Embeddings

import httpx
import asyncio

async def create_embeddings():
    """Generate embeddings for text input."""
    async with httpx.AsyncClient() as client:
        response = await client.post(
            "https://api.melious.ai/v1/embeddings",
            headers={"Authorization": "Bearer your_api_key"},
            json={
                "model": "qwen3-embedding-8b",
                "input": "The quick brown fox jumps over the lazy dog"
            }
        )
        data = response.json()
        embedding = data["data"][0]["embedding"]
        print(f"Generated {len(embedding)}-dimensional embedding")
        print(f"CO2 emissions: {data['environment_impact']['carbon_g_co2']:.2f}g")
        return embedding

# Batch embeddings example
async def create_batch_embeddings():
    """Generate embeddings for multiple texts."""
    texts = [
        "The quick brown fox",
        "jumps over the lazy dog",
        "Hello, world!"
    ]

    async with httpx.AsyncClient() as client:
        response = await client.post(
            "https://api.melious.ai/v1/embeddings",
            headers={"Authorization": "Bearer your_api_key"},
            json={
                "model": "qwen3-embedding-8b",
                "input": texts,
                "mode": "price"  # Optimize for lowest cost
            }
        )
        data = response.json()
        embeddings = [item["embedding"] for item in data["data"]]
        print(f"Generated {len(embeddings)} embeddings")
        return embeddings

# Example usage
asyncio.run(create_embeddings())
asyncio.run(create_batch_embeddings())

// Generate embeddings for text input
const createEmbeddings = async () => {
  const response = await fetch(
    'https://api.melious.ai/v1/embeddings',
    {
      method: 'POST',
      headers: {
        'Authorization': 'Bearer your_api_key',
        'Content-Type': 'application/json'
      },
      body: JSON.stringify({
        model: 'qwen3-embedding-8b',
        input: 'The quick brown fox jumps over the lazy dog'
      })
    }
  );

  const data = await response.json();
  const embedding = data.data[0].embedding;
  console.log(`Generated ${embedding.length}-dimensional embedding`);
  console.log(`CO2 emissions: ${data.environment_impact.carbon_g_co2.toFixed(2)}g`);
  return embedding;
};

// Batch embeddings example
const createBatchEmbeddings = async () => {
  const texts = [
    'The quick brown fox',
    'jumps over the lazy dog',
    'Hello, world!'
  ];

  const response = await fetch(
    'https://api.melious.ai/v1/embeddings',
    {
      method: 'POST',
      headers: {
        'Authorization': 'Bearer your_api_key',
        'Content-Type': 'application/json'
      },
      body: JSON.stringify({
        model: 'qwen3-embedding-8b',
        input: texts,
        mode: 'price'  // Optimize for lowest cost
      })
    }
  );

  const data = await response.json();
  const embeddings = data.data.map(item => item.embedding);
  console.log(`Generated ${embeddings.length} embeddings`);
  return embeddings;
};

// Example usage
createEmbeddings();
createBatchEmbeddings();

# Single text embedding
curl -X POST "https://api.melious.ai/v1/embeddings" \
  -H "Authorization: Bearer your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-embedding-8b",
    "input": "The quick brown fox jumps over the lazy dog"
  }'

# Batch embeddings with routing
curl -X POST "https://api.melious.ai/v1/embeddings" \
  -H "Authorization: Bearer your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-embedding-8b",
    "input": ["Text 1", "Text 2", "Text 3"],
    "mode": "price",
    "filters": {
      "countries": ["NL", "FR", "DE"],
      "max_input_cost": 1.0
    }
  }'

# Long context embedding
curl -X POST "https://api.melious.ai/v1/embeddings" \
  -H "Authorization: Bearer your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-embedding-8b",
    "input": "Your long document text here..."
  }'