to generate. Defaults to "256x256".
+	 * The size of the image to generate.
 	 */
 	private String size;
 
+	/**
+	 * Optional. The quality of the generated image. hd: Generates more refined images
+	 * with richer details and higher overall consistency, but takes longer. standard:
+	 * Quickly generates images, suitable for scenarios with high speed requirements,
+	 * takes less time.
+	 */
+	private String quality;
+
 	/**
 	 * Sensitive word detection control
 	 */

core/src/main/java/ai/z/openapi/service/image/ImageService.java

@@ -12,4 +12,19 @@ public interface ImageService {
 	 */
 	ImageResponse createImage(CreateImageRequest createImageRequest);
 
+	/**
+	 * Asynchronously creates an image based on the provided generation request. Returns
+	 * immediately with a task ID that can be used to query the status.
+	 * @param createImageRequest the image generation request
+	 * @return AsyncImageResponse containing the task ID and initial status
+	 */
+	AsyncImageResponse createImageAsync(CreateImageRequest createImageRequest);
+
+	/**
+	 * Queries the status and result of an async image generation task.
+	 * @param taskId the async task ID returned by createImageAsync
+	 * @return AsyncImageResponse containing task status and results when completed
+	 */
+	AsyncImageResponse queryAsyncResult(String taskId);
+
 }

core/src/main/java/ai/z/openapi/service/image/ImageServiceImpl.java

@@ -2,6 +2,7 @@
 
 import ai.z.openapi.AbstractAiClient;
 import ai.z.openapi.api.images.ImagesApi;
+import ai.z.openapi.service.model.AsyncResultRetrieveParams;
 import ai.z.openapi.utils.RequestSupplier;
 
 /**
@@ -24,4 +25,18 @@ public ImageResponse createImage(CreateImageRequest createImageRequest) {
 		return this.zAiClient.executeRequest(createImageRequest, supplier, ImageResponse.class);
 	}
 
+	@Override
+	public AsyncImageResponse createImageAsync(CreateImageRequest createImageRequest) {
+		RequestSupplier<CreateImageRequest, AsyncImageResult> supplier = imagesApi::createImageAsync;
+		return this.zAiClient.executeRequest(createImageRequest, supplier, AsyncImageResponse.class);
+	}
+
+	@Override
+	public AsyncImageResponse queryAsyncResult(String taskId) {
+		AsyncResultRetrieveParams request = new AsyncResultRetrieveParams(taskId);
+		RequestSupplier<AsyncResultRetrieveParams, AsyncImageResult> supplier = (params) -> imagesApi
+			.queryAsyncResult(params.getTaskId());
+		return zAiClient.executeRequest(request, supplier, AsyncImageResponse.class);
+	}
+
 }

core/src/main/java/ai/z/openapi/service/model/ChatFunction.java

@@ -15,6 +15,10 @@ public class ChatFunction {
 
 	private String description;
 
-	private ChatFunctionParameters parameters;
+	/**
+	 * The JSON schema defining the function's input arguments, you can use the
+	 * ChatFunctionParameters or others
+	 */
+	private Object parameters;
 
 }

pom.xml

@@ -45,7 +45,7 @@
     </scm>
 
     <properties>
-        <revision>0.3.0</revision>
+        <revision>0.3.1</revision>
         <java.version>8</java.version>
         <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
         <project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>

samples/src/main/ai.z.openapi.samples/ImageGenerationAsyncExample.java

@@ -0,0 +1,49 @@
+package ai.z.openapi.samples;
+
+import ai.z.openapi.ZaiClient;
+import ai.z.openapi.service.image.AsyncImageResponse;
+import ai.z.openapi.service.image.CreateImageRequest;
+
+/**
+ * Images Example
+ * Demonstrates how to use ZaiClient to generate async image
+ */
+public class ImageGenerationAsyncExample {
+
+    public static void main(String[] args) {
+        // Create client, recommended to set API Key via environment variable
+        // export ZAI_API_KEY=your.api_key
+        // for Z.ai use the `ZaiClient`, for Zhipu AI use the ZhipuAiClient.builder().ofZHIPU().build()
+        ZaiClient client = ZaiClient.builder().baseUrl("https://dev.bigmodel.cn/api/paas/v4/").apiKey("08d9c717e10a4dbc8bd3963cb70aafe0.ZAMAdBKwQsrlAbcZ").build();
+
+        generateAsyncImage(client);
+        client.close();
+    }
+
+    private static void generateAsyncImage(ZaiClient client) {
+        System.out.println("\n=== Basic Images Generation Example ===");
+
+        // Create image generation request
+        CreateImageRequest request = CreateImageRequest.builder()
+            .model("glm-image")
+            .prompt("A beautiful sunset over mountains, digital art style")
+            .size("1024x1024")
+            .quality("hd")
+            .build();
+
+        try {
+            // Execute request
+            AsyncImageResponse response = client.images().createImageAsync(request);
+            System.out.println("Response 1: " + response.getData());
+            String taskId = response.getData().getId();
+            response = client.images().queryAsyncResult(taskId);
+            System.out.println("Response 2: " + response.getData());
+            Thread.sleep(40000);
+            response = client.images().queryAsyncResult(taskId);
+            System.out.println("Response 3: " + response.getData());
+        } catch (Exception e) {
+            System.err.println("Exception occurred: " + e.getMessage());
+            e.printStackTrace();
+        }
+    }
+}