LM Studio Embeddor

Local Studio Embeddings

Overview

Generate embeddings using LM Studio's local model server. Perfect for running embeddings locally with a user-friendly interface and support for multiple open-source models.

Key Features

Local model serving
Temperature control
OpenAI-compatible API
Multiple model support

Requirements

LM Studio application
Running local server
Compatible embedding model

Configuration

Required Parameters

lmStudioBaseUrlLM Studio server URL
lmStudioApiKeyAPI key (if configured)

Optional Parameters

temperatureModel temperature (Default: 0.0)

Example Usage

// Basic configuration
const embedder = new LMStudioEmbeddor({
  lmStudioBaseUrl: "http://localhost:1234/v1",
  lmStudioApiKey: "your-api-key"
});

// Configuration with temperature
const customEmbedder = new LMStudioEmbeddor({
  lmStudioBaseUrl: "http://localhost:1234/v1",
  lmStudioApiKey: "your-api-key",
  temperature: 0.7
});

// Generate embeddings
const result = await embedder.embed({
  input: "Your text to embed"
});

// Batch processing
const batchResult = await embedder.embedBatch({
  inputs: [
    "First text to embed",
    "Second text to embed"
  ]
});

Best Practices

Verify server is running
Monitor resource usage
Cache frequent embeddings
Handle connection errors

Performance Tips

Use appropriate batch sizes
Optimize temperature settings
Pre-load models in LM Studio

Response Format

{
  "embeddings": {
    "vectors": number[][],
    "dimensions": number
  },
  "metadata": {
    "model_info": {
      "name": string,
      "temperature": number
    },
    "processing_time": number
  },
  "status": {
    "success": boolean,
    "error": string | null
  }
}