IBM Watson™ Discovery Service Ideas

We've moved...

You'll be redirected shortly, we've moved to our new idea portal: https://ibm-watson.ideas.aha.io

1 VOTE

Display correct document names in the SDU interface.

Nokia is using WDS for their HR Chatbot, and trying out long tail search optimisation through SDU. Anyhow, in the SDU UI's dropdown file list, the files uploaded from the CAESAR/SEA (chatbot asset) Admin Panel to Discovery always get "_" as the ex...

Created 4 days ago by Guest

1 Already exists
2 VOTE

Smart Document Understanding returns document structure

Right now, the output of SDU is aggregated into a JSON array. It would be great if SDU could return the parsed structure of the document. This way we can know for sure if this word in the document is a 'Table of Content' type, or 'Subtitle' type....

Created 8 months ago by Guest

1 Already exists
1 VOTE

Add support for the Dutch Language

Today we have support for the Dutch language in Watson Assistant, Watson Knowledge Studio and also in Watson Explorer Content Analytics. For customers moving to the cloud for content exploration and knowledge use cases, support across the productp...

Created 9 months ago by Guest

3 Already exists
1 VOTE

Adding a confirmation layer before deleting a collection

I got this request from a client, who was surprised with the ease of deleting a collection in WDS if you have access to the UI (and I guess with the API too). His questions are:- Is it possible to create some layer of protection to pr...

Created 9 months ago by Guest

1 Already exists
16 VOTE

Allow custom IDs for documents when adding them to the discovery index

Whenever we face discovery setups with multiple stages or environments, its very hard and time consuming to manage multiple copies of the same document as discovery generates a new, different ID for each document in each collection. It would make ...

Created 11 months ago by Robin Rojowiec

1 Already exists
3 VOTE

Remove or Strip HTML tags during ingestion

Affects both ingestion and document conversion / segmentation. Benefits usage of the ingested content making it consumable in a more basic format. Original customer use case was to not only remove / strip HTML but also segment based on HTML he...

Created over 1 year ago by Guest

4 Already exists
3 VOTE

Detail metadata for enriched entities from WKS model

Currently, where is a detail information for enriched relation from WKS model, such as enriched sentences, position of first and second entities of the relation. We would like a similar detail information for enriched entities from WKS model too. ...

Created over 1 year ago by Guest

1 Already exists
2 VOTE

Multiple addition of sample questions in training

Training of Natural Language Query in Discovery: Every sample question for training can be added only once. In a real world scenario with automated feedback, similar questions / training data will be added more than one time only. Right now the...

Created over 1 year ago by Mick Garcia

1 Already exists
10 VOTE

Standard WDS crawler for websites

The standard WDS crawler supports filesystem, sharepoint and databases.Since one of the few document types that WDS can ingest is HTML, it would make sense to have the standard crawler also support HTTP and HTTPS accessible websites. https://bigb...

Created almost 2 years ago by JAYSEN OLLERENSHAW

1 Already exists