lmstudio-js (TypeScript SDK)Authentication Project Setup

Basics

Cancelling Predictions Chat Completions Generate Completions Image Input Configuring the Model Speculative Decoding Structured Response Working with Chats

Agentic Flows

The .act() call Tool Definition

Plugins

Introduction to Plugins

Prompt Preprocessor

Custom Configuration Custom Status Report Examples Handling Aborts

Custom Configuration

Sharing Plugins

Using npm Dependencies

Text Embedding

Tokenization

Manage Models

List Local Models List Loaded Models Manage Models in Memory

API Reference

LLMLoadModelConfig LLMPredictionConfigInput

Model Info

Get Context Length Get Model Info

Prompt Preprocessor

Handling Aborts

A prediction may be aborted by the user while your generator is still running. In such cases, you should handle the abort gracefully by handling the ctl.abortSignal.

You can learn more about AbortSignal in the MDN documentation.

Examples

Previous Page

Introduction

Writing generators for LM Studio plugins using TypeScript