📝 Update README.md and examples to reflect Flux 2 support

Author: MrGraversen

README.md

@@ -2,19 +2,24 @@
 
 Welcome to the [**Replicate AI**](https://replicate.com/) Integration project! 🎉
 
-This project provides a streamlined Java 21-based framework to effortlessly interact with and create predictions for **Replicate**'s
-powerful AI models. Built with **Spring Boot**, it enables quick and modular access to various AI services, making integration a breeze for
+This project provides a streamlined Java 21-based framework to effortlessly interact with and create predictions for *
+*Replicate**'s
+powerful AI models. Built with **Spring Boot**, it enables quick and modular access to various AI services, making
+integration a breeze for
 developers.
 
-The project allows downloading of **Replicate AI** models' JSONSchemas for requests and responses through the official API, and dynamically
+The project allows downloading of **Replicate AI** models' JSONSchemas for requests and responses through the official
+API, and dynamically
 creates a Maven module to enable developers to interact with the AI models using strongly typed Java code.
 
-Furthermore, it supports **Spring Boot AutoConfiguration**, allowing efficient and powerful integration with Spring Boot applications to
+Furthermore, it supports **Spring Boot AutoConfiguration**, allowing efficient and powerful integration with Spring Boot
+applications to
 enable easy access to **Replicate**'s AI offerings—just add your API key!
 
 ## 🚀 Quick Start
 
-The quickest way to get off the ground is depending on `spring-boot-starter-replicate`. The module, provided an API key to Replicate,
+The quickest way to get off the ground is depending on `spring-boot-starter-replicate`. The module, provided an API key
+to Replicate,
 handles all configuration of the underlying modules to ensure a smooth start.
 
 ```xml
@@ -37,28 +42,22 @@ replicate:
 
 ## Replicate Models
 
-By default, this project supports a number of common AI models for text completion using large language models and text-to-image models for
+By default, this project supports a number of common AI models for text completion using large language models and
+text-to-image models for
 image generation. Specifically, the following models are currently supported out of the box:
 
-### Meta Llama 3
-
-* [`meta-llama-3-8b-instruct`](https://replicate.com/meta/meta-llama-3-8b-instruct)
-* [`meta-llama-3-70b-instruct`](https://replicate.com/meta/meta-llama-3-70b-instruct)
-* [`meta-llama-3.1-405b-instruct`](https://replicate.com/meta/meta-llama-3.1-405b-instruct)
-
-For the Llama 3 family of models, tokenization for text completion is supported by `spring-boot-starter-replicate`, making it easy to
-create and maintain stateful conversations.
-
 ### Black Forest Labs Flux
 
-* [`flux-dev`](https://replicate.com/black-forest-labs/flux-dev)
-* [`flux-schnell`](https://replicate.com/black-forest-labs/flux-schnell)
-* [`flux-pro`](https://replicate.com/black-forest-labs/flux-pro)
+* [`flux-2-dev`](https://replicate.com/black-forest-labs/flux-2-dev)
+* [`flux-2-flex`](https://replicate.com/black-forest-labs/flux-2-flex)
+* [`flux-2-pro`](https://replicate.com/black-forest-labs/flux-2-pro)
+* [`flux-2-max`](https://replicate.com/black-forest-labs/flux-2-max)
 
 ---
 
 > [!TIP]
-> It is possible to build this project to support different AI models that are not included by default for simplicity reasons.
+> It is possible to build this project to support different AI models that are not included by default for simplicity
+> reasons.
 > Please see the section describing the `replicate-tools` module.
 
 ## 📂 Module Overview
@@ -67,18 +66,22 @@ Below is a more focused description regarding each discrete module of this proje
 
 ### `replicate-client`
 
-Core module for handling API requests and responses from **Replicate**. Use this if you only want to create predictions with Java code in
+Core module for handling API requests and responses from **Replicate**. Use this if you only want to create predictions
+with Java code in
 the simplest possible manner.
 
 ### `replicate-models`
 
-Auto-generated models from **Replicate**’s JSONSchemas, providing strongly typed Java interfaces for AI models. The models supported are
+Auto-generated models from **Replicate**’s JSONSchemas, providing strongly typed Java interfaces for AI models. The
+models supported are
 generated using `replicate-tools`. From this repository, the following packages are supported:
 
-* [`default`](https://github.com/MrGraversen/replicate-java/packages/2297525?version=0.0.8-default): Default models as described above.
-* [`llama3`](https://github.com/MrGraversen/replicate-java/packages/2297525?version=0.0.8-llama3): A specialised module consisting only of
-  the Llama 3 family of AI models.
-* [`flux`](https://github.com/MrGraversen/replicate-java/packages/2297525?version=0.0.8-flux): A specialised module consisting only of the
+* [`default`](https://github.com/MrGraversen/replicate-java/packages/2297525?version=0.0.8-default): Default models as
+  described above.
+* [`openai`](https://github.com/MrGraversen/replicate-java/packages/2297525?version=0.0.8-openai): A specialized module
+  consisting only of OpenAI models.
+* [`flux`](https://github.com/MrGraversen/replicate-java/packages/2297525?version=0.0.8-flux): A specialized module
+  consisting only of the
   Flux family of AI models.
 
 ### `replicate-tools`
@@ -111,100 +114,48 @@ mvn compile
 ```
 
