chore: update example

Author: hlhr202

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/cat1.json

@@ -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));