.webp)
Document Question Answering (DQA) is the task of answering questions based on document images or text. DQA models take a (document, question) pair as input and return an answer in natural language. These models typically rely on multi-modal features, combining text, the position of words, and sometimes images. DQA can be used for tasks such as parsing structured documents, extracting information from forms or tables, and invoice information extraction.
Document Q&A APIs are an expanding market that counts many providers offering those services, but their performance may vary from one provider to another depending on your images. They also have different costs and processing times: it is in your best interest to test a variation of them before choosing the right one.
By aggregating several Document Q&A providers on a single API, Eden AI allows you to use different engines at the same time depending on the type of document you wish to analyse.
You can directly start building now. If you have any questions, don't hesitate to schedule a call with us!
Start buildingBook a demoDrop your email and we'll get back to you ASAP to answer any questions you have or just to say hi —we promise not to spam you!
-p-500.webp){kind=small}
-p-500.webp){kind=small}
