phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-04 18:13:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into add-mcp-authentication-param

Browse source
This commit is contained in:
Omar Abdelwahab 2025-11-05 14:12:32 -08:00 • committed by GitHub
commit 411b18a90f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
515 changed files with 1213 additions and 370490 deletions
Download patch file Download diff file Expand all files Collapse all files

8
src/llama_stack/providers/remote/inference/watsonx/watsonx.py
View file

@ -283,8 +283,8 @@ class WatsonXInferenceAdapter(LiteLLMOpenAIMixin):
# ...
provider_resource_id = f"{self.__provider_id__}/{model_spec['model_id']}"
if "embedding" in functions:
embedding_dimension = model_spec["model_limits"]["embedding_dimension"]
context_length = model_spec["model_limits"]["max_sequence_length"]
embedding_dimension = model_spec.get("model_limits", {}).get("embedding_dimension", 0)
context_length = model_spec.get("model_limits", {}).get("max_sequence_length", 0)
embedding_metadata = {
"embedding_dimension": embedding_dimension,
"context_length": context_length,
@ -306,10 +306,6 @@ class WatsonXInferenceAdapter(LiteLLMOpenAIMixin):
metadata={},
model_type=ModelType.llm,
)
# In theory, I guess it is possible that a model could be both an embedding model and a text chat model.
# In that case, the cache will record the generator Model object, and the list which we return will have
# both the generator Model object and the text chat Model object. That's fine because the cache is
# only used for check_model_availability() anyway.
self._model_cache[provider_resource_id] = model
models.append(model)
return models