[Bug]: All backends using gpt-3.5-turbo as default model

[gyliu513]

Checklist

• I've searched for similar issues and couldn't find anything matching
• I've included steps to reproduce the behavior

Affected Components

• K8sGPT (CLI)
• K8sGPT Operator

K8sGPT Version

v0.3.38

Kubernetes Version

v1.30

Host OS and its Version

No response

Steps to reproduce

gyliu@guangyas-air k8sgpt % ./bin/k8sgpt auth add --backend watsonxai
Warning: model input is empty, will use the default value: gpt-3.5-turbo
Provider with same name already exists.

gyliu@guangyas-air k8sgpt % ./bin/k8sgpt auth add --backend localai
Warning: model input is empty, will use the default value: gpt-3.5-turbo
localai added to the AI backend provider list

From above, we can see both watrsonxai and localai settinng gpt-3.5-turbo as default model, this is not right.

Expected behaviour

Each LLM backend should have its own default model

Actual behaviour

No response

Additional Information

No response

[AlexsJones]

This is certainly something we could change

[AlexsJones]

Can you give us a suggestion on the default models for backends? @gyliu513

[gyliu513]

@AlexsJones As each LLM provider has its own default model, so how about we bind the LLM provider with a default mode, so that when the customer add auth, if they did not specify the model name, we will use the default model bind with the LLM provider, comments? Thanks