fix: return result for together's get_params (#1484)

# What does this PR do?

- return results for together's get_params
- fix issue
<img width="1538" alt="image"
src="https://github.com/user-attachments/assets/c4cd3802-85ef-4ff3-b2fd-76737be2e4ff"
/>

- the `return params` was accidentally deleted in
https://github.com/meta-llama/llama-stack/pull/1362/files#diff-d9345410ea64589cee96487b22eab0d45f7497a80c25dca295cecd254decb204

[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])

## Test Plan
```
npm test examples
```


[//]: # (## Documentation)
This commit is contained in:
Xi Yan 2025-03-07 12:52:26 -08:00 committed by GitHub
parent 1257288361
commit 5a2b9e121c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -32,9 +32,7 @@ from llama_stack.apis.inference import (
)
from llama_stack.distribution.request_headers import NeedsRequestProviderData
from llama_stack.log import get_logger
from llama_stack.providers.utils.inference.model_registry import (
ModelRegistryHelper,
)
from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper
from llama_stack.providers.utils.inference.openai_compat import (
convert_message_to_openai_dict,
get_sampling_options,
@ -227,6 +225,7 @@ class TogetherInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProvi
**self._build_options(request.sampling_params, request.logprobs, request.response_format),
}
logger.debug(f"params to together: {params}")
return params
async def embeddings(
self,