import cc.projectargus.libargus.*;
import java.lang.foreign.Arena;
import java.nio.file.Path;

public class Main {
    public static void main(String[] args) {
        // Initialize global backends (CUDA/CPU)
        ArgusBackend.init();

        try (Arena arena = Arena.ofConfined();
             ArgusModel model = ArgusModel.load(arena, Path.of("models/llama-3-8b.gguf"), 99, true)) {
             
             // Initialize context configurations
             ArgusContextConfig config = new ArgusContextConfig.Builder(4096)
                 .cpuThreads(8)
                 .typeK(ArgusContextConfig.KV_TYPE_Q4_0) // Quantize KV Cache
                 .typeV(ArgusContextConfig.KV_TYPE_Q4_0)
                 .build();
                 
             try (ArgusContext context = ArgusContext.init(arena, model, config)) {
                 // Run text evaluation & generation loop...
             }
        } finally {
             // Tear down native backend drivers
             ArgusBackend.free();
        }
    }
}

import cc.projectargus.libargus.*;
import java.lang.foreign.Arena;
import java.nio.file.Path;
import java.util.List;

public class MultimodalApp {
    public static void main(String[] args) {
        ArgusBackend.init();

        try (Arena arena = Arena.ofConfined();
              ArgusModel baseModel = ArgusModel.load(arena, Path.of("models/qwen2-vl-7b-it.gguf"), 99, true);
              ArgusContext context = ArgusContext.init(arena, baseModel, new ArgusContextConfig.Builder(8192).build());
              // Load the multimodal adapter context
              ArgusMultimodalContext mctx = ArgusMultimodalContext.init(arena, baseModel, Path.of("models/qwen2-vl-7b-it.mmproj"), 4, true)) {

            // 1. Load an image or audio file into unmanaged memory
            try (ArgusBitmap image = ArgusBitmap.loadFile(arena, mctx, Path.of("media/cat.png"), false)) {
                
                // 2. Tokenize prompt text replacing the media marker
                String prompt = "<__media__>\nDescribe what you see in this image.";
                try (ArgusInputChunks chunks = mctx.tokenize(arena, prompt, true, List.of(image))) {
                    
                    // 3. Evaluate chunks (handles image projection on GPU & M-RoPE position grids)
                    int newNPast = context.evalMultimodalChunks(mctx, chunks, 0, 0, 1024, true);
                    System.out.println("Prompt evaluated. Ready to sample output tokens! New position: " + newNPast);
                }
            }
        } finally {
            ArgusBackend.free();
        }
    }
}

// Iterate and read frames/timestamps from a video file sequentially
try (ArgusVideo video = ArgusVideo.loadFile(arena, mctx, Path.of("media/video.mp4"), 4.0f, 5000);
     ArgusVideoItem item = new ArgusVideoItem()) {
    while (video.readNext(item)) {
        if (item.bitmap() != null) {
            // Process the extracted RGB frame bitmap (ownership is managed by ArgusVideoItem)
            ArgusBitmap frame = item.bitmap();
            // ...
        } else if (item.text() != null) {
            // Received a video timestamp chunk (e.g. "[00m05s]")
            System.out.println("At timestamp: " + item.text());
        }
    }
}

import cc.projectargus.libargus.*;
import java.lang.foreign.Arena;
import java.lang.foreign.MemorySegment;
import java.lang.foreign.ValueLayout;
import java.nio.file.Path;

public class EmbeddingsApp {
    public static void main(String[] args) {
        ArgusBackend.init();

        try (Arena arena = Arena.ofConfined();
             ArgusModel model = ArgusModel.load(arena, Path.of("models/jina-embeddings-v3-Q4_K_M.gguf"), 99, true)) {

            // Initialize context configuration with embeddings enabled
            ArgusContextConfig config = new ArgusContextConfig.Builder(512)
                .cpuThreads(4)
                .embeddings(true)
                .build();

            try (ArgusContext context = ArgusContext.init(arena, model, config)) {
                // Tokenize and evaluate prompt
                String text = "text-matching: Retrieve semantic vector for this sentence.";
                MemorySegment textSeg = arena.allocateFrom(text);
                
                MemorySegment tokenBuf = arena.allocate(ValueLayout.JAVA_INT, 512);
                int nTokens = context.tokenize(textSeg, tokenBuf, true);
                
                context.decodeBatch(tokenBuf, nTokens, 0, 0, false);

                // Retrieve embedding vector (e.g., 1024 dimensions)
                int expectedDim = 1024;
                MemorySegment embeddingsBuf = arena.allocate(ValueLayout.JAVA_FLOAT, expectedDim);
                int nFloats = context.getEmbeddings(0, embeddingsBuf, expectedDim);
                
                System.out.println("Retrieved embeddings containing " + nFloats + " floats.");
            }
        } finally {
            ArgusBackend.free();
        }
    }
}

// Access model vocabulary metadata
int bos = model.vocabBos();
int eos = model.vocabEos();
int eot = model.vocabEot(); // End-Of-Turn token for chat models
int nTokens = model.vocabNTokens(); // Vocabulary capacity
boolean isEog = model.vocabIsEog(sampledToken); // Native End-Of-Generation verification

// Query model architecture dimensions & parameters
int nEmbd = model.nEmbd(); // Embedding dimension size (e.g. 1024)
int nCtxTrain = model.nCtxTrain(); // Context length training ceiling
int nLayer = model.nLayer(); // Transformer layers count
int nHead = model.nHead(); // Attention head count
long nParams = model.nParams(); // Total model parameters count

// Retrieve metadata strings by key name
String modelArch = model.getMetadataValue("general.architecture"); // e.g. "qwen2vl"
String modelName = model.getMetadataValue("general.name"); // e.g. "Qwen2 VL 2B Instruct"

// Traverse and inspect the complete metadata dictionary
java.util.Map<String, String> metadata = model.getMetadataMap();
metadata.forEach((key, val) -> System.out.println(key + " -> " + val));

try (Arena sessionArena = Arena.ofConfined()) {
    // Define biased tokens and their steering weights (e.g. -Float.MAX_VALUE to ban)
    int[] steerTokens = new int[] { 151644, 151645 }; // <__think__> tags
    float[] steerValues = new float[] { -Float.MAX_VALUE, -Float.MAX_VALUE };

    // Allocate unmanaged struct segment ONCE outside the hot generation loop
    MemorySegment biasSeg = sessionArena.allocate(ArgusLayouts.LOGIT_BIAS, steerTokens.length);
    for (int i = 0; i < steerTokens.length; i++) {
        biasSeg.setAtIndex(ValueLayout.JAVA_INT, i * 2, steerTokens[i]);
        biasSeg.setAtIndex(ValueLayout.JAVA_FLOAT, i * 2 + 1, steerValues[i]);
    }

    while (generating) {
        context.decodeBatch(batch);
        
        // Zero-copy, zero-allocation token generation downcall passing raw pointer
        int token = context.sampleTokenWithBias(
            seqId, temperature, repeatPenalty, biasSeg, steerTokens.length
        );
        if (token == model.vocabEos()) break;
    }
}