Get Started

Embedding

This quickstart walks you through generating your first embedding with SIRAYA Model Router.

Embedding quickstart

Basic Request

To generate embeddings, send a POST request to /v1/embeddings with your text input and chosen model:

PythonTypeScript (fetch)cURL

import requests

response = requests.post(
  "https://llm.siraya.ai/v1/embeddings",
  headers={
    "Authorization": "Bearer <API_KEY>",
    "Content-Type": "application/json",
  },
  json={
    "model": "gemini-embedding-2",
    "input": "Hello world"
  }
)

data = response.json()
embedding = data["data"][0]["embedding"]
print(f"Embedding dimension: {len(embedding)}")  # 3072 for gemini-embedding-2
print(f"Embedding: {embedding}")

const response = await fetch('https://llm.siraya.ai/v1/embeddings', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer <API_KEY>',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'gemini-embedding-2',
    input: 'Hello world'
  }),
});

const data = await response.json();
const embedding = data.data[0].embedding;
console.log(`Embedding dimension: ${embedding.length}`);

curl https://llm.siraya.ai/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <API_KEY>" \
  -d '{
    "model": "gemini-embedding-2",
    "input": "Hello world"
  }'

gemini-embedding-2 returns 3072-dimensional vectors by default. Pass the optional dimensions parameter for a smaller vector; Google recommends 768, 1536 or 3072.