phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-13 19:02:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

style: apply pre-commit fixes

Browse source 
🤖 Applied by @github-actions bot via pre-commit workflow
This commit is contained in:
github-actions[bot] 2025-10-06 08:16:04 +00:00
parent ecafe40a84
commit ca771cd921
2 changed files with 5 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

7
llama_stack/providers/remote/inference/watsonx/watsonx.py
View file

@ -4,7 +4,6 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
import asyncio
from typing import Any
import requests
@ -56,14 +55,14 @@ class WatsonXInferenceAdapter(LiteLLMOpenAIMixin):
async def list_models(self) -> list[Model] | None:
models = []
for model_spec in self._get_model_specs():
functions = [f['id'] for f in model_spec.get("functions", [])]
functions = [f["id"] for f in model_spec.get("functions", [])]
# Format: {"embedding_dimension": 1536, "context_length": 8192}
# Example of an embedding model:
# {'model_id': 'ibm/granite-embedding-278m-multilingual',
# 'label': 'granite-embedding-278m-multilingual',
# 'label': 'granite-embedding-278m-multilingual',
# 'model_limits': {'max_sequence_length': 512, 'embedding_dimension': 768},
# ...
# ...
if "embedding" in functions:
embedding_dimension = model_spec["model_limits"]["embedding_dimension"]
context_length = model_spec["model_limits"]["max_sequence_length"]