AWS AI Services
Understand the variety of AI services available through AWS, and how they can be used, through code and in the AWS Console.
Amazon AI services include a wide variety of pre-trained tools for developers to integrate AI functionality without having to understand the details of ML algorithms.
Many of the available AWS AI services are used by Amazon’s e-commerce site, so the deep-learning algorithms can be continuously updated based on new training data managed by AWS.
There are services to convert text to speech and vice versa (Amazon Polly, Amazon Transcribe), use AI in chatbots (Amazon Lex), analyze visual data (Amazon Rekognition), process text (Amazon Comprehend), and translate text (Amazon Translate).
Note: Other cloud-computing platforms, including Google Cloud and Microsoft Azure, also have pre-trained AI and ML models that can be used to benchmark the quality of the available AWS AI services.
Some available AWS AI services
The below table lists some available AWS AI services according to how they can be used:
Category | Use Case | Service |
Computer vision | Analyze images and videos | Amazon Rekognition |
Detect defects and automate inspection | Amazon Lookout for Vision | |
Utilize computer vision at the edge | AWS Panorama | |
Automated data extraction and analysis | Extract text and data | Amazon Textract |
Acquire insights from text | Amazon Comprehend | |
Control quality of automation | Amazon Augmented AI | |
Language AI | Build chatbots and virtual agents | Amazon Lex |
Automate speech recognition (speech-to-text) | Amazon Transcribe | |
Give apps a voice (text-to-speech) | Amazon Polly | |
Improve customer experience | Find accurate information faster (using natural-language search) | Amazon Kendra |
Personalize online experiences | Amazon Personalize | |
Engage audiences in every language | Amazon Translate | |
Business metrics | Forecast business metrics | Amazon Forecast |
Detect online fraud | Amazon Fraud Detector | |
Identify data anomalies | Amazon Lookout for Metrics | |
Code and DevOps | Improve application availability | Amazon DevOps Guru |
Automated code reviews | Amazon CodeGuru Reviewer | |
Eliminate costly, inefficient code | Amazon CodeGuru Profiler | |
Industrial AI | Detect abnormal machine conditions | Amazon Lookout for Equipment |
Predictive maintenance | Amazon Monitron | |
Healthcare | Store and analyze health data | Amazon Healthlake |
Extract health data | Amazon Comprehend Medical |
Using an AWS AI service from code
Let’s pick an AWS AI service and consider how we can use it from Python code. In the code example below, we use Amazon Comprehend through the boto3 Python library from AWS. The code is designed to detect the language of the text contained in sample.txt. We then use the pycountry library to display the detected language(s), along with an accuracy score from Amazon Comprehend’s ML model.
To run the Python code below successfully, change the values in config.env to correspond to an accessible AWS account.
AWS_ACCESS_KEY_ID={{aws_access_key}}AWS_SECRET_ACCESS_KEY={{aws_secret_access_key}}AWS_REGION=us-east-1