AWS Document Understanding Reference App

This reference application helps to understand the contents of general documents (PDF, image, audio, video, text). These integrations can be easily embedded into any Appian applications, not only perform the task of understanding the context of the uploaded document, but also provide a seamless user experience.

• It uses AWS Textract to extract the text line block out of pdf or image file, and use AWS Comprehend to analyze the text to detect key phrases.
• Additional Textract APIs for Identification Document Extraction, and Query PDF document.
• For audio (mp3) and video (mp4) media file, the app will use AWS Transcribe to generate a text transcription from the media file.
• For image file, the app will use AWS Rekognition to detect key objects from the image, a sample use case is if a gun detected from the image, take actions accordingly.
• Comprehend NLP service to uncover insights and connections in Text file.
• When click "End" button, it will delete the uploaded file from both Appian and AWS S3

Added Textract Identification extraction, Textract Query feature, and Comprehend service integration