call sagemaker endpoint using lambda function

Question

I have some data in S3 and I want to create a lambda function to predict the output with my deployed aws sagemaker endpoint then I put the outputs in S3 again. Is it necessary in this case to create an api gateway like decribed in this link ? and in the lambda function what I have to put. I expect to put (where to find the data, how to invoke the endpoint, where to put the data)

Thanks

Julien Simon · Accepted Answer · 2019-02-11 08:40:48Z

4

you definitely don't have to create an API in API Gateway. You can invoke the endpoint directly using the invoke_endpoint() API, passing the endpoint name, the content type, and the payload.

For example:

import boto3

endpoint_name = <INSERT_ENDPOINT_NAME>
runtime = boto3.Session().client(service_name='sagemaker-runtime',region_name='us-east-1')

response = runtime.invoke_endpoint(EndpointName=endpoint_name, ContentType='application/x-image', Body=payload)
print(response['Body'].read())

More examples here using a Lambda function: https://medium.com/@julsimon/using-chalice-to-serve-sagemaker-predictions-a2015c02b033

answered Feb 11, 2019 at 8:40

Julien Simon

2,78913 silver badges21 bronze badges

Sign up to request clarification or add additional context in comments.

2 Comments

Walid Sliti Over a year ago

thank you for your response but that's not exactly my problem can you please see this new issue which more clarify my issue thank you

NMAK Over a year ago

@Julien Simon, Could you please have a look at stackoverflow.com/questions/59379081/… and let know what's going on wrong here. I believe it has to do with JSON request format.

Collectives™ on Stack Overflow

call sagemaker endpoint using lambda function

1 Answer 1

2 Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

2 Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related