Hi everyone,
I have a challenge where I need to classify more than 10 different types of documents. I understand that the traditional Classify Document approach in Appian requires a substantial amount of training data to build an accurate model.
Is it possible to use generative AI (Gen-AI) for document classification in Appian instead? Or is Gen-AI generally not suitable for handling multiple document types like this?
I’m aware that the current Appian AI Skills for document classification do not use Gen-AI, but I wanted to check if there are any alternative approaches or best practices. I also tried using extraction with unstructured Gen-AI for classification, but it turned out to be more complex than I expected—especially converting the output to JSON and so on.
Thanks for any advice or suggestions!ps; currently lacks of documents so i not using the classification document method xD
Discussion posts and replies are publicly visible
In general, you can use gen AI to classify documents. Whether to OOTB Appian services fulfil your specific requirements is a different story. You will probably have to do some research.
Hi Abdul,
Have you tried using the AI Document Center? It has a classification module that allows you to categorize documents using GenAI. This would be an ideal use case for that: https://docs.appian.com/suite/help/25.2/aidc-2.8/classification.html. I do, however, recommend gathering a good dataset of different document types so that you can cover edge cases but this should be help you get started.