Function Code and JSON prompt for tutorial from Rob Shocks on AWS LLAMA 2

gistfile1.txt

## LAMNDA FUNCTION lambda_function.py

import boto3
import json

# grab environment variables
ENDPOINT_NAME = "jumpstart-dft-meta-textgeneration-llama-2-7b-rs"
runtime= boto3.client('runtime.sagemaker')

def lambda_handler(event, context):
    
    response = runtime.invoke_endpoint(EndpointName=ENDPOINT_NAME,
                                       ContentType='application/json',
                                       Body=event['body'],
                                       CustomAttributes="accept_eula=true")
    
    response_content = response['Body'].read().decode()
    result = json.loads(response_content)
    
    
    return {
        "statusCode": 200,
        "body": json.dumps(result)
    }
 
 ## POSTMAN JSON PAYLOAD
 
 {
    "inputs": [
        [
            {"role": "system", "content": "You are an expert in copywriting"},
            {"role": "user", "content": "Write me a tweet about super conductors"}
        ]
    ],
    "parameters": {"max_new_tokens": 256, "top_p": 0.9, "temperature": 0.6}
}

 
    

Hey, I get this error when running this code into a deployed AWS Sagemaker endpoint, can you help ? - '''[ERROR] ModelError: An error occurred (ModelError) when calling the InvokeEndpoint operation: Received client error (422) from primary with message "Failed to deserialize the JSON body into the target type: inputs: invalid type: sequence, expected a string at line 2 column 11".
Traceback (most recent call last):
  File "/var/task/lambda_function.py", line 11, in lambda_handler
    response = runtime.invoke_endpoint(EndpointName=ENDPOINT_NAME,
  File "/var/runtime/botocore/client.py", line 530, in _api_call
    return self._make_api_call(operation_name, kwargs)
  File "/var/runtime/botocore/client.py", line 960, in _make_api_call
    raise error_class(parsed_response, operation_name)'''

{"inputs":"what is an abacus?",
"parameters": {"max_new_tokens": 128, "top_p": 0.9, "temperature": 1}
}

Try this idk why the role user format is not working with sage endpoint.

Hey, I get this error when running this code into a deployed AWS Sagemaker endpoint, can you help ? - '''[ERROR] ModelError: An error occurred (ModelError) when calling the InvokeEndpoint operation: Received client error (422) from primary with message "Failed to deserialize the JSON body into the target type: inputs: invalid type: sequence, expected a string at line 2 column 11". Traceback (most recent call last):   File "/var/task/lambda_function.py", line 11, in lambda_handler     response = runtime.invoke_endpoint(EndpointName=ENDPOINT_NAME,   File "/var/runtime/botocore/client.py", line 530, in _api_call     return self._make_api_call(operation_name, kwargs)   File "/var/runtime/botocore/client.py", line 960, in _make_api_call     raise error_class(parsed_response, operation_name)'''