Mistral AI Embeddor

State-of-the-Art Embeddings

Overview

Generate high-quality embeddings using Mistral AI's advanced language models. Features robust rate limiting, automatic retries, and configurable API settings.

Available Models

mistral-embed
mistral-embed-light

Key Features

Concurrent request handling
Automatic retry mechanism
Configurable timeouts
Custom API endpoints

Configuration

Required Parameters

modelMistral AI model name
mistralApiKeyAPI authentication key

Optional Parameters

maxConcurrentRequestsDefault: 5
maxRetriesDefault: 3
requestTimeoutDefault: 30000ms
apiEndpointDefault: https://api.mistral.ai/v1

Example Usage

// Basic configuration
const embedder = new MistralAIEmbeddor({
  model: "mistral-embed",
  mistralApiKey: "your-api-key",
});

// Advanced configuration
const advancedEmbedder = new MistralAIEmbeddor({
  model: "mistral-embed-light",
  mistralApiKey: "your-api-key",
  maxConcurrentRequests: 10,
  maxRetries: 5,
  requestTimeout: 60000,
  apiEndpoint: "https://custom-endpoint.com/v1"
});

// 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

Use environment variables for API keys
Implement proper error handling
Monitor rate limits
Cache frequently used embeddings

Performance Tips

Adjust concurrent requests based on usage
Set appropriate timeout values
Use batch processing for multiple inputs

Response Format

{
  "embeddings": {
    "vectors": number[][],
    "dimensions": number,
    "model": string
  },
  "usage": {
    "prompt_tokens": number,
    "total_tokens": number
  },
  "metadata": {
    "processing_time": number,
    "retries": number,
    "api_version": string
  },
  "status": {
    "success": boolean,
    "error": string | null
  }
}