phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

Remove request arg from chat completion response processing (#240)

Browse source 
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
This commit is contained in:
Yuan Tang 2024-10-15 16:03:17 -04:00 • committed by GitHub
parent 209cd3d35e
commit 80ada04f76
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
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(