fix: simplify

cpp/src/LlamaCPPBinding.cpp

@@ -9,7 +9,6 @@ Napi::Object LlamaCPPBinding::Init(Napi::Env env, Napi::Object exports) {
     Napi::Function func = DefineClass(env, "LlamaCPP", {
         InstanceMethod("initialize", &LlamaCPPBinding::Initialize),
         InstanceMethod("runQuery", &LlamaCPPBinding::RunQuery),
-        InstanceMethod("runQueryStream", &LlamaCPPBinding::RunQueryStream),
     });
 
     constructor = Napi::Persistent(func);
@@ -59,24 +58,3 @@ Napi::Value LlamaCPPBinding::RunQuery(const Napi::CallbackInfo& info) {
     std::string response = llama_->RunQuery(prompt, max_tokens);
     return Napi::String::New(env, response);
 }
-
-Napi::Value LlamaCPPBinding::RunQueryStream(const Napi::CallbackInfo& info) {
-    Napi::Env env = info.Env();
-    if (info.Length() < 2 || !info[0].IsString() || !info[1].IsFunction()) {
-        Napi::TypeError::New(env, "String and function expected").ThrowAsJavaScriptException();
-        return env.Null();
-    }
-
-    std::string prompt = info[0].As<Napi::String>().Utf8Value();
-    Napi::Function callback = info[1].As<Napi::Function>();
-    size_t max_tokens = 1000;
-    if (info.Length() > 2 && info[2].IsNumber()) {
-        max_tokens = info[2].As<Napi::Number>().Uint32Value();
-    }
-
-    llama_->RunQueryStream(prompt, max_tokens, [&env, &callback](const std::string& token) {
-        callback.Call(env.Global(), {Napi::String::New(env, token)});
-    });
-
-    return env.Undefined();
-}

cpp/src/LlamaCPPBinding.h

@@ -13,7 +13,6 @@ class LlamaCPPBinding : public Napi::ObjectWrap<LlamaCPPBinding> {
 
     Napi::Value Initialize(const Napi::CallbackInfo& info);
     Napi::Value RunQuery(const Napi::CallbackInfo& info);
-    Napi::Value RunQueryStream(const Napi::CallbackInfo& info);
 
     std::unique_ptr<LlamaWrapper> llama_;
 };

example/index.js

@@ -0,0 +1,13 @@
+const Llama = require('../index.js');
+
+async function main() {
+    const llama = new Llama();
+
+    llama.initialize(__dirname + "/models/Meta-Llama-3.1-8B-Instruct-Q3_K_S.gguf");
+
+    console.log("\nRunning a simple query:");
+    const response = llama.runQuery("Tell me a short story.", 100);
+    console.log("Response:", response);
+}
+
+main().catch(console.error);

index.d.ts

@@ -2,5 +2,4 @@ export class Llama {
   constructor();
   initialize(modelPath: string, contextSize?: number): boolean;
   runQuery(prompt: string, maxTokens?: number): string;
-  runQueryStream(prompt: string, callback: (token: string) => void, maxTokens: number): void;
 }

package.json

@@ -13,13 +13,13 @@
     "node": ">=18.0.0"
   },
   "dependencies": {
-    "node-addon-api": "6.1.0",
+    "node-addon-api": "8.1.0",
     "cmake-js": "7.2.1"
   },
   "scripts": {
     "install": "cmake-js compile -d cpp print-configure",
     "build": "cmake-js compile -d cpp print-configure",
-    "example": "node example/test.js"
+    "example": "node example/index.js"
   },
   "keywords": [
     "node",

yarn.lock

@@ -2498,10 +2498,10 @@ nerf-dart@^1.0.0:
   resolved "https://registry.yarnpkg.com/nerf-dart/-/nerf-dart-1.0.0.tgz#e6dab7febf5ad816ea81cf5c629c5a0ebde72c1a"
   integrity sha512-EZSPZB70jiVsivaBLYDCyntd5eH8NTSMOn3rB+HxwdmKThGELLdYv8qVIMWvZEFy9w8ZZpW9h9OB32l1rGtj7g==
 
-node-addon-api@6.1.0:
-  version "6.1.0"
-  resolved "https://registry.yarnpkg.com/node-addon-api/-/node-addon-api-6.1.0.tgz#ac8470034e58e67d0c6f1204a18ae6995d9c0d76"
-  integrity sha512-+eawOlIgy680F0kBzPUNFhMZGtJ1YmqM6l4+Crf4IkImjYrO/mqPwRMh352g23uIaQKFItcQ64I7KMaJxHgAVA==
+node-addon-api@8.1.0:
+  version "8.1.0"
+  resolved "https://registry.yarnpkg.com/node-addon-api/-/node-addon-api-8.1.0.tgz#55a573685dd4bd053f189cffa4e6332d2b1f1645"
+  integrity sha512-yBY+qqWSv3dWKGODD6OGE6GnTX7Q2r+4+DfpqxHSHh8x0B4EKP9+wVGLS6U/AM1vxSNNmUEuIV5EGhYwPpfOwQ==
 
 node-api-headers@^0.0.2:
   version "0.0.2"