fix: rewrite ChatExample using actual API (Pair, InferenceParameters, generate)

ChatMessage and ChatRequest don't exist in the codebase. Replace with
the real API: InferenceParameters.setMessages(String, List<Pair>) for
building the message history and model.generate() for streaming output,
matching the pattern used in MainExample.

https://claude.ai/code/session_016atM3vkBsmaia7QGXKex8w

Author: claude

src/test/java/examples/ChatExample.java

@@ -1,9 +1,10 @@
 package examples;
 
-import de.kherud.llama.ChatMessage;
-import de.kherud.llama.ChatRequest;
+import de.kherud.llama.InferenceParameters;
 import de.kherud.llama.LlamaModel;
+import de.kherud.llama.LlamaOutput;
 import de.kherud.llama.ModelParameters;
+import de.kherud.llama.Pair;
 
 import java.io.BufferedReader;
 import java.io.InputStreamReader;
@@ -23,16 +24,23 @@ public static void main(String... args) throws Exception {
                 .setGpuLayers(43);
         try (LlamaModel model = new LlamaModel(modelParams)) {
             BufferedReader reader = new BufferedReader(new InputStreamReader(System.in, StandardCharsets.UTF_8));
-            List<ChatMessage> messages = new ArrayList<>();
-            messages.add(new ChatMessage(ChatMessage.Role.SYSTEM, "You are a helpful assistant."));
+            List<Pair<String, String>> messages = new ArrayList<>();
+            String system = "You are a helpful assistant.";
             while (true) {
                 System.out.print("User: ");
                 String input = reader.readLine();
-                messages.add(new ChatMessage(ChatMessage.Role.USER, input));
-                ChatRequest request = new ChatRequest(messages, false);
-                ChatMessage response = (ChatMessage) model.chat(request);
-                System.out.println("Assistant: " + response.getContent());
-                messages.add(response);
+                messages.add(new Pair<>("user", input));
+                StringBuilder response = new StringBuilder();
+                InferenceParameters inferParams = new InferenceParameters("")
+                        .setMessages(system, messages)
+                        .setUseChatTemplate(true);
+                System.out.print("Assistant: ");
+                for (LlamaOutput output : model.generate(inferParams)) {
+                    System.out.print(output);
+                    response.append(output);
+                }
+                System.out.println();
+                messages.add(new Pair<>("assistant", response.toString()));
             }
         }
     }