Embeddings API

The Embeddings API allows you to convert text into vector embeddings that can be used for various natural language processing tasks.

Create Embeddings

Endpoint

POST /v1/embeddings

Request Format

{
  "model": "string",
  "input": "string" | ["string"],
  "encoding_format": "string"
}

Parameters

Parameter	Type	Required	Description
model	string	Yes	The ID of the model to use
input	string or array	Yes	Input text to embed
encoding_format	string	No	The format to return the embeddings in

Response Format

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [number],
      "index": number
    }
  ],
  "model": "string",
  "usage": {
    "prompt_tokens": number,
    "total_tokens": number
  }
}

Example Request

curl https://api.fluence.ai/v1/embeddings \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "fluence-embedding",
    "input": "The quick brown fox jumps over the lazy dog"
  }'

Example Response

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [
        0.0023064255,
        -0.009327292,
        ...
      ],
      "index": 0
    }
  ],
  "model": "fluence-embedding",
  "usage": {
    "prompt_tokens": 9,
    "total_tokens": 9
  }
}

Supported Models

Model	Description	Dimensions
fluence-embedding	General purpose embeddings	1536
fluence-embedding-large	Large embeddings for complex tasks	3072

Use Cases

1. Semantic Search
2. Text Classification
3. Clustering
4. Recommendation Systems
5. Question Answering

Best Practices

1. Batch your requests when possible
2. Cache embeddings for frequently used text
3. Consider the dimensionality of your embeddings
4. Normalize embeddings before comparison
5. Use appropriate distance metrics

Error Codes

Status Code	Error Code	Description
400	invalid_request	The request was invalid
401	authentication_error	Authentication failed
429	rate_limit_exceeded	Rate limit exceeded
500	server_error	Internal server error

Rate Limits

• 100 requests per minute
• 1000 requests per hour