fix: use ollama list to find models

[mattf]

What does this PR do?

closes #1853

Test Plan

uv run llama stack build --image-type conda --image-name ollama --config llama_stack/templates/ollama/build.yaml

ollama pull llama3.2:3b

LLAMA_STACK_CONFIG=http://localhost:8321 uv run pytest tests/integration/inference/test_text_inference.py -v --text-model=llama3.2:3b

[raghotham]

Can we then make sure the model is running when inference calls are made?

[mattf]

Can we then make sure the model is running when inference calls are made?

ollama will automatically start the requested model in response to a /api/chat request

[leseb]

I'm not sure this is right.

[leseb]

Could please add a comment in the code to explain Ollama's behavior we just discussed? Thanks!

[mattf]

Could please add a comment in the code to explain Ollama's behavior we just discussed? Thanks!

@leseb ptal

[mattf]

@leseb the ci failure looks transient, please rerun