chore: update example

example/js/langchain/langchain.js

@@ -0,0 +1,29 @@
+import { MemoryVectorStore } from "langchain/vectorstores/memory";
+import { LLamaEmbeddings } from "llama-node/dist/extensions/langchain.js";
+import { LLama } from "llama-node";
+import { LLamaCpp } from "llama-node/dist/llm/llama-cpp.js";
+import path from "path";
+const model = path.resolve(process.cwd(), "../ggml-vicuna-7b-1.1-q4_1.bin");
+const llama = new LLama(LLamaCpp);
+const config = {
+    path: model,
+    enableLogging: true,
+    nCtx: 1024,
+    nParts: -1,
+    seed: 0,
+    f16Kv: false,
+    logitsAll: false,
+    vocabOnly: false,
+    useMlock: false,
+    embedding: true,
+    useMmap: true,
+};
+llama.load(config);
+const run = async () => {
+    // Load the docs into the vector store
+    const vectorStore = await MemoryVectorStore.fromTexts(["Hello world", "Bye bye", "hello nice world"], [{ id: 2 }, { id: 1 }, { id: 3 }], new LLamaEmbeddings({ maxConcurrency: 1 }, llama));
+    // Search for the most similar document
+    const resultOne = await vectorStore.similaritySearch("hello world", 1);
+    console.log(resultOne);
+};
+run();

example/js/llama-cpp/embedding.js

@@ -0,0 +1,30 @@
+import { LLama } from "llama-node";
+import { LLamaCpp } from "llama-node/dist/llm/llama-cpp.js";
+import path from "path";
+const model = path.resolve(process.cwd(), "../ggml-vicuna-7b-1.1-q4_1.bin");
+const llama = new LLama(LLamaCpp);
+const config = {
+    path: model,
+    enableLogging: true,
+    nCtx: 1024,
+    nParts: -1,
+    seed: 0,
+    f16Kv: false,
+    logitsAll: false,
+    vocabOnly: false,
+    useMlock: false,
+    embedding: true,
+    useMmap: true,
+};
+llama.load(config);
+const prompt = `Who is the president of the United States?`;
+const params = {
+    nThreads: 4,
+    nTokPredict: 2048,
+    topK: 40,
+    topP: 0.1,
+    temp: 0.2,
+    repeatPenalty: 1,
+    prompt,
+};
+llama.getEmbedding(params).then(console.log);

example/js/llama-cpp/llama-cpp.js

@@ -0,0 +1,37 @@
+import { LLama } from "llama-node";
+import { LLamaCpp } from "llama-node/dist/llm/llama-cpp.js";
+import path from "path";
+const model = path.resolve(process.cwd(), "../ggml-vicuna-7b-1.1-q4_1.bin");
+const llama = new LLama(LLamaCpp);
+const config = {
+    path: model,
+    enableLogging: true,
+    nCtx: 1024,
+    nParts: -1,
+    seed: 0,
+    f16Kv: false,
+    logitsAll: false,
+    vocabOnly: false,
+    useMlock: false,
+    embedding: false,
+    useMmap: true,
+};
+llama.load(config);
+const template = `How are you?`;
+const prompt = `### Human:
+
+${template}
+
+### Assistant:`;
+llama.createCompletion({
+    nThreads: 4,
+    nTokPredict: 2048,
+    topK: 40,
+    topP: 0.1,
+    temp: 0.2,
+    repeatPenalty: 1,
+    stopSequence: "### Human",
+    prompt,
+}, (response) => {
+    process.stdout.write(response.token);
+});

example/js/llama-cpp/tokenize.js

@@ -0,0 +1,21 @@
+import { LLama } from "llama-node";
+import { LLamaCpp } from "llama-node/dist/llm/llama-cpp.js";
+import path from "path";
+const model = path.resolve(process.cwd(), "../ggml-vicuna-7b-1.1-q4_1.bin");
+const llama = new LLama(LLamaCpp);
+const config = {
+    path: model,
+    enableLogging: true,
+    nCtx: 1024,
+    nParts: -1,
+    seed: 0,
+    f16Kv: false,
+    logitsAll: false,
+    vocabOnly: false,
+    useMlock: false,
+    embedding: false,
+    useMmap: true,
+};
+llama.load(config);
+const content = "how are you?";
+llama.tokenize({ content, nCtx: 2048 }).then(console.log);

