This portal is to open public enhancement requests against products and services offered by the IBM Data & AI organization. To view all of your ideas submitted to IBM, create and manage groups of Ideas, or create an idea explicitly set to be either visible by all (public) or visible only to you and IBM (private), use the IBM Unified Ideas Portal (https://ideas.ibm.com).
Shape the future of IBM!
We invite you to shape the future of IBM, including product roadmaps, by submitting ideas that matter to you the most. Here's how it works:
Search existing ideas
Start by searching and reviewing ideas and requests to enhance a product or service. Take a look at ideas others have posted, and add a comment, vote, or subscribe to updates on them if they matter to you. If you can't find what you are looking for,
Post your ideas
Post ideas and requests to enhance a product or service. Take a look at ideas others have posted and upvote them if they matter to you,
Post an idea
Upvote ideas that matter most to you
Get feedback from the IBM team to refine your idea
Specific links you will want to bookmark for future use
Welcome to the IBM Ideas Portal (https://www.ibm.com/ideas) - Use this site to find out additional information and details about the IBM Ideas process and statuses.
IBM Unified Ideas Portal (https://ideas.ibm.com) - Use this site to view all of your ideas, create new ideas for any IBM product, or search for ideas across all of IBM.
ideasibm@us.ibm.com - Use this email to suggest enhancements to the Ideas process or request help from IBM for submitting your Ideas.
IBM Employees should enter Ideas at https://ideas.ibm.com
See this idea on ideas.ibm.com
As users of the Wastonx AI platform, most of the time we use the watsonx python SDK to call the model API. Support case CS4244931
Currently:
Now, we can see the deprecation as well as removal details of a particular model from the Watsonx UI in prompt lab.
As a user, I can see all these informations in the prompt lab.
Its a manual process to open prompt lab and perceive it.
Problem:
But all these deprecation warning, removal date are not received in the downstream API call via cURL or Python SDK, which makes it difficult o keep a track for the LLM that's getting deprecated. Since, no precaution is received we still continue to use the old model, and when its removed, all the downstream application starts failing with escalation in process.
Solution:
Adding the Warning/notice when using the SDK to call.
This warning can be sent as a metadata, and in doing so, it helps in being ready for the removal or change the models in configurations with safe time in hand.
Needed By | Month |
By clicking the "Post Comment" or "Submit Idea" button, you are agreeing to the IBM Ideas Portal Terms of Use.
Do not place IBM confidential, company confidential, or personal information into any field.
This is a good RFE. The caveat is that output of API calls are not often monitored and warning/message at API level may also go unnoticed.
1) One of the way notifications can be sent are by opt-in process at watsonx.ai instance level configuration in IBM Cloud for future updates/notifications.
2) Additionally, this instance configuration can list all the models supported by watsonx.ai and instance owner/admin can check which model they plan to use from the list. The opt-in notification can trigger notifications only for the models they selected and not for the entire spectrum of models available whether they are used or not.
3) This can list can also show (Deprecated on <date>) with the name of the model name as well so developers/admin do not select those models proactively.