feat: prepare for release embedding preview version

Author: hlhr202

README.md

@@ -38,6 +38,8 @@ The current version supports only one inference session on one LLama instance at
 
 If you wish to have multiple inference sessions concurrently, you need to create multiple LLama instances
 
+### Inference
+
 ```typescript
 import path from "path";
 import { LLamaClient } from "llama-node";
@@ -80,6 +82,42 @@ llama.createTextCompletion(
 );
 ```
 
+### Embedding
+
+Preview version, embedding end token may change in the future. Do not use it in production!
+
+```typescript
+import { LLamaClient } from "llama-node";
+import path from "path";
+
+const model = path.resolve(process.cwd(), "./ggml-alpaca-7b-q4.bin");
+
+const llama = new LLamaClient(
+    {
+        path: model,
+        numCtxTokens: 128,
+    },
+    true
+);
+
+const prompt = `how are you`;
+
+llama
+    .getEmbedding({
+        prompt,
+        numPredict: BigInt(128),
+        temp: 0.2,
+        topP: 1,
+        topK: BigInt(40),
+        repeatPenalty: 1,
+        repeatLastN: BigInt(64),
+        seed: BigInt(0),
+        feedPrompt: true,
+    })
+    .then(console.log);
+
+```
+
 ---
 
 ## Self built

example/embedding.ts

@@ -0,0 +1,28 @@
+import { LLamaClient } from "../src";
+import path from "path";
+
+const model = path.resolve(process.cwd(), "./ggml-alpaca-7b-q4.bin");
+
+const llama = new LLamaClient(
+    {
+        path: model,
+        numCtxTokens: 128,
+    },
+    true
+);
+
+const prompt = `how are you`;
+
+llama
+    .getEmbedding({
+        prompt,
+        numPredict: BigInt(128),
+        temp: 0.2,
+        topP: 1,
+        topK: BigInt(40),
+        repeatPenalty: 1,
+        repeatLastN: BigInt(64),
+        seed: BigInt(0),
+        feedPrompt: true,
+    })
+    .then(console.log);

package-lock.json

@@ -1,13 +1,13 @@
 {
   "name": "llama-node",
-  "version": "0.0.6",
+  "version": "0.0.7",
   "description": "",
   "main": "dist/index.js",
   "module": "dist/index.mjs",
   "type": "module",
   "scripts": {
     "build": "tsup",
-    "start": "tsx example/inference.ts",
+    "start": "tsx example/embedding.ts",
     "test:core": "npm t --workspaces=packages/core",
     "start:core": "npm start --workspaces=packages/core",
     "build:core": "npm run build --workspaces=packages/core",

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llama-node/core",
-  "version": "0.0.6",
+  "version": "0.0.7",
   "main": "index.js",
   "types": "index.d.ts",
   "napi": {

packages/core/@llama-node/core.darwin-arm64.node

@@ -4,14 +4,16 @@ const platforms = {
     "darwin-arm64": "aarch64-apple-darwin",
     "darwin-x64": "x86_64-apple-darwin",
     "linux-x64-gnu": "x86_64-unknown-linux-gnu",
-    "win32-x64-msvc": "x86_64-pc-windows-msvc"
+    "win32-x64-msvc": "x86_64-pc-windows-msvc",
 };
 
 const compile = () => {
     Object.entries(platforms).forEach(([platform, target]) => {
-        exec(`napi build --platform --target ${target} --release`).stdout?.pipe(
-            process.stdout
+        const buildProcess = exec(
+            `napi build --platform --target ${target} --release`
         );
+        buildProcess.stdout?.pipe(process.stdout);
+        buildProcess.stderr?.pipe(process.stderr);
     });
 };