example/js/llama-rs/embedding.js

@@ -0,0 +1,30 @@
+import { LLama } from "llama-node";
+import { LLamaRS } from "llama-node/dist/llm/llama-rs.js";
+import path from "path";
+import fs from "fs";
+const model = path.resolve(process.cwd(), "../ggml-alpaca-7b-q4.bin");
+const llama = new LLama(LLamaRS);
+llama.load({ path: model });
+const getWordEmbeddings = async (prompt, file) => {
+    const data = await llama.getEmbedding({
+        prompt,
+        numPredict: 128,
+        temp: 0.2,
+        topP: 1,
+        topK: 40,
+        repeatPenalty: 1,
+        repeatLastN: 64,
+        seed: 0,
+    });
+    console.log(prompt, data);
+    await fs.promises.writeFile(path.resolve(process.cwd(), file), JSON.stringify(data));
+};
+const run = async () => {
+    const dog1 = `My favourite animal is the dog`;
+    await getWordEmbeddings(dog1, "./example/semantic-compare/dog1.json");
+    const dog2 = `I have just adopted a cute dog`;
+    await getWordEmbeddings(dog2, "./example/semantic-compare/dog2.json");
+    const cat1 = `My favourite animal is the cat`;
+    await getWordEmbeddings(cat1, "./example/semantic-compare/cat1.json");
+};
+run();

example/js/llama-rs/llama-rs.js

@@ -0,0 +1,27 @@
+import { LLama } from "llama-node";
+import { LLamaRS } from "llama-node/dist/llm/llama-rs.js";
+import path from "path";
+const model = path.resolve(process.cwd(), "../ggml-alpaca-7b-q4.bin");
+const llama = new LLama(LLamaRS);
+llama.load({ path: model });
+const template = `how are you`;
+const prompt = `Below is an instruction that describes a task. Write a response that appropriately completes the request.
+
+### Instruction:
+
+${template}
+
+### Response:`;
+llama.createCompletion({
+    prompt,
+    numPredict: 128,
+    temp: 0.2,
+    topP: 1,
+    topK: 40,
+    repeatPenalty: 1,
+    repeatLastN: 64,
+    seed: 0,
+    feedPrompt: true,
+}, (response) => {
+    process.stdout.write(response.token);
+});

example/js/llama-rs/semantic-compare/compare.js

@@ -0,0 +1,16 @@
+import * as tf from "@tensorflow/tfjs-node";
+import dog1 from "./dog1.json";
+import dog2 from "./dog2.json";
+import cat1 from "./cat1.json";
+const dog1Tensor = tf.tensor(dog1);
+const dog2Tensor = tf.tensor(dog2);
+const cat1Tensor = tf.tensor(cat1);
+const compareCosineSimilarity = (tensor1, tensor2) => {
+    const dotProduct = tensor1.dot(tensor2);
+    const norm1 = tensor1.norm();
+    const norm2 = tensor2.norm();
+    const cosineSimilarity = dotProduct.div(norm1.mul(norm2));
+    return cosineSimilarity.dataSync()[0];
+};
+console.log("dog1 vs dog2", compareCosineSimilarity(dog1Tensor, dog2Tensor));
+console.log("dog1 vs cat1", compareCosineSimilarity(dog1Tensor, cat1Tensor));

example/js/llama-rs/tokenize.js

@@ -0,0 +1,8 @@
+import { LLama } from "llama-node";
+import { LLamaRS } from "llama-node/dist/llm/llama-rs.js";
+import path from "path";
+const model = path.resolve(process.cwd(), "../ggml-alpaca-7b-q4.bin");
+const llama = new LLama(LLamaRS);
+llama.load({ path: model });
+const content = "how are you?";
+llama.tokenize(content).then(console.log);

example/package.json

@@ -1,27 +1,25 @@
 {
   "name": "@llama-node/examples",
-  "version": "1.0.0",
+  "version": "0.0.30",
   "description": "",
   "main": "index.js",
   "type": "module",
   "scripts": {
     "build": "tsc -p .",
-    "langchain": "tsx src/langchain/langchain.ts",
-    "llama-cpp": "tsx src/llama-cpp/llama-cpp.ts",
-    "llama-rs": "tsx src/llama-rs/llama-rs.ts",
-    "test": "echo \"Error: no test specified\" && exit 1"
+    "langchain": "node js/langchain/langchain.js",
+    "llama-cpp": "node js/llama-cpp/llama-cpp.js",
+    "llama-rs": "node js/llama-rs/llama-rs.js"
   },
   "author": "",
   "license": "MIT",
   "devDependencies": {
     "@types/node": "^18.15.11",
-    "tsx": "^3.12.6",
     "typescript": "^5.0.4",
     "langchain": "^0.0.56"
   },
   "dependencies": {
-    "@llama-node/core": "file:../packages/core",
-    "@llama-node/llama-cpp": "file:../packages/llama-cpp",
-    "llama-node": "file:../"
+    "@llama-node/core": "0.0.30",
+    "@llama-node/llama-cpp": "0.0.30",
+    "llama-node": "0.0.30"
   }
-}
+}

example/tsconfig.json

@@ -11,7 +11,7 @@
     // "disableReferencedProjectLoad": true,             /* Reduce the number of projects loaded automatically by TypeScript. */
 
