POST
/
embeddings
curl --request POST \
  --url https://api.electronhub.ai/v1/embeddings \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "text-embedding-ada-002",
  "input": "<string>",
  "encoding_format": "float",
  "dimensions": 123
}'
{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [
        123
      ],
      "index": 123
    }
  ],
  "model": "<string>",
  "usage": {
    "prompt_tokens": 123,
    "total_tokens": 123
  }
}

The Embeddings API enables you to generate numerical representations of text that can be used for semantic search, clustering, and other machine learning tasks.

​
Create Embeddings

POST /embeddings

Generate embeddings for input text.

​
Request Body

​
input
string | array
required

Input text to embed, encoded as a string or array of strings

​
model
string
required

The model to use for generating embeddings (e.g., “text-embedding-ada-002”, “text-embedding-3-small”, “text-embedding-3-large”)

​
encoding_format
string

The format to return the embeddings in (“float” or “base64”)

​
dimensions
integer

The number of dimensions the resulting output embeddings should have (only supported in text-embedding-3 models)

​
user
string

A unique identifier representing your end-user

​
Response

Returns an embedding object containing the vector embeddings.

​
Example

const response = await fetch('https://api.electronhub.ai/v1/embeddings', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    input: 'The quick brown fox jumps over the lazy dog',
    model: 'text-embedding-3-small'
  })
});

const data = await response.json();
console.log(data);

​
Multiple Inputs

You can embed multiple text inputs in a single request:

{
  "input": [
    "Text to embed 1",
    "Text to embed 2",
    "Text to embed 3"
  ],
  "model": "text-embedding-3-small"
}

​
Use Cases

  • Semantic Search: Find documents similar to a query
  • Clustering: Group similar texts together
  • Classification: Train classifiers on embedding features
  • Recommendation: Recommend items based on similarity
  • Anomaly Detection: Identify outliers in text data

​
Best Practices

  • Use text-embedding-3-small for most use cases (good balance of performance and cost)
  • Use text-embedding-3-large for maximum performance
  • Batch multiple inputs in a single request for efficiency
  • Store embeddings for reuse rather than regenerating them

Authorizations

​
Authorization
string
header
required

Enter your API key (starts with 'ek-')

Body

application/json

Response

200 - application/json

Success

The response is of type object.