# What does this PR do?
It avoids model_limit KeyError while trying to get embedding models for
Watsonx
Closes https://github.com/llamastack/llama-stack/issues/4059
## Test Plan
Start server with watsonx distro:
```bash
llama stack list-deps watsonx | xargs -L1 uv pip install
uv run llama stack run watsonx
```
Run
```python
client = LlamaStackClient(base_url=base_url)
client.models.list()
```
Check if there is any embedding model available (currently there is not
a single one)<hr>This is an automatic backport of pull request #4060
done by [Mergify](https://mergify.com).
Co-authored-by: Wojciech-Rebisz <147821486+Wojciech-Rebisz@users.noreply.github.com>
0899f78943