Embeddings (OpenAI Format)

Official Documentation

OpenAI Embeddings

📝 Introduction

Get a vector representation of a given input that can be easily consumed by machine learning models — for semantic search, clustering, recommendations, classification and RAG.

📮 Endpoint

POST /v1/embeddings

Authentication

Authorization: Bearer $WS_API_KEY

💡 Request Examples

Single Text ✅

curl http://baseurl/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WS_API_KEY" \
  -d '{
    "model": "text-embedding-3-small",
    "input": "The food was delicious and the waiter was very friendly."
  }'

Response Example:

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0023064255, -0.009327292, -0.0028842222, "..."]
    }
  ],
  "model": "text-embedding-3-small",
  "usage": {
    "prompt_tokens": 12,
    "total_tokens": 12
  }
}

Batch Input ✅

curl http://baseurl/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WS_API_KEY" \
  -d '{
    "model": "text-embedding-3-large",
    "input": [
      "First document text",
      "Second document text",
      "Third document text"
    ],
    "dimensions": 1024
  }'

📋 Request Body Parameters

Parameter	Type	Required	Description
model	string	Yes	text-embedding-3-large, text-embedding-3-small or text-embedding-ada-002
input	string / array	Yes	Text (or array of texts) to embed. Max 8192 tokens per input
dimensions	integer	No	Number of output dimensions (only text-embedding-3-* models). Allows shortening vectors
encoding_format	string	No	float (default) or base64
user	string	No	End-user identifier

📥 Response Fields

Field	Type	Description
object	string	Always list
data	array	One embedding object per input, each with index and embedding (vector of floats)
model	string	Model used
usage	object	prompt_tokens, total_tokens

Available Models

Model ID	Max Dimensions
text-embedding-3-large	3072
text-embedding-3-small	1536
text-embedding-ada-002	1536 (fixed)