Create Embeddings

POST /v1/embeddings

Creates an embedding vector representing the input text. Embeddings are useful for semantic search, clustering, and similarity comparison.

Request Body

string

required

The embedding model to use (e.g., text-embedding-3-small, text-embedding-3-large, text-embedding-ada-002).

string | array

required

The text to embed. Can be a single string or an array of strings for batch processing.

string

default:"float"

The format to return embeddings in. Options: float or base64.

integer

The number of dimensions for the output embeddings. Only supported by some models.

Response

string

Always list.

array

Array of embedding objects.

Show Embedding object

string

Always embedding.

integer

The index of the embedding in the input array.

array

The embedding vector (array of floats).

string

The model used to generate embeddings.

object

Token usage statistics.

Show properties

integer

Number of tokens in the input.

integer

Total tokens processed.

Examples

Single Text Embedding

from openai import OpenAI

client = OpenAI(
    api_key="sk-voidai-your_key_here",
    base_url="https://api.voidai.app/v1"
)

response = client.embeddings.create(
    model="text-embedding-3-small",
    input="The quick brown fox jumps over the lazy dog."
)

embedding = response.data[0].embedding
print(f"Embedding dimension: {len(embedding)}")
print(f"First 5 values: {embedding[:5]}")

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'sk-voidai-your_key_here',
  baseURL: 'https://api.voidai.app/v1'
});

const response = await client.embeddings.create({
  model: 'text-embedding-3-small',
  input: 'The quick brown fox jumps over the lazy dog.'
});

const embedding = response.data[0].embedding;
console.log(`Embedding dimension: ${embedding.length}`);
console.log(`First 5 values: ${embedding.slice(0, 5)}`);

curl https://api.voidai.app/v1/embeddings \
  -H "Authorization: Bearer sk-voidai-your_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-3-small",
    "input": "The quick brown fox jumps over the lazy dog."
  }'

Batch Embeddings

texts = [
    "How do I reset my password?",
    "What are your pricing plans?",
    "How can I contact support?"
]

response = client.embeddings.create(
    model="text-embedding-3-small",
    input=texts
)

for i, data in enumerate(response.data):
    print(f"Text {i}: {len(data.embedding)} dimensions")

const texts = [
  'How do I reset my password?',
  'What are your pricing plans?',
  'How can I contact support?'
];

const response = await client.embeddings.create({
  model: 'text-embedding-3-small',
  input: texts
});

response.data.forEach((data, i) => {
  console.log(`Text ${i}: ${data.embedding.length} dimensions`);
});

curl https://api.voidai.app/v1/embeddings \
  -H "Authorization: Bearer sk-voidai-your_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-3-small",
    "input": [
      "How do I reset my password?",
      "What are your pricing plans?",
      "How can I contact support?"
    ]
  }'

Custom Dimensions

# Use smaller dimension for efficiency
response = client.embeddings.create(
    model="text-embedding-3-large",
    input="Your text here",
    dimensions=256
)

embedding = response.data[0].embedding
print(f"Reduced dimension: {len(embedding)}")  # 256

const response = await client.embeddings.create({
  model: 'text-embedding-3-large',
  input: 'Your text here',
  dimensions: 256
});

console.log(`Reduced dimension: ${response.data[0].embedding.length}`);  // 256

Response Example

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0023, -0.0095, 0.0152, ...]
    }
  ],
  "model": "text-embedding-3-small",
  "usage": {
    "prompt_tokens": 10,
    "total_tokens": 10
  }
}

Use Cases

Semantic Search

Find similar content by comparing embedding distances.

Clustering

Group similar documents together based on embeddings.

Classification

Use embeddings as features for ML classifiers.

Recommendations

Find similar items for recommendation systems.

Similarity Search Example

import numpy as np
from openai import OpenAI

client = OpenAI(
    api_key="sk-voidai-your_key_here",
    base_url="https://api.voidai.app/v1"
)

def cosine_similarity(a, b):
    return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b))

# Create embeddings for documents
documents = [
    "Python is a programming language",
    "JavaScript runs in the browser",
    "Machine learning uses neural networks"
]

doc_embeddings = client.embeddings.create(
    model="text-embedding-3-small",
    input=documents
).data

# Search query
query = "How do I code in Python?"
query_embedding = client.embeddings.create(
    model="text-embedding-3-small",
    input=query
).data[0].embedding

# Find most similar document
similarities = [
    cosine_similarity(query_embedding, doc.embedding)
    for doc in doc_embeddings
]

best_match_idx = np.argmax(similarities)
print(f"Best match: {documents[best_match_idx]}")
print(f"Similarity: {similarities[best_match_idx]:.4f}")

Model Comparison

Model	Dimensions	Best For
`text-embedding-3-small`	1536	Cost-effective, general use
`text-embedding-3-large`	3072	Highest quality, customizable dimensions
`text-embedding-ada-002`	1536	Legacy, broad compatibility

Chat

Images

Audio

Video

Embeddings

Moderations

Models

Discounts

Create Embeddings

Request Body

Response

Examples

Single Text Embedding

Batch Embeddings

Custom Dimensions

Response Example

Use Cases

Semantic Search

Clustering

Classification

Recommendations

Similarity Search Example

Model Comparison

​Request Body

​Response

​Examples

​Single Text Embedding

​Batch Embeddings

​Custom Dimensions

​Response Example

​Use Cases

Semantic Search

Clustering

Classification

Recommendations

​Similarity Search Example

​Model Comparison

Request Body

Response

Examples

Single Text Embedding

Batch Embeddings

Custom Dimensions

Response Example

Use Cases

Similarity Search Example

Model Comparison