GET /ai/deployment/{id}/logs

Return logs for the vLLM deployment (deploy/--deployment-vllm). Optional ?stream=true to request streaming (may not be supported).

Path parameters

  • id string(uuid) Required

Responses

  • 200 application/json

    200

    Hide response attribute Show response attribute object
    • logs array[object]

      List of log entries

      A single log entry

      Hide logs attributes Show logs attributes object
      • time string

        Timestamp of the log entry

      • message string

        Log message content

      • node string

        Node identifier
  • 400 application/json

    400

    Hide response attribute Show response attribute object
    • error string

      Error description
  • 404 application/json

    404

    Hide response attribute Show response attribute object
    • error string

      Error description
  • 500 application/json

    500

    Hide response attribute Show response attribute object
    • error string

      Error description
GET /ai/deployment/{id}/logs 
curl \
 --request GET 'https://api-ch-gva-2.exoscale.com/v2/ai/deployment/{id}/logs'
Response examples (200) 
{
  "logs": [
    {
      "time": "string",
      "message": "string",
      "node": "string"
    }
  ]
}
Response examples (400) 
{
  "error": "string"
}
Response examples (404) 
{
  "error": "string"
}
Response examples (500) 
{
  "error": "string"
}