> ## Documentation Index
> Fetch the complete documentation index at: https://docs.savegate.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Embeddings

> Create vector embeddings for text

## Overview

Create embeddings for text inputs. Useful for semantic search, clustering, and RAG applications.

## Request

### Body Parameters

<ParamField body="model" type="string" required>
  Embedding model ID (e.g., `text-embedding-3-small`, `text-embedding-ada-002`)
</ParamField>

<ParamField body="input" type="string or array" required>
  Text or array of texts to embed
</ParamField>

<ParamField body="encoding_format" type="string" default="float">
  Format for embeddings (`float` or `base64`)
</ParamField>

## Response

<ResponseField name="object" type="string">
  Object type (always `list`)
</ResponseField>

<ResponseField name="data" type="array">
  Array of embedding objects

  <Expandable title="embedding object">
    <ResponseField name="object" type="string">
      Always `embedding`
    </ResponseField>

    <ResponseField name="embedding" type="array">
      The embedding vector
    </ResponseField>

    <ResponseField name="index" type="integer">
      Index of the embedding
    </ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="model" type="string">
  Model used
</ResponseField>

<ResponseField name="usage" type="object">
  Token usage
</ResponseField>

## Examples

<CodeGroup>
  ```python Python theme={null}
  from openai import OpenAI

  client = OpenAI(
      api_key="sk-savegate-xxxxxxxxxxxxx",
      base_url="https://api.savegate.ai/v1"
  )

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

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

  ```javascript Node.js theme={null}
  import OpenAI from 'openai';

  const client = new OpenAI({
    apiKey: 'sk-savegate-xxxxxxxxxxxxx',
    baseURL: 'https://api.savegate.ai/v1'
  });

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

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

  ```bash cURL theme={null}
  curl https://api.savegate.ai/v1/embeddings \
    -H "Authorization: Bearer sk-savegate-xxxxxxxxxxxxx" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "text-embedding-3-small",
      "input": "Your text here"
    }'
  ```
</CodeGroup>

## Batch Embeddings

```python theme={null}
# Embed multiple texts at once
texts = [
    "First document",
    "Second document",
    "Third document"
]

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

embeddings = [item.embedding for item in response.data]
print(f"Created {len(embeddings)} embeddings")
```

## Supported Models

| Model                    | Dimension | Description            |
| ------------------------ | --------- | ---------------------- |
| `text-embedding-3-small` | 1536      | Latest, most efficient |
| `text-embedding-3-large` | 3072      | Highest quality        |
| `text-embedding-ada-002` | 1536      | Previous generation    |

## Use Cases

<CardGroup cols={2}>
  <Card title="Semantic Search" icon="magnifying-glass">
    Find relevant documents based on meaning
  </Card>

  <Card title="Clustering" icon="layer-group">
    Group similar texts together
  </Card>

  <Card title="RAG Applications" icon="robot">
    Retrieval-augmented generation
  </Card>

  <Card title="Recommendations" icon="star">
    Content recommendation systems
  </Card>
</CardGroup>