Your Delphi app
  ????????? makerai.embedder.dll  ??????  llama.dll  ??????  GGUF model file
  ????????? makerai.gen.dll       ??????  llama.dll  ??????  GGUF model file

uses uMakerAi.Embedder.Import;

var
  Emb: TEmbedder;
  VecA, VecB: TArray<Single>;
  Similarity: Single;
begin
  Emb := TEmbedder.Create; // loads makerai.embedder.dll from the exe folder
  try
    Emb.Load('C:\models\mxbai-embed-large-v1-q4_k_m.gguf', 99);
    // 99 = offload all layers to GPU; use 0 for CPU-only

    VecA := Emb.Embed('The cat sat on the mat');
    VecB := Emb.Embed('A feline resting on a rug');

    Similarity := TEmbedder.CosineSimilarity(VecA, VecB);
    Writeln(Format('Similarity: %.4f', [Similarity]));
    // → typically 0.85+ for semantically similar sentences
  finally
    Emb.Free;
  end;
end;

var
  Texts: TArray<string>;
  Vecs:  TArray<TArray<Single>>;
begin
  Texts := ['first sentence', 'second sentence', 'third sentence'];
  Vecs  := Emb.EmbedBatch(Texts);
  // Vecs[0], Vecs[1], Vecs[2] — one vector per input
end;

var Code: TLlamaErrorCode;
begin
  Code := Emb.ValidateModelFile('C:\models\my-model.gguf');
  if Code = llamaErrNone then
    Emb.Load('C:\models\my-model.gguf')
  else
    Writeln('Invalid model: ', Ord(Code));
end;

uses uMakerAi.Gen.Import;

var
  Gen:    TLlamaGenerator;
  Output: string;
begin
  Gen := TLlamaGenerator.Create; // loads makerai.gen.dll
  try
    Gen.Load('C:\models\llama3.2-3b-instruct-q4_k_m.gguf', 99);
    // parameters: model path, GPU layers (99=all), context size (0=default 4096)

    Output := Gen.Generate('Explain quantum entanglement in one paragraph:', 256);
    Writeln(Output);
  finally
    Gen.Free;
  end;
end;

Gen.GenerateStream(
  'Write a short poem about the Andes mountains:',
  128,   // max tokens
  0.8,   // temperature
  0.95,  // top-p
  procedure(const Piece: string; IsLast: Boolean)
  begin
    if not IsLast then
      Write(Piece)     // print each token as it arrives
    else
      Writeln;         // newline at the end
  end);

uses uMakerAi.Gen.Import;

// Greedy decoding (deterministic, best for benchmarks)
Gen.GenerateStream(Prompt, 128, 0, 0, smGreedy, 0, 0, OnToken);

// Mirostat v2 (self-regulating quality, good for creative text)
Gen.GenerateStream(Prompt, 256, 0, 0, smMirostatV2,
  5.0,  // tau  — target entropy (higher = more creative)
  0.1,  // eta  — learning rate
  OnToken);

// Min-P sampling (better coherence at high temperatures)
Gen.GenerateStream(Prompt, 256, 0.9, 0, smMinP,
  0.05, // min_p
  1,    // min_keep
  OnToken);

var History: string;
begin
  History := '';
  Gen.Load('C:\models\llama3.2-3b-instruct-q4_k_m.gguf');

  // Turn 1
  Gen.Reset;
  History := History + '<|user|>What is the capital of France?<|end|><|assistant|>';
  History := History + Gen.Generate(History, 64);

  // Turn 2
  Gen.Reset;
  History := History + '<|end|><|user|>And what is its population?<|end|><|assistant|>';
  History := History + Gen.Generate(History, 64);
end;

uses uMakerAi.Embeddings.Llamacpp;

var
  Emb: TAiLlamacppEmbeddings;
  Vec: TAiEmbeddingData;  // TArray<Double>
begin
  Emb := TAiLlamacppEmbeddings.Create(nil);
  try
    Emb.ModelPath  := 'C:\models\mxbai-embed-large-v1-q4_k_m.gguf';
    Emb.NGPULayers := 99;    // 0 for CPU-only
    Vec := Emb.CreateEmbedding('The quick brown fox jumps over the lazy dog', '');
    Writeln(Format('%d-dimensional vector, first value: %.6f', [Length(Vec), Vec[0]]));
  finally
    Emb.Free;
  end;
end;

// Use local model during development / testing
Embedder := TAiLlamacppEmbeddings.Create(nil);
TAiLlamacppEmbeddings(Embedder).ModelPath := 'C:\models\mxbai-embed-large-v1-q4.gguf';

// Switch to OpenAI in production — zero code change at the call site
// Embedder := TAiEmbeddingFactory.Instance.CreateDriver('OpenAI', nil);

Vec := Embedder.CreateEmbedding(MyText, '');

bin/                          CPU DLLs ??? copy these alongside your .exe
  makerai.embedder.dll
  makerai.gen.dll
  llama.dll
  ggml.dll
  ggml-base.dll
  ggml-cpu.dll
  ggml-cpu-alderlake.dll      ??? CPU dispatch variants, auto-selected at runtime
  ggml-cpu-haswell.dll
  ggml-cpu-zen4.dll
  ...

delphi/                       Delphi wrapper units ??? add to library search path
  uMakerAi.ErrorCodes.pas     Shared error code enum
  uMakerAi.Embedder.Import.pas  TEmbedder wrapper
  uMakerAi.Gen.Import.pas     TLlamaGenerator wrapper
  uMakerAi.Config.pas         INI-based model path helper (optional)

  makerAI/                    MakerAI component integration
    uMakerAi.Embeddings.Llamacpp.pas   TAiLlamacppEmbeddings