HuggingFace Embeddor

Open Source Embeddings

Overview

Generate embeddings using HuggingFace's extensive collection of open-source models. Supports both hosted inference endpoints and local model deployment.

Popular Models

sentence-transformers/all-mpnet-base-v2
sentence-transformers/all-MiniLM-L6-v2
BAAI/bge-large-en-v1.5

Key Features

Hosted inference API
Custom endpoints
Model versioning
Batch processing

Configuration

Required Parameters

apiKeyHuggingFace API token
modelNameModel identifier

Optional Parameters

inferenceEndpointCustom endpoint URL

Example Usage

// Using hosted inference API
const embedder = new HuggingFaceEmbeddor({
  apiKey: "your-api-key",
  modelName: "sentence-transformers/all-mpnet-base-v2"
});

// Using custom inference endpoint
const customEmbedder = new HuggingFaceEmbeddor({
  apiKey: "your-api-key",
  modelName: "BAAI/bge-large-en-v1.5",
  inferenceEndpoint: "https://your-endpoint.huggingface.cloud"
});

// 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

Choose appropriate model size
Monitor API usage limits
Implement error handling
Cache common embeddings

Model Selection Tips

Consider model size vs. performance
Check language support
Verify model updates

Response Format

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