phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-10 11:39:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Remove request arg from chat completion response processing

Browse source 
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
This commit is contained in:
Yuan Tang 2024-10-11 16:18:40 -04:00
parent a2b87ed0cb
commit fe9029f169
No known key found for this signature in database
7 changed files with 14 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_stack/providers/utils/inference/openai_compat.py
View file

@ -50,9 +50,7 @@ def text_from_choice(choice) -> str:
def process_chat_completion_response(
request: ChatCompletionRequest,
response: OpenAICompatCompletionResponse,
formatter: ChatFormat,
response: OpenAICompatCompletionResponse, formatter: ChatFormat
) -> ChatCompletionResponse:
choice = response.choices[0]
@ -78,9 +76,7 @@ def process_chat_completion_response(
async def process_chat_completion_stream_response(
request: ChatCompletionRequest,
stream: AsyncGenerator[OpenAICompatCompletionResponse, None],
formatter: ChatFormat,
stream: AsyncGenerator[OpenAICompatCompletionResponse, None], formatter: ChatFormat
) -> AsyncGenerator:
yield ChatCompletionResponseStreamChunk(
event=ChatCompletionResponseEvent(