SageMaker endpoint AWS Lambda inference Issue

Question

I've deployed a category trained model and hosted the endpoint.. and trying to inference this, but have a issue.. basically we take a short description i.e "laptop screen" this should return a category i.e "Hardware" the problem i'm facing is that i just seem to get this error when inferencing this via postman.

i.e if i send this {"data":"laptop screen"}

i get this error in the body

{
    "errorMessage": "Expecting value: line 1 column 1 (char 0)",
    "errorType": "JSONDecodeError",
    "stackTrace": [
        [
            "/var/task/lambda_function.py",
            21,
            "lambda_handler",
            "result = json.loads(response['Body'].read().decode())"
        ],
        [
            "/var/lang/lib/python3.6/json/__init__.py",
            354,
            "loads",
            "return _default_decoder.decode(s)"
        ],
        [
            "/var/lang/lib/python3.6/json/decoder.py",
            339,
            "decode",
            "obj, end = self.raw_decode(s, idx=_w(s, 0).end())"
        ],
        [
            "/var/lang/lib/python3.6/json/decoder.py",
            357,
            "raw_decode",
            "raise JSONDecodeError(\"Expecting value\", s, err.value) from None"
        ]
    ]
}

this is my lambda function:

import os
import io
import boto3
import json
import csv

ENDPOINT_NAME = os.environ['ENDPOINT_NAME']
runtime= boto3.client('runtime.sagemaker')

def lambda_handler(event, context):
    print("Received event: " + json.dumps(event, indent=2))
    
    data = json.loads(json.dumps(event))
    payload = data['data']
    print(payload)
    response = runtime.invoke_endpoint(EndpointName=ENDPOINT_NAME,
                                        ContentType='text/csv',
                                        Body=payload)
    print(response)
    result = json.loads(response['Body'].read().decode())
    
    return result

Ive added this to admin IAM role too

{
    "Sid": "VisualEditor0",
    "Effect": "Allow",
    "Action": "sagemaker:InvokeEndpoint",
    "Resource": "*"
}

Any assistance would be ace, i feel im pretty close it works fine when it comes to predicting priority, but need help when predicting category string.

For the future, please spend a minute to see how to properly format your code snippets (done it for you this time). — desertnaut
– desertnaut, Commented Jul 21, 2021 at 9:57
In postman, did you try sending {"data":"laptop screen", "content-type": "text/csv"} ? — vmachan
– vmachan, Commented Jul 21, 2021 at 18:11
Hi Bud, cheers for the response, yep i tried this and still throwing the same error? :/ — user203818
– user203818, Commented Jul 22, 2021 at 8:48
can you post the lambda cloudwatch entries? Is there any chance response is empty? — rok
– rok, Commented Jul 22, 2021 at 14:54

Ram Vegiraju · Accepted Answer · 2021-07-22 18:42:51Z

1

For your lambda function, I think the error might be with the way you're passing your payload in, take the following code snippet.

    data = json.loads(json.dumps(event))
    payload = json.dumps(data)
    response = runtime.invoke_endpoint(EndpointName=ENDPOINT_NAME,
                                       ContentType='application/json',
                                       Body=payload)
    result = json.loads(response['Body'].read().decode())

Adjust the payload that you are passing in to use json.dumps() to encode your data properly for the endpoint.

I work for AWS & my opinions are my own

edited Jul 22, 2021 at 18:42

answered Jul 22, 2021 at 17:19

Ram Vegiraju

3793 silver badges5 bronze badges

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

10 Comments

user203818 Over a year ago

Hi Bud, thanks for the heads up.. I tried this when submitting {"data":"laptop screen"}

user203818 Over a year ago

data = json.loads(json.dumps(event)) payload = json.dumps(data) response = runtime.invoke_endpoint(EndpointName=ENDPOINT_NAME, ContentType='text/csv', Body=payload) result = json.loads(response['Body'].read().decode())

user203818 Over a year ago

and got this error {"errorMessage": "Expecting value: line 1 column 1 (char 0)", "errorType": "JSONDecodeError", "stackTrace": [["/var/task/lambda_function.py", 22, "lambda_handler", "result = json.loads(response['Body'].read().decode())"], ["/var/lang/lib/python3.6/json/__init__.py", 354, "loads", "return _default_decoder.decode(s)"], ["/var/lang/lib/python3.6/json/decoder.py", 339, "decode", "obj, end = self.raw_decode(s, idx=_w(s, 0).end())"], ["/var/lang/lib/python3.6/json/decoder.py", 357, "raw_decode", "raise JSONDecodeError(\"Expecting value\", s, err.value) from None"]]}

user203818 Over a year ago

interesting, when i invoke {"data":"laptop screen"} json.dumps(data) does work on a different endpoint with a model to predict a number based on urgency i.e '1-7' this is correct, but when i invoke the same data on an endpoint based on a category label i.e should be returning response as 'Hardware' i get this same error thrown? even after adjusting the payload to use json.dumps()? could it be because i'm trying to predict a label and not a integer?

Ram Vegiraju Over a year ago

I think that might be an issue with your inference code then in the script you're providing or container you're bringing.

|

Collectives™ on Stack Overflow

SageMaker endpoint AWS Lambda inference Issue

1 Answer 1

10 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

10 Comments

Your Answer

Sign up or log in

Post as a guest

Related