AWS Notebook Instance is working but Lambda is not accepting the input - tensorflow

Question

I developed an ANN tool by using pycharm/tensorflow on my own computer. I uploaded the h5 and json files to Amazon Sagemaker by creating a Notebook Instance. I was finally able to successfully create an endpoint and make it work. The following code in Notebook Instance -Jupyter works:
import json
import boto3
import numpy as np
import io
import sagemaker
from sagemaker.tensorflow.model import TensorFlowModel
client = boto3.client('runtime.sagemaker')
data = np.random.randn(1,6).tolist()
endpoint_name = 'sagemaker-tensorflow-**********'
response = client.invoke_endpoint(EndpointName=endpoint_name, Body=json.dumps(data))
response_body = response['Body']
print(response_body.read())
However, the problem occurs when I created a lambda function and call the endpoint from there. The input should be a row of 6 features -that is a 1-by-6 vector. I enter the following input into lambda {"data":"1,1,1,1,1,1"} and it gives me the following error:
Traceback (most recent call last):
File "/var/task/lambda_function.py", line 20, in lambda_handler
Body=payload)
File "/var/runtime/botocore/client.py", line 316, in _api_call
return self._make_api_call(operation_name, kwargs)
File "/var/runtime/botocore/client.py", line 635, in _make_api_call
raise error_class(parsed_response, operation_name)
I think the problem is that the input needs to be 1-by-6 instead of 6-by-1 and I don't know how to do that.

Answer 1

I assume the content type you specified is text/csv, so try out:
{"data": ["1,1,1,1,1,1"]}