phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-03 09:53:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

further fixes according to investigation and PR comments

Browse source
This commit is contained in:
r-bit-rry 2025-11-30 17:31:07 +02:00
parent 9b3c041af0
commit c3c9edf981
14 changed files with 212 additions and 30 deletions
Download patch file Download diff file Expand all files Collapse all files

10
src/llama_stack/providers/remote/inference/watsonx/watsonx.py
View file

@ -15,6 +15,7 @@ from llama_stack.log import get_logger
from llama_stack.providers.remote.inference.watsonx.config import WatsonXConfig
from llama_stack.providers.utils.inference.litellm_openai_mixin import LiteLLMOpenAIMixin
from llama_stack.providers.utils.inference.openai_compat import prepare_openai_completion_params
from llama_stack.providers.utils.inference.stream_utils import wrap_async_stream
from llama_stack_api import (
Model,
ModelType,
@ -178,7 +179,7 @@ class WatsonXInferenceAdapter(LiteLLMOpenAIMixin):
async def openai_completion(
self,
params: OpenAICompletionRequestWithExtraBody,
) -> OpenAICompletion:
) -> OpenAICompletion | AsyncIterator[OpenAICompletion]:
"""
Override parent method to add watsonx-specific parameters.
"""
@ -211,7 +212,12 @@ class WatsonXInferenceAdapter(LiteLLMOpenAIMixin):
timeout=self.config.timeout,
project_id=self.config.project_id,
)
return await litellm.atext_completion(**request_params)
result = await litellm.atext_completion(**request_params)
if params.stream:
return wrap_async_stream(result) # type: ignore[arg-type] # LiteLLM streaming types
return result # type: ignore[return-value] # external lib lacks type stubs
async def openai_embeddings(
self,