     /* Language and Environment */
-    "target": "es2016",                                  /* Set the JavaScript language version for emitted JavaScript and include compatible library declarations. */
+    "target": "ESNext",                                  /* Set the JavaScript language version for emitted JavaScript and include compatible library declarations. */
     // "lib": [],                                        /* Specify a set of bundled library declaration files that describe the target runtime environment. */
     // "jsx": "preserve",                                /* Specify what JSX code is generated. */
     // "experimentalDecorators": true,                   /* Enable experimental support for legacy experimental decorators. */
@@ -30,7 +30,7 @@
     "moduleResolution": "nodenext",                     /* Specify how TypeScript looks up a file from a given module specifier. */
     // "baseUrl": "./",                                  /* Specify the base directory to resolve non-relative module names. */
     // "paths": {},                                      /* Specify a set of entries that re-map imports to additional lookup locations. */
-    "rootDirs": ["src"],                                   /* Allow multiple folders to be treated as one when resolving modules. */
+    "rootDirs": ["ts"],                                   /* Allow multiple folders to be treated as one when resolving modules. */
     // "typeRoots": [],                                  /* Specify multiple folders that act like './node_modules/@types'. */
     // "types": [],                                      /* Specify type package names to be included without being referenced in a source file. */
     // "allowUmdGlobalAccess": true,                     /* Allow accessing UMD globals from modules. */
@@ -55,7 +55,7 @@
     // "sourceMap": true,                                /* Create source map files for emitted JavaScript files. */
     // "inlineSourceMap": true,                          /* Include sourcemap files inside the emitted JavaScript. */
     // "outFile": "./",                                  /* Specify a file that bundles all outputs into one JavaScript file. If 'declaration' is true, also designates a file that bundles all .d.ts output. */
-    "outDir": "./dist",                                   /* Specify an output folder for all emitted files. */
+    "outDir": "./js",                                   /* Specify an output folder for all emitted files. */
     // "removeComments": true,                           /* Disable emitting comments. */
     // "noEmit": true,                                   /* Disable emitting files from a compilation. */
     // "importHelpers": true,                            /* Allow importing helper functions from tslib once per project, instead of including them per-file. */

scripts/version.ts

@@ -2,6 +2,7 @@ import main from "../package.json";
 import core from "../packages/core/package.json";
 import cpp from "../packages/llama-cpp/package.json";
 import cli from "../packages/cli/package.json";
+import example from "../example/package.json";
 import semver from "semver";
 import path from "path";
 import fs from "fs";
@@ -21,7 +22,7 @@ if (!semver.valid(newVersion)) {
     process.exit(1);
 }
 
-const newVersionIsGreaterThanAll = [main, core, cli].every((pkg) => {
+const newVersionIsGreaterThanAll = [main, core, cli, example].every((pkg) => {
     return semver.gt(newVersion, pkg.version);
 });
 
@@ -35,6 +36,7 @@ console.log(`main: ${main.version}`);
 console.log(`core: ${core.version}`);
 console.log(`cli: ${cli.version}`);
 console.log(`cpp: ${cpp.version}`);
+console.log(`example: ${example.version}`);
 
 console.log(`New version: ${newVersion}`);
 
@@ -43,6 +45,7 @@ main.version = newVersion;
 core.version = newVersion;
 cli.version = newVersion;
 cpp.version = newVersion;
+example.version = newVersion;
 main.dependencies["@llama-node/cli"] = newVersion;
 main.optionalDependencies["@llama-node/core"] = newVersion;
 main.optionalDependencies["@llama-node/llama-cpp"] = newVersion;
@@ -53,6 +56,9 @@ main.peerDependencies["@llama-node/core"] = newVersion;
 main.peerDependencies["@llama-node/llama-cpp"] = newVersion;
 main.peerDependencies["@llama-node/cli"] = newVersion;
 cli.dependencies["@llama-node/core"] = newVersion;
+example.dependencies["llama-node"] = newVersion;
+example.dependencies["@llama-node/core"] = newVersion;
+example.dependencies["@llama-node/llama-cpp"] = newVersion;
 
 console.log("Writing new versions...");
 fs.writeFileSync(
@@ -75,4 +81,9 @@ fs.writeFileSync(
     JSON.stringify(cli, null, 2)
 );
 
+fs.writeFileSync(
+    path.join(__dirname, "../example/package.json"),
+    JSON.stringify(example, null, 2)
+);
+
 console.log("Done!");