Currently, paperai uses the standard txtai API when running searches. This method returns the matching index ids. The API should be enriched [similar to what is being done in tldrstory](https://github.com/neuml/tldrstory/blob/master/src/python/tldrstory/api.py) to return more information.