 > [!TIP]
-> If you decide to use AI models that are more complex than simple text completion or text-to-image generators, note that you may depend on
-> just `replicate-client` and `replicate-models` with your custom set of models, to enable easy, strongly typed access to the Replicate API.
+> If you decide to use AI models that are more complex than simple text completion or text-to-image generators, note
+> that you may depend on
+> just `replicate-client` and `replicate-models` with your custom set of models, to enable easy, strongly typed access
+> to the Replicate API.
 
 ### `spring-boot-starter-replicate`
 
-Auto-configures **Replicate** integration, provided an API token. Through this, you will have access to more advanced encapsulations to
+Auto-configures **Replicate** integration, provided an API token. Through this, you will have access to more advanced
+encapsulations to
 create images and manage conversations.
 
 ## 📈 Examples
 
-### Example 1 - Conversations with Llama 3
+### Example – Image generation with Flux 2 Pro
 
 ```java
 
 @Slf4j
+@Component
 @RequiredArgsConstructor
-public class LlamaConversationExample {
-    private final ConversationFacade conversationFacade;
-
-    /**
-     * Simple example of exchanging one message with meta-llama-3-70b-instruct
-     */
-    public void runExampleOne() {
-        final var conversationOptions = new ConversationOptions(
-                1.25 // temperature
-        );
-
-        final var createConversation = new CreateConversation(
-                "You are a friendly and witty assistant! Respond in one short sentence only.", // systemMessage
-                Llama3Models.LLAMA_3_70B_INSTRUCT // meta-llama-3-70b-instruct
-        );
-
-        final var conversation = conversationFacade.create(createConversation, conversationOptions);
-
-        conversationFacade.chat(conversation.getId(), TextMessage.user("Introduce yourself to me 😊")).whenComplete(logConversation());
-        // => I'm LLaMA, your go-to sidekick for banter, advice, and getting stuff done, with a healthy dose of sarcasm and humor! 😉
-    }
+public class Flux2Example {
+    private final ReplicateFacade replicateFacade;
 
     /**
-     * Example of exchanging a "deeper" conversation with meta-llama-3-70b-instruct
+     * Create one image using flux2-dev
      */
-    public void runExampleTwo() {
-        final var conversationOptions = new ConversationOptions(
-                0.75 // temperature
-        );
-
-        final var createConversation = new CreateConversation(
-                "You are a calculator app. Respond only with the result of the math query.", // systemMessage
-                Llama3Models.LLAMA_3_70B_INSTRUCT // meta-llama-3-70b-instruct
-        );
+    public void runExample() {
+        final var createImagePrediction = CreateImagePrediction2.builder()
+                .prompt("A photo of a happy sheep grazing on a beautiful summer day")
+                .aspectRatio(AspectRatios.RATIO_5_BY_4)
+                .build();
 
-        final var conversation = conversationFacade.create(createConversation, conversationOptions);
-
-        conversationFacade.chat(conversation.getId(), TextMessage.user("What is 2 + 2?")) // => 4
-                .thenCompose(conversationFacade.chat(TextMessage.user("What is 3 * 3?"))) // => 9
-                .thenCompose(conversationFacade.chat(TextMessage.user("What is seven minus two?"))) // => 5
-                .whenComplete(logConversation());
-    }
-
-    private BiConsumer<Conversation, Throwable> logConversation() {
-        return (conversation, throwable) -> {
-            if (throwable == null) {
-                log.info("{}", conversation.getConversation());
-            } else {
-                log.error(throwable.getMessage(), throwable);
-            }
-        };
+        replicateFacade.createPrediction(FluxModels.FLUX_2_PRO, createImagePrediction);
     }
-}
-```
-
-### Example 2 - Image generation with Flux
-
-```java
-
-@Slf4j
-@RequiredArgsConstructor
-public class FluxExample {
-    private final ReplicateFacade replicateFacade;
-
-    /**
-     * Create one image using flux-dev
-     */
-    public void runExampleOne() {
-        final var createImagePrediction = new CreateImagePrediction(
-                TextToImagePrompt.portrait("A photo of a sheep on a grassy field on a beautiful summer day"),
-                1, // outputs
-                25, // inferenceSteps
-                null // seed (random)
-        );
 
-        replicateFacade.createPrediction(
-                FluxModels.FLUX_DEV,
-                createImagePrediction
+    @EventListener(value = PredictionUpdatedEvent.class, condition = "#event.getStatus().name() == 'SUCCEEDED'")
+    public void onPredictionUpdated(PredictionUpdatedEvent event) {
+        log.info(
+                "Completed prediction '{}' with model '{}', view it here: {}",
+                event.getId(),
+                event.getModel(),
+                ReplicateUrl.fromPrediction(event.getId())
         );
     }
 }