Feat add generate builder

README.md

@@ -171,6 +171,50 @@ Then you can use the Model classes to run models:
  }
 ```
 
+Or you can use a **Flow API**:
+
+```java
+ public void sample() throws IOException {
+    String model = "tjake/Llama-3.2-1B-Instruct-JQ4";
+    String workingDirectory = "./models";
+
+    String prompt = "What is the best season to plant avocados?";
+
+    // Downloads the model or just returns the local path if it's already downloaded
+    File localModelPath = new Downloader(workingDirectory, model).huggingFaceModel();
+
+    // Loads the quantized model and specified use of quantized memory
+    AbstractModel m = ModelSupport.loadModel(localModelPath, DType.F32, DType.I8);
+
+    PromptContext ctx;
+    // Checks if the model supports chat prompting and adds prompt in the expected format for this model
+    if (m.promptSupport().isPresent()) {
+        ctx = m.promptSupport()
+                .get()
+                .builder()
+                .addSystemMessage("You are a helpful chatbot who writes short responses.")
+                .addUserMessage(prompt)
+                .build();
+    } else {
+        ctx = PromptContext.of(prompt);
+    }
+
+    System.out.println("Prompt: " + ctx.getPrompt() + "\n");
+    // Generates a response to the prompt and prints it
+    // The api allows for streaming or non-streaming responses
+    // The response is generated with a temperature of 0.7 and a max token length of 256
+    Generator.Response r = m.generateBuilder()
+            .session(UUID.randomUUID()) //By default, UUID.randomUUID()
+            .promptContext(ctx) // Required or use prompt(String text)
+            .ntokens(256) //By default, 256
+            .temperature(0.0f) //By default, 0.0f
+            .onTokenWithTimings((s, aFloat) -> {}) //By default, (s, aFloat) -> {}, nothing
+            .generate();
+
+    System.out.println(r.responseText);
+ }
+```
+
 ## ⭐ Give us a Star! 
 
 If you like or are using this project to build your own, please give us a star. It's a free way to show your support.

jlama-core/src/main/java/com/github/tjake/jlama/model/functions/Generator.java

@@ -149,6 +149,10 @@ default Response generate(
         return generate(session, promptContext, temperature, ntokens, (s, aFloat) -> {});
     }
 
+    default GenerateBuilder generateBuilder() {
+        return new GenerateBuilder(this);
+    }
+
     enum PoolingType {
         MODEL, // Use the model's pooling layers
         AVG,
@@ -179,4 +183,67 @@ default Map<String, Float> classify(String input, PoolingType poolingType) {
     Tokenizer getTokenizer();
 
     Optional<PromptSupport> promptSupport();
+
+    class GenerateBuilder {
+        private UUID session = UUID.randomUUID();
+        private PromptContext promptContext;
+        private float temperature = 0.0f;
+        private int ntokens = 256;
+        private BiConsumer<String, Float> onTokenWithTimings = (s, aFloat) -> {};
+        private final Generator generator;
+
+        public GenerateBuilder(Generator generator) {
+            this.generator = generator;
+        }
+
+        public GenerateBuilder session(UUID session) {
+            this.session = session;
+
+            return this;
+        }
+
+        public GenerateBuilder session(String session) {
+            this.session = UUID.fromString(session);
+
+            return this;
+        }
+
+        public GenerateBuilder promptContext(PromptContext promptContext) {
+            this.promptContext = promptContext;
+
+            return this;
+        }
+
+        public GenerateBuilder prompt(String prompt) {
+            this.promptContext = PromptContext.of(prompt);
+
+            return this;
+        }
+
+        public GenerateBuilder temperature(float temperature) {
+            this.temperature = temperature;
+
+            return this;
+        }
+
+        public GenerateBuilder ntokens(int ntokens) {
+            this.ntokens = ntokens;
+
+            return this;
+        }
+
+        public GenerateBuilder onTokenWithTimings(BiConsumer<String, Float> onTokenWithTimings) {
+            this.onTokenWithTimings = onTokenWithTimings;
+
+            return this;
+        }
+
+        public Response generate() {
+            if (promptContext == null) {
+                throw new IllegalArgumentException("promptContext cannot be null");
+            }
+
+            return generator.generate(session, promptContext, temperature, ntokens, onTokenWithTimings);
+        }
+    }
 }