elizaos--eliza/packages/docs/cloud/api/embeddings.mdx

---
title: Embeddings
description: Generate vector embeddings for text using elizaOS Cloud embedding API.
---

# Embeddings

Generate vector embeddings for text to power semantic search and RAG applications.

## Create Embedding

<div className="api-endpoint">
  <span className="method-badge method-badge-post">POST</span>
  <span className="path">/api/v1/embeddings</span>
</div>

Generate vector embeddings for the provided text.

### Request

<Tabs>
  <Tab title="cURL">

```bash
curl -X POST "https://elizacloud.ai/api/v1/embeddings" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": "The quick brown fox jumps over the lazy dog",
    "model": "text-embedding-3-small"
  }'
```
  </Tab>
  <Tab title="JavaScript">

```javascript
const response = await fetch('https://elizacloud.ai/api/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.data[0].embedding);

```
  </Tab>
  <Tab title="Python">

```python
import requests

response = requests.post(
    'https://elizacloud.ai/api/v1/embeddings',
    headers={
        'Authorization': 'Bearer YOUR_API_KEY',
        'Content-Type': 'application/json',
    },
    json={
        'input': 'The quick brown fox jumps over the lazy dog',
        'model': 'text-embedding-3-small',
    }
)

data = response.json()
print(data['data'][0]['embedding'])
```
  </Tab>
</Tabs>

### Parameters

| Parameter         | Type         | Required | Description                                        |
| ----------------- | ------------ | -------- | -------------------------------------------------- |
| `input`           | string/array | ✓        | Text to embed (string or array of strings)         |
| `model`           | string       |          | Embedding model. Default: `text-embedding-3-small` |
| `encoding_format` | string       |          | Output format: `float` or `base64`                 |
| `dimensions`      | integer      |          | Number of dimensions for output                    |

### Response

```json
{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [0.0023, -0.0145, 0.0312, ...],
      "index": 0
    }
  ],
  "model": "text-embedding-3-small",
  "usage": {
    "prompt_tokens": 10,
    "total_tokens": 10
  }
}
```

---

## Batch Embeddings

Embed multiple texts in a single request:

```json
{
  "input": [
    "First sentence to embed",
    "Second sentence to embed",
    "Third sentence to embed"
  ],
  "model": "text-embedding-3-small"
}
```

<Info>
  Batch requests are more efficient. You can embed up to 100 texts per request.
</Info>

---

## Available Models

Embedding model availability and dimensions are deployment-specific. Use
`/api/v1/models`, the API Explorer, or the embeddings response metadata for the
current catalog.

---

## Use Cases

### Semantic Search

```javascript
// Embed your query
const queryResponse = await fetch("https://elizacloud.ai/api/v1/embeddings", {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    input: "How do I reset my password?",
    model: "text-embedding-3-small",
  }),
});

const queryEmbedding = (await queryResponse.json()).data[0].embedding;
// Find similar documents using cosine similarity
```

### Cosine Similarity

```javascript
function cosineSimilarity(a, b) {
  const dotProduct = a.reduce((sum, val, i) => sum + val * b[i], 0);
  const magnitudeA = Math.sqrt(a.reduce((sum, val) => sum + val * val, 0));
  const magnitudeB = Math.sqrt(b.reduce((sum, val) => sum + val * val, 0));
  return dotProduct / (magnitudeA * magnitudeB);
}
```