AWS costum entity recognition: Wrong ARN-Endpoint

Question

I try to use the custom entity recognition I just trained on Amazon Web Service (AWS). The training worked so far:

However, if i try to recognize my entities with AWS Lambda (code below) with the given ARN-Endpoint I get the following error (even tho AWS should use the latest Version of the botocore/boto3 framework "EntpointArn" is not available (Docs)):

Response:
{
  "errorMessage": "Parameter validation failed:\nUnknown parameter in input: \"EndpointArn\", must be one of: Text, LanguageCode",
  "errorType": "ParamValidationError",
  "stackTrace": [
    "  File \"/var/task/lambda_function.py\", line 21, in lambda_handler\n    entities = client.detect_entities(\n",
    "  File \"/var/runtime/botocore/client.py\", line 316, in _api_call\n    return self._make_api_call(operation_name, kwargs)\n",
    "  File \"/var/runtime/botocore/client.py\", line 607, in _make_api_call\n    request_dict = self._convert_to_request_dict(\n",
    "  File \"/var/runtime/botocore/client.py\", line 655, in _convert_to_request_dict\n    request_dict = self._serializer.serialize_to_request(\n",
    "  File \"/var/runtime/botocore/validate.py\", line 297, in serialize_to_request\n    raise ParamValidationError(report=report.generate_report())\n"
  ]
}

I fixed this error with the first 4 lines in my code:

#---The hack I found on stackoverflow----
import sys
from pip._internal import main

main(['install', '-I', '-q', 'boto3', '--target', '/tmp/', '--no-cache-dir', '--disable-pip-version-check'])
sys.path.insert(0,'/tmp/')

#----------------------------------------

import json
import boto3

client = boto3.client('comprehend', region_name='us-east-1')

text = "Thats my nice text with different entities!"

entities = client.detect_entities(
            Text = text,
            LanguageCode = "de", #If you specify an endpoint, Amazon Comprehend uses the language of your custom model, and it ignores any language code that you provide in your request.
            EndpointArn = "arn:aws:comprehend:us-east-1:215057830319:entity-recognizer/MyFirstRecognizer"
)

However, I still get one more error I cannot fix:

Response:
{
  "errorMessage": "An error occurred (ValidationException) when calling the DetectEntities operation: 1 validation error detected: Value 'arn:aws:comprehend:us-east-1:XXXXXXXXXXXX:entity-recognizer/MyFirstRecognizer' at 'endpointArn' failed to satisfy constraint: Member must satisfy regular expression pattern: arn:aws(-[^:]+)?:comprehend:[a-zA-Z0-9-]*:[0-9]{12}:entity-recognizer-endpoint/[a-zA-Z0-9](-*[a-zA-Z0-9])*",
  "errorType": "ClientError",
  "stackTrace": [
    "  File \"/var/task/lambda_function.py\", line 25, in lambda_handler\n    entities = client.detect_entities(\n",
    "  File \"/tmp/botocore/client.py\", line 316, in _api_call\n    return self._make_api_call(operation_name, kwargs)\n",
    "  File \"/tmp/botocore/client.py\", line 635, in _make_api_call\n    raise error_class(parsed_response, operation_name)\n"
  ]
}

This error also occurs if I use the NodeJS framework with the given endpoint. The funny thing I should mention is that every ARN-Endpoint I found (in tutorials) looks exactly like mine and do not match with the regex-pattern returned as error.

I'm not quite sure if I do something wrong here or if it is a bug on the AWS-Cloud (or SDK).. Maybe somebody can reproduce this error and/or find a solution (or even a hack) for this problem

Cheers

Answer 1

Endpoint ARN are different AWS resource as compared to Model ARN. Model ARN refers to a custom model while endpoint hosts that model. In your code, your code you are passing in the modelARN instead of endpointARN which is causing the error to be raised.

You can differentiate between the two ARNs on the basis of the prefix.

endpoint arn - arn:aws:comprehend:us-east-1:XXXXXXXXXXXX:entity-recognizer-endpoint/xxxxxxxxxx

model arn - arn:aws:comprehend:us-east-1:XXXXXXXXXXXX:entity-recognizer/MyFirstRecognizer

You can read more about Comprehend custom endpoints and its pricing on the documentation page. https://docs.aws.amazon.com/comprehend/latest/dg/detecting-cer-real-time.html