- TypeScript 98.2%
- JavaScript 0.9%
- Shell 0.6%
- PowerShell 0.3%
| Filename | Latest commit message | Latest commit date |
|---|---|---|
| .github/workflows | ||
| .vscode | ||
| packages | ||
| patches | ||
| publish | ||
| scaffolds | ||
| scripts | ||
| .eslintrc.json | ||
| .gitignore | ||
| .gitmodules | ||
| .npmrc | ||
| .nvmrc | ||
| .prettierrc.json | ||
| CONTRIBUTING.md | ||
| jest.config.js | ||
| jestSnapshotResolver.js | ||
| lerna.json | ||
| LICENSE | ||
| package-lock.json | ||
| package.json | ||
| README.md | ||
| release.sh | ||
| tsconfig.build.json | ||
| tsconfig.cjs.json | ||
| tsconfig.esm.json | ||
| tsconfig.json | ||
| tsconfig.types.json | ||
| turbo.json | ||
Use local LLMs in TypeScript
LM Studio Client SDK
lmstudio-js is LM Studio's official JavaScript client SDK, written in TypeScript. It allows you to
- Use LLMs to respond in chats or predict text completions
- Define functions as tools, and turn LLMs into autonomous agents that run completely locally
- Load, configure, and unload models from memory
- Supports both browser and any Node-compatible environments
- Generate embeddings for text, and more!
Using python? See lmstudio-python
Installation
npm install @lmstudio/sdk --save
Quick Example
import { LMStudioClient } from "@lmstudio/sdk";
const client = new LMStudioClient();
const model = await client.llm.model("llama-3.2-1b-instruct");
const result = await model.respond("What is the meaning of life?");
console.info(result.content);
For more examples and documentation, visit lmstudio-js docs.
Why use lmstudio-js over openai sdk?
Open AI's SDK is designed to use with Open AI's proprietary models. As such, it is missing many features that are essential for using LLMs in a local environment, such as:
- Managing loading and unloading models from memory
- Configuring load parameters (context length, gpu offload settings, etc.)
- Speculative decoding
- Getting information (such as context length, model size, etc.) about a model
- ... and more
In addition, while openai sdk is automatically generated, lmstudio-js is designed from ground-up to be clean and easy to use for TypeScript/JavaScript developers.
Contributing
You can build the project locally by following these steps:
git clone https://github.com/lmstudio-ai/lmstudio-js.git --recursive
cd lmstudio-js
npm install
npm run build
See CONTRIBUTING.md for more information.
Community
Discuss all things lmstudio-js in #dev-chat in LM Studio's Community Discord server.