phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-03 18:00:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix model_limits KeyError

Browse source
This commit is contained in:
Wojciech-Rebisz 2025-11-04 10:56:56 +01:00
parent d45137a399
commit 13142267be
2 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/llama_stack/providers/inline/agents/meta_reference/agent_instance.py
View file

@ -1016,7 +1016,7 @@ async def load_data_from_url(url: str) -> str:
async with httpx.AsyncClient() as client: async with httpx.AsyncClient() as client:
r = await client.get(url) r = await client.get(url)
resp = r.text resp = r.text
return resp return str(resp)
raise ValueError(f"Unexpected URL: {type(url)}") raise ValueError(f"Unexpected URL: {type(url)}")

4
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']}" provider_resource_id = f"{self.__provider_id__}/{model_spec['model_id']}"
if "embedding" in functions: if "embedding" in functions:
embedding_dimension = model_spec["model_limits"]["embedding_dimension"] embedding_dimension = model_spec.get("model_limits", {}).get("embedding_dimension", 0)
context_length = model_spec["model_limits"]["max_sequence_length"] context_length = model_spec.get("model_limits", {}).get("max_sequence_length", 0)
embedding_metadata = { embedding_metadata = {
"embedding_dimension": embedding_dimension, "embedding_dimension": embedding_dimension,
"context_length": context_length, "context_length": context_length,