IBM Data and AI

Welcome to the IBM Data and AI Ideas Portal for Clients!

We welcome and appreciate your feedback on IBM Data and AI Products to help make them even better than they are today!
Before you submit an idea, please perform a search first as a similar idea may have already been reported in the portal. If a related idea is not yet listed, please create a new idea and include with it a description which includes expected behavior as well as why having this feature would improve the service and how it would address your use case.
IBM Employees:
Clients:
  • Our team welcomes any feedback and suggestions you have for improving our offerings / products! This forum allows us to connect your offering / product improvement ideas with IBM product and engineering teams.

  • If you have not registered on this portal please click on the following link and register. To complete registration you will need to open the email you will receive from Aha to confirm your identity. http://ibm.biz/IBM-Data-and-AI-Portal-Register

Additional Information:
  • The shorter URL for this site is: https://ibm.biz/IBM-Data-and-AI-Ideas

  • To view our roadmaps: http://ibm.biz/Data-and-AI-Roadmaps

  • Reminder: This is not the place to submit defects or support needs, please use normal support channel for these cases

  • Please do not use the Ideas Portal for reporting bugs - we ask that you report bugs or issues with the product by contacting IBM support.

Ability to Split Documents At Ingest Time

It would be useful to be able to provide Discovery logic that would allow it to split one ingested document into multiple indexed documents.  For example, make every paragraph or page a single Discovery document.

  • Avatar32.5fb70cce7410889e661286fd7f1897de Guest
  • Jun 5 2017
  • Delivered
Who would benefit from this IDEA? As Deb, I want to create answers from our FAQ for questions people are asking my chat bot
Idea Priority Medium
  • Attach files
  • Avatar40.8f183f721a2c86cd98fddbbe6dc46ec9
    Guest commented
    12 Dec, 2017 05:37am

    Is there an expectation to add configuring of splitting into the Discovery Tool?  So setting up splitting would happen in the UI rather than using the API...?

  • Avatar40.8f183f721a2c86cd98fddbbe6dc46ec9
    Guest commented
    3 Oct, 2017 04:53pm

    thanks, @James Anderson !

  • Admin
    Phil Anderson commented
    3 Oct, 2017 04:48pm

    Yes, you can read the docs here: https://console.bluemix.net/docs/services/discovery/building.html#doc-segmentation and the announcement here https://apps.na.collabserv.com/blogs/152f58a2-3bb3-4992-86a7-c56ad4bbd21c/entry/Document_Splitting_answer_units_Beta_Released?lang=en_us

  • Avatar40.8f183f721a2c86cd98fddbbe6dc46ec9
    Guest commented
    3 Oct, 2017 04:41pm

    @James Anderson

    Do we have some document/info about this feature?

     

    thanks!

  • Admin
    Phil Anderson commented
    3 Oct, 2017 04:35pm

    This is now in Production (in beta)

  • Avatar40.8f183f721a2c86cd98fddbbe6dc46ec9
    Guest commented
    25 Jul, 2017 04:46am

    have we got some update on this requirement?

    thanks!

  • Avatar40.8f183f721a2c86cd98fddbbe6dc46ec9
    Guest commented
    20 Jul, 2017 03:31pm

    Along with splitting the document, there is also a need to have HTML version of the text in another field (can be made optional). When we split using Document Conversion as answer units, everything becomes plain text. So even if there is a table or list, it all becomes mixed up.

    Idea is to having a "html" field along with "text" field in the json, just like it is having when we upload html file.

     

     

  • Admin
    Phil Anderson commented
    30 Jun, 2017 12:29pm

    Hi Senthil, no need to type +1, just ensure you click the vote button, which actually gives this a plus one :)

NOTICE TO EU RESIDENTS: per EU Data Protection Policy, if you wish to remove your personal information from the IBM ideas portal, please login to the ideas portal using your previously registered information then change your email to "anonymous@euprivacy.out" and first name to "anonymous" and last name to "anonymous". This will ensure that IBM will not send any emails to you about all idea submissions