> ## Documentation Index
> Fetch the complete documentation index at: https://nusaai-edit.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Embeddings

> > Convert text into high-dimensional numerical vectors for various AI tasks.

Embeddings are numerical representations of text that capture semantic meaning. They convert human-readable text into high-dimensional vectors that machine learning models can understand and process. These vectors enable tasks such as semantic search, recommendation systems, clustering, and anomaly detection.

## How Embeddings Work

When you send text to the embeddings endpoint, the underlying AI model processes the text and outputs a list of floating-point numbers (a vector). Texts with similar meanings will have vectors that are numerically "closer" to each other in the high-dimensional space.

The Neosantara AI API provides an [`/v1/embeddings`](/api-reference/embeddings/create-embeddings) endpoint to generate these vectors.

## Usage

To generate embeddings, send a POST request to the `/v1/embeddings` endpoint with your text input.

### Endpoint

> POST [https://api.neosantara.xyz/v1/embeddings](https://api.neosantara.xyz/v1/embeddings)

### Request Body

```json theme={null}
{
  "input": "The quick brown fox jumps over the lazy dog.",
  "model": "nusa-embedding-0001",
  "encoding_format": "float"
}
```

See [full reference](/api-reference/embeddings/create-embeddings)

### Supported Embedding Models

The Neosantara AI API supports various embedding models, often utilizing intelligent fallbacks to ensure reliability. Some of the available models include:

* **`nusa-embedding-0001`**: The primary embedding model, offering good performance for general-purpose embeddings.

### Example Response

```json theme={null}
{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [
        0.00539745,
        -0.007137805,
        0.02102179,
        -0.003181825,
        // ... (truncated for brevity)
        -0.010260487
      ],
      "index": 0
    }
  ],
  "model": "nusa-embedding-0001",
  "usage": {
    "prompt_tokens": 9,
    "total_tokens": 9
  }
}
```

## Examples with OpenAI SDK

You can generate embeddings using the OpenAI SDK by configuring its `base_url` to point to the Neosantara AI API.

<CodeGroup>
  ```python Py icon="python" theme={null}
  from openai import OpenAI

  # Replace "YOUR_API_KEY" with your actual Neosantara AI API Key
  client = OpenAI(
      api_key="YOUR_API_KEY",
      base_url="https://api.neosantara.xyz/v1"
  )

  def get_embeddings(texts: list[str], model: str = "nusa-embedding-0001"):
      """
      Generates embeddings for a list of texts using the Neosantara AI API.
      """
      print(f"Generating embeddings for model: {model}")

      try:
          response = client.embeddings.create(
              model=model,
              input=texts,
              encoding_format="float"
          )

          # The response.data contains a list of embedding objects
          # Each object has 'embedding' (the vector) and 'index'
          embeddings = [item.embedding for item in response.data]

          print(f"Generated {len(embeddings)} embeddings. Dimension: {len(embeddings[0]) if embeddings else 0}")
          print(f"Total tokens used: {response.usage.total_tokens}")

          return embeddings

      except Exception as e:
          print(f"An error occurred during embedding generation: {e}")
          return None

  if __name__ == "__main__":
      example_texts = [
          "Artificial intelligence is transforming industries.",
          "Machine learning is a subset of AI.",
          "Deep learning enables neural networks."
      ]
      
      generated_vectors = get_embeddings(example_texts)

      if generated_vectors:
          print("\nFirst embedding vector (truncated):")
          print(generated_vectors[0][:10], "...") # Print first 10 elements
  ```

  ```javascript Js icon="square-js" theme={null}
  import OpenAI from 'openai';

  // Replace "YOUR_API_KEY" with your actual Neosantara AI API Key
  const client = new OpenAI({
    apiKey: "YOUR_API_KEY",
    baseURL: "https://api.neosantara.xyz/v1",
  });

  async function getEmbeddings(texts, model = "nusa-embedding-0001") {
    console.log(`Generating embeddings for model: ${model}`);

    try {
      const response = client.embeddings.create({
        model: model,
        input: texts,
        encoding_format: "float",
      });

      // The response.data contains a list of embedding objects
      // Each object has 'embedding' (the vector) and 'index'
      const embeddings = response.data.map(item => item.embedding);

      console.log(`Generated ${embeddings.length} embeddings. Dimension: ${embeddings[0] ? embeddings[0].length : 0}`);
      console.log(`Total tokens used: ${response.usage.total_tokens}`);

      return embeddings;

    } catch (error) {
      console.error(`An error occurred during embedding generation: ${error.message}`);
      return null;
    }
  }

  // Example usage
  (async () => {
    const exampleTexts = [
      "Artificial intelligence is transforming industries.",
      "Machine learning is a subset of AI.",
      "Deep learning enables neural networks."
    ];
    
    const generatedVectors = await getEmbeddings(exampleTexts);

    if (generatedVectors) {
      console.log("\nFirst embedding vector (truncated):");
      console.log(generatedVectors[0].slice(0, 10), "..."); // Print first 10 elements
    }
  })();
  ```
</CodeGroup>