phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-10 03:30:58 +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

4
llama_stack/providers/adapters/inference/together/together.py
View file

@ -108,7 +108,7 @@ class TogetherInferenceAdapter(
) -> ChatCompletionResponse:
params = self._get_params(request)
r = client.completions.create(**params)
return process_chat_completion_response(request, r, self.formatter)
return process_chat_completion_response(r, self.formatter)
async def _stream_chat_completion(
self, request: ChatCompletionRequest, client: Together
@ -123,7 +123,7 @@ class TogetherInferenceAdapter(
stream = _to_async_generator()
async for chunk in process_chat_completion_stream_response(
request, stream, self.formatter
stream, self.formatter
):
yield chunk