Batch

Launch a batch workflow

Pre-requisites

Minio should already be installed with Seldon Deploy. The minio browser should be exposed on /minio/. For a managed trial cluster by default the credentials will be as per the deploy login.

On a production cluster the namespace needs to have been setup with a service account. This is documented under Getting Started > Product Installation > Argo

Iris Model

iris

We will:

  • Deploy a pretrained sklearn iris model
  • Run a batch job to get predictions
  • Check the output

Deploy Model

deploy1

Use the model uri:

gs://seldon-models/sklearn/iris

Setup Input Data

Download the input data file.

Go to the minio browser and use the button in the bottom-right to create a bucket. Call it data.

createbucket

Again from the bottom-right choose to upload the input-data.txt file to the data bucket.

uploadfile

Run a Batch Job

Go to ‘Batch Jobs’ in the middle-right under the text ‘Initiate or get the status of batch requests’. Create a batch job with parameters:

Input Data Location: s3://data/input-data.txt
Output Data Location: s3://data/output-data-{{workflow.name}}.txt
Number of Workers: 15
Number of Retries: 3
Method: Predict
Transport Protocol: REST
Input Data Type: ndarray
Object Store Secret Name: seldon-job-secret

batchjobdetails

Here ‘seldon-job-secret’ is a pre-created secret in the namespace containing env vars

Give the job 1-2 minutes to complete. Then refresh the page to see the status.

batchjobstatus

In minio you should now see an output file:

miniooutput

If you open that file you should see contents such as:

{"data": {"names": ["t:0", "t:1", "t:2"], "ndarray": [[0.0006985194531162841, 0.003668039039435755, 0.9956334415074478]]}, "meta": {"requestPath": {"iris-container": "seldonio/sklearnserver:1.5.0-dev"}, "tags": {"tags": {"batch_id": "8a8f5e26-2b44-11eb-8723-ae3ff26c8be6", "batch_index": 3.0, "batch_instance_id": "8a8ff94e-2b44-11eb-b8d0-ae3ff26c8be6"}}}}
{"data": {"names": ["t:0", "t:1", "t:2"], "ndarray": [[0.0006985194531162841, 0.003668039039435755, 0.9956334415074478]]}, "meta": {"requestPath": {"iris-container": "seldonio/sklearnserver:1.5.0-dev"}, "tags": {"tags": {"batch_id": "8a8f5e26-2b44-11eb-8723-ae3ff26c8be6", "batch_index": 6.0, "batch_instance_id": "8a903666-2b44-11eb-b8d0-ae3ff26c8be6"}}}}
{"data": {"names": ["t:0", "t:1", "t:2"], "ndarray": [[0.0006985194531162841, 0.003668039039435755, 0.9956334415074478]]}, "meta": {"requestPath": {"iris-container": "seldonio/sklearnserver:1.5.0-dev"}, "tags": {"tags": {"batch_id": "8a8f5e26-2b44-11eb-8723-ae3ff26c8be6", "batch_index": 1.0, "batch_instance_id": "8a8fbe98-2b44-11eb-b8d0-ae3ff26c8be6"}}}}

If not, see the argo section for troubleshooting.


Last modified May 25, 2021