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

# Check Connection

> Verifies connectivity to the Ollama server and checks if it's running

## Query Parameters

<ParamField query="baseUrl" type="string">
  Optional Ollama server URL to check (defaults to [http://localhost:11434](http://localhost:11434))
</ParamField>

<ParamField query="apiKey" type="string">
  Optional API key for authentication (if Ollama server requires it)
</ParamField>

## Response

<ResponseField name="success" type="boolean">
  Indicates if the connection check was successful
</ResponseField>

<ResponseField name="connected" type="boolean">
  Whether connection to Ollama was successful
</ResponseField>

<ResponseField name="version" type="string">
  Ollama version if connected
</ResponseField>

<RequestExample>
  ```bash cURL theme={null}
  curl --request GET \
    --url 'http://localhost:3000/api/v1/ollama/check-connection' \
    --header 'Authorization: Bearer <token>'
  ```

  ```bash cURL (Custom Ollama URL) theme={null}
  curl --request GET \
    --url 'http://localhost:3000/api/v1/ollama/check-connection?baseUrl=http://192.168.1.100:11434' \
    --header 'Authorization: Bearer <token>'
  ```

  ```javascript JavaScript theme={null}
  const response = await fetch(
    'http://localhost:3000/api/v1/ollama/check-connection',
    {
      method: 'GET',
      headers: {
        'Authorization': 'Bearer <token>'
      }
    }
  );

  const data = await response.json();
  ```

  ```python Python theme={null}
  import requests

  url = "http://localhost:3000/api/v1/ollama/check-connection"
  headers = {"Authorization": "Bearer <token>"}

  response = requests.get(url, headers=headers)
  data = response.json()
  ```
</RequestExample>

<ResponseExample>
  ```json 200 - Connected theme={null}
  {
    "success": true,
    "connected": true,
    "version": "0.1.22"
  }
  ```

  ```json 200 - Not Connected theme={null}
  {
    "success": true,
    "connected": false
  }
  ```

  ```json 401 - Unauthorized theme={null}
  {
    "success": false,
    "connected": false,
    "error": "Unauthorized"
  }
  ```

  ```json 500 - Connection Failed theme={null}
  {
    "success": false,
    "connected": false,
    "error": "Connection failed: ECONNREFUSED"
  }
  ```
</ResponseExample>

## Notes

<Info>
  Use this endpoint to verify Ollama is running before attempting other operations.
</Info>

* Returns `connected: true` only if Ollama is running and reachable
* The `version` field shows the Ollama server version
* Useful for health checks and setup validation
* Default Ollama URL is `http://localhost:11434`

## Usage Example

```javascript theme={null}
// Check connection before pulling a model
async function safePullModel(modelName) {
  const checkResponse = await fetch(
    'http://localhost:3000/api/v1/ollama/check-connection',
    { headers: { 'Authorization': 'Bearer <token>' } }
  );
  const checkData = await checkResponse.json();
  
  if (!checkData.connected) {
    console.error('Ollama is not running. Please start Ollama first.');
    return;
  }
  
  // Proceed with model pull
  const pullResponse = await fetch(
    'http://localhost:3000/api/v1/ollama/pull-model',
    {
      method: 'POST',
      headers: {
        'Authorization': 'Bearer <token>',
        'Content-Type': 'application/json'
      },
      body: JSON.stringify({ modelName })
    }
  );
  
  return await pullResponse.json();
}
```