[New Feature]: Multiple AI Model Support

[riverma]

Checked for duplicates

Yes - I've already checked

Alternatives considered

Have you considered alternative solutions to your feature request?

Yes - and alternatives don't suffice

Related problems

Is your feature request related to any problems? Please help us understand if so, including linking to any other issue tickets.

Currently only a single model is supported at a time, even if the model is not accessible to the user.

Describe the feature request

A clear and concise description of your request.

It'd be great to have the following type of user interaction:

python slim-cli.py ... --use-ai <MODEL_ID>

Where, <MODEL_ID> is one of:

• openai-chatgpt4o
• azure-chatgpt4o
• llama3.1-70b
• llama3.1-400b

For each of the above, there should be a check to ensure required environment variables are set, and if they are not, the program should exit. For example, the first model, the environment variable OPENAI_KEY should be set.

Additionally, the argparse usage and the README should document the models and when to use which.

[yunks128]

This is integrated, and an error message is included when OPENAI_KEY is missing.
Example:

python slim-cli.py ... --use-ai openai/gpt-4o
python slim-cli.py ... --use-ai azure/gpt-4o
python slim-cli.py ... --use-ai ollama/llama3.1:70b