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
This topic is about too many endpoint for inferencing in foundation models through watsonx which makes application development harder to do.
We are facing a big workload with a customer (Banco do Brasil) due to too many endpoint for inferencing watsonx.ai models. The client needs chat endpoint and we had to create a transformation layer to convert text generation APIs to chat generation APIs. The main workload is in the tags required for each model architecture (example: llama need a kind of tags for chat application, mistral other, granite other, etc) and the management of deployed models. Because they are deployed models but each application (agent, byom, prompt) has a different endpoint.
For BYOM the endpoint is (Completion endpoint – to use in chat application you must to perform all prompt transformation based on the model architecture. If you are using multiple models you must to build prompt transformation for every single architecture)): https://us-south.ml.cloud.ibm.com/ml/v1/deployments/{deploy_id}/text/generation?version=2021-05-01
For Agents deployed the endpoint is (already a chat endpoint why to create a new one? Why not a text/chat endpoint with deployment id as a parameter?): https://us-south.ml.cloud.ibm.com/ml/v4/deployments/{deploy_id}/ai_service?version=2021-05-01
For default models text generation: https://us-south.ml.cloud.ibm.com/ml/v1/text/generation?version=2023-05-29
For default models text chat: https://us-south.ml.cloud.ibm.com/ml/v1/text/chat?version=2023-05-29
PS: As we can see in the development hub there is a chat endpoint where I can perform tool calling: https://www.ibm.com/watsonx/developer/
It should be only two endpoints:
1 – text generation, only for models that is impossible to perform chat generation.
2- chat generation, for all models where is possible to perform chat generation even when the customer needs a single iteration with the model (one user input, one assistant output and a system input if required). For BYOM models we can use the chat structure based on the model architecture and deployment can be a parameter just as model is. The same should be considered for agent deployment and prompt deployment.
Needed By | Yesterday (Let's go already!) |
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.