phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-15 14:08:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into vector-store-chunks

Browse source
This commit is contained in:
Francisco Arceo 2025-08-03 21:00:44 -04:00 • committed by GitHub
commit d764e35b2d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 4 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

7
llama_stack/providers/utils/inference/litellm_openai_mixin.py
View file

@ -158,9 +158,8 @@ class LiteLLMOpenAIMixin(
params["model"] = self.get_litellm_model_name(params["model"])
logger.debug(f"params to litellm (openai compat): {params}")
# unfortunately, we need to use synchronous litellm.completion here because litellm
# caches various httpx.client objects in a non-eventloop aware manner
response = litellm.completion(**params)
# see https://docs.litellm.ai/docs/completion/stream#async-completion
response = await litellm.acompletion(**params)
if stream:
return self._stream_chat_completion(response)
else:
@ -170,7 +169,7 @@ class LiteLLMOpenAIMixin(
self, response: litellm.ModelResponse
) -> AsyncIterator[ChatCompletionResponseStreamChunk]:
async def _stream_generator():
for chunk in response:
async for chunk in response:
yield chunk
async for chunk in convert_openai_chat_completion_stream(

2
tests/integration/test_cases/inference/chat_completion.json
View file

@ -78,7 +78,7 @@
},
{
"role": "user",
"content": "What's the weather like in San Francisco?"
"content": "What's the weather like in San Francisco, CA?"
}
],
"tools": [