mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 12:07:34 +00:00
Test fixes in openai_compat
This commit is contained in:
parent
e56a3f266c
commit
d60514b57b
7 changed files with 221 additions and 7 deletions
|
@ -130,7 +130,7 @@ class FireworksInferenceAdapter(OpenAIMixin, ModelRegistryHelper, Inference, Nee
|
|||
async def _stream_completion(self, request: CompletionRequest) -> AsyncGenerator:
|
||||
params = await self._get_params(request)
|
||||
|
||||
stream = self.client.completions.create(**params)
|
||||
stream = await self.client.completions.create(**params)
|
||||
async for chunk in process_completion_stream_response(stream):
|
||||
yield chunk
|
||||
|
||||
|
@ -208,9 +208,9 @@ class FireworksInferenceAdapter(OpenAIMixin, ModelRegistryHelper, Inference, Nee
|
|||
params = await self._get_params(request)
|
||||
|
||||
if "messages" in params:
|
||||
stream = self.client.chat.completions.create(**params)
|
||||
stream = await self.client.chat.completions.create(**params)
|
||||
else:
|
||||
stream = self.client.completions.create(**params)
|
||||
stream = await self.client.completions.create(**params)
|
||||
async for chunk in process_chat_completion_stream_response(stream, request):
|
||||
yield chunk
|
||||
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue