IBM Watson™ Discovery Service Ideas

While building solutions for enterprise customers, I need the ability to limit certain documents or portions of documents to end-users. I would like Discovery to get the ACLs from the source document store, and apply those ACLs at search time to ...

It would be handy to be able to delete documents from a collection by defining conditions. Something I would do in a sql-database like this: DELETE FROM collection_name WHERE publication_date < date('2018-01-01')

Our project would quite certainly benefit from using the bias parameter in querys: rather that using a hard filter based on some metadata value, we would like to weigh some metadata values more in certain cases. However, our metadata values are mo...

It would be nice if also passages can show the relevant keywords for the search. Normally in the UI I would just show the passages and would be nice to show where the search result come from

Hi! Our offering (Equipment Maintenancne Assistant) embeds Watson Discovery. The EMA DevOps team indirectly provisions WDS instances. Currently, once the plan is upgraded from WDS lite to advanced, there is no way to downgrade customer plans witho...

Currently, on the Discovery Catalog page the metrics are separated from the price. For example, when I expand Up to 1M docs $500/ instance/month is displayed. I have to scroll down to see $1,500/instance/month. They only way I know up to 1M i...

We have a JSON file containing all the needed natural language queries and examples for training WDS collection. It would be helpful if there is a way to upload these bulk of queries at the same time to WDS.

When iterating in Discovery, especially when experimenting with multiple and more complex queries it would be very useful to be able to save my query once I have it in suitable shape so I can iterate on another one without losing my work.

The current stemming approach used for Italian language misses some patterns for plurals e.g. (visti, visto). Look into improvements that can capture more of these patterns.

Annotation of semantic meaning of text within tables utilizing headers for context