I'm working with Google Auto ML Natural Language API.
I have already a trained model.
In the beginning, when I trained the model, it was deployed and everything was fine. According with Google's new rules from 22th January 2019, models that have no prediction traffic for 7 or more weeks will be silently undeployed and archived.
At moment, I can't predict any result with that trained model, because it is undeployed as it was probably unused for 7 weeks.
Also according to Google if id like to continue using the model I should redeploy it using the Deploy API. https://cloud.google.com/natural-language/automl/docs/models#deploying_or_undeploying_a_model
I try to redeploy the model and I get an error so I can't make any prediction.
How can I deploy a model, without errors, in order to begin predict results?
So, I'll show the steps that I made to try to solve this problem:
- Run deploy request with right data.
- Run operations request
- Wait for deployment to finish
- Run operations request again
- Show list of models that I have (It's UNDEPLOYED)
1 https://automl.googleapis.com/v1beta1/projects/{project}/locations/{location}/models/{Model ID}:deploy
{
"name": "projects/{project}/locations/{location}/operations/{Model ID}",
"metadata": {
"@type": "type.googleapis.com/google.cloud.automl.v1beta1.OperationMetadata",
"createTime": {Time},
"updateTime": {Time}
}
}
2 and 4 https://automl.googleapis.com/v1beta1/projects/{project}/locations/{location}/operations
"operations": [
{
"name": "projects/{project}/locations/{location}/operations/{Model ID}",
"metadata": {
"@type": "type.googleapis.com/google.cloud.automl.v1beta1.OperationMetadata",
"createTime": {Time},
"updateTime": "{Time},
"progressPercent": 100
},
"done": true,
"error": {
"code": 4
}
}
]
5 https://automl.googleapis.com/v1beta1/projects/{project}/locations/{location}/models
"model": [
{
"name": "projects/{project}/locations/{location}/models/{Model ID}",
"displayName": {name},
"datasetId": {dataset id},
"createTime": {time},
"deploymentState": "UNDEPLOYED",
"updateTime": {time},
"textClassificationModelMetadata": {}
}
]
So, I was expecting 0 errors in operations request, when the model finished the deployment progress, but it shows an error code 4. I have searched this error code 4 in this provided enum: https://github.com/googleapis/googleapis/blob/master/google/rpc/code.proto
For error code 4:
// The deadline expired before the operation could complete. For operations
// that change the state of the system, this error may be returned
// even if the operation has completed successfully. For example, a
// successful response from a server could have been delayed long
// enough for the deadline to expire.
//
// HTTP Mapping: 504 Gateway Timeout
DEADLINE_EXCEEDED = 4;
I don't know why this timeout is happening.
I already search in Quotas Limits, but everything is fine.
This problem should be resolved now. Sorry about the inconvenience, but your model should be deployable now. Please try and write back if you still see an issue.