Skip to content

change Model for template rag or other services #1081

Description

@ALutz273

💡 Feature Description

I would like to change the model from the “rag” template. For example, from ibm-granite/granite-3.3-8b-instruct to ibm-granite-4.1-8b or Mistral-Small-3.2-24B-Instruct-2506

################
#### list models ###
################
#-> ai-services application  model list -t rag-cpu  --runtime podman
Models in application template rag-cpu:
- BAAI/bge-reranker-v2-m3 (1)
- ibm-granite/granite-embedding-278m-multilingual (2)
- ibm-granite/granite-3.3-8b-instruct (3)

####################
#### change models ####
####################
ai-services application  model change -m 3 "ibm-granite/granite-4.1-8b" -t rag-cpu  --runtime podman 


❗ Why This Matters

This can make the service faster or better, depending on the use case.

🧩 Requirements

Changes to the ai-services CLI.
Changes defaults of templates.

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or request

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions