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

# Log embedding models

> Learn how to log embedding models.

In Keywords AI, you can log outputs of embedding models. This is useful for a variety of use cases, such as semantic search, clustering, and more.

You can use the same API endpoint to log embedding models.

```
https://api.keywordsai.co/api/request-logs/create/
```

**Here is an example of how to log an embedding model.**

<CodeGroup>
  ```python Python theme={"system"}
  import requests

  url = "https://api.keywordsai.co/api/request-logs/create/"
  headers = {
      "Authorization": "Bearer YOUR_KEYWORDS_AI_API_KEY",
      "Content-Type": "application/json"
  }
  payload = {
      "latency": 0.323887338,
      "embedding": [
          -0.006929283495992422,
          -0.005336422007530928,
          -4.547132266452536e-05,
          -0.024047505110502243
      ],
      "log_type": "embedding",
      "model": "text-embedding-3-small",
      "input": "something to embed"
  }
  response = requests.request("POST", url, headers=headers, json=payload)
  ```

  ```typescript Typescript theme={"system"}
  const url = 'https://api.keywordsai.co/api/request-logs/create/';
  const headers = {
      'Authorization': 'Bearer YOUR_KEYWORDS_AI_API_KEY',
      'Content-Type': 'application/json'
  };

  const payload = {
      latency: 0.323887338,
      embedding: [
          -0.006929283495992422,
          -0.005336422007530928,
          -4.547132266452536e-05,
          -0.024047505110502243
      ],
      log_type: 'embedding',
      model: 'text-embedding-3-small',
      input: 'something to embed'
  };

  fetch(url, {
      method: 'POST',
      headers: headers,
      body: JSON.stringify(payload)
  })
  .then(response => response.json())
  .then(data => {
      console.log(data);
  })
  ```
</CodeGroup>