LocalMode

$ pnpm install @localmode/core @localmode/transformers

import { createVectorDB, embed, embedMany, chunk } from '@localmode/core';
import { transformers } from '@localmode/transformers';

// Create embedding model
const model = transformers.embedding('Xenova/bge-small-en-v1.5');

// Create vector database with typed metadata
const db = await createVectorDB<{ text: string }>({
  name: 'docs',
  dimensions: 384,
});

// Chunk and embed documents
const chunks = chunk(documentText, { size: 512, overlap: 50 });
const { embeddings } = await embedMany({
  model,
  values: chunks.map((c) => c.text),
});

// Store vectors
await db.addMany(
  chunks.map((c, i) => ({
    id: `chunk-${i}`,
    vector: embeddings[i],
    metadata: { text: c.text },
  }))
);

// Search
const { embedding: query } = await embed({ model, value: 'What is AI?' });
const results = await db.search(query, { k: 5 });

$ pnpm install @localmode/core @localmode/webllm

import { streamText, generateObject, jsonSchema } from '@localmode/core';
import { webllm } from '@localmode/webllm';
import { z } from 'zod';

// Stream text from a local LLM
const model = webllm.languageModel('Llama-3.2-1B-Instruct-q4f16_1-MLC');

const result = await streamText({
  model,
  prompt: 'Explain quantum computing simply',
  maxTokens: 500,
});

for await (const chunk of result.stream) {
  process.stdout.write(chunk.text);
}

// Structured output with Zod schema
const { object } = await generateObject({
  model: webllm.languageModel('Qwen3-1.7B-q4f16_1-MLC'),
  schema: jsonSchema(
    z.object({
      name: z.string(),
      age: z.number(),
      interests: z.array(z.string()),
    })
  ),
  prompt: 'Generate a profile for a software engineer named Alex',
});