I just went to Bluemix and saw that there is a new experimental service called Discovery. Apparently, it can ingest PDFs, Word Documents, and HTML pages among other file types.
What's the difference between that service and Document Conversion(DC)? Before, I used to convert my documents using DC and then index them in Retrieve and Rank? Is Discovery the merge of Retrieve and Rank and Document Conversion?
The IBM Watson™ Discovery Service uses data analysis combined with cognitive intuition to take your unstructured data and enrich it so you can query it for the information you need. The service enables you to ingest and index content so that you can subsequently use that information to answer queries.
The service is experimental now but the idea is that you will be able to do something similar to what you currently do with Document Conversion and Retrieve and Rank. One of the main benefits is that ingestion and indexing are now managed by the service.
For detailed information, see the documentation.
Note: I work for IBM Watson
