Skip to main content
GET
/
api
/
gen-ai
/
beta
/
endpoints
/
{endpointId}
/
versions
/
{versionNumber}
/
realTimeLogs
Get Gen AI Endpoint Version Real Time Logs
curl --request GET \
  --url https://api.example.com/api/gen-ai/beta/endpoints/{endpointId}/versions/{versionNumber}/realTimeLogs \
  --header 'X-Domino-Api-Key: <api-key>'
{
  "isComplete": true,
  "logContent": [
    {
      "log": "<string>",
      "logType": "<string>",
      "size": 123,
      "timestamp": 123
    }
  ],
  "pagination": {
    "latestTime": "<string>",
    "limit": 123,
    "offset": 123
  }
}

Authorizations

​
X-Domino-Api-Key
string
header
required

Path Parameters

​
endpointId
string
required

The id of the endpoint to retrieve real time logs for.

​
versionNumber
integer
required

The version number to retrieve real time logs for.

Query Parameters

​
logType
enum<string>
default:complete

The type of log to retrieve. The available types of logs are: complete - This is the default if the value is not provided. All logs lines displayed in the Model Endpoint Version's runtime environment. stdout - Log lines displayed in the stdout of the Model Endpoint Version's runtime environment. stderr - Log lines displayed in the stderr of the Model Endpoint Version's runtime environment. prepareoutput - Log lines generated by the environment preparing the Model Endpoint Version. Defaults to complete.

Available options:
complete,
prepareoutput,
stdout,
stderr
​
limit
integer
default:10000

The maximum number of result to retrieve. Defaults to 10000.

​
offset
integer
default:0

The offset from the first result. Defaults to 0.

​
latestTime
string
default:0

The epoch timestamp after which to return logs in nanoseconds. Defaults to 0.

Response

Success

​
isComplete
boolean
required
​
logContent
object[]
required
​
pagination
object
required