phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 04:04:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

revert openai_compat changes and use OpenAIMixin for openai_chat_completion

Browse source
This commit is contained in:
Swapna Lekkala 2025-09-18 16:06:53 -07:00
parent 0f5bef893a
commit a6baa7b3d4
9 changed files with 23 additions and 303 deletions
Download patch file Download diff file Expand all files Collapse all files

32
llama_stack/apis/inference/inference.py
View file

@ -451,20 +451,6 @@ class ChatCompletionResponseStreamChunk(MetricResponseMixin):
event: ChatCompletionResponseEvent
@json_schema_type
class UsageInfo(BaseModel):
"""Usage information for a model.
:param completion_tokens: Number of tokens generated
:param prompt_tokens: Number of tokens in the prompt
:param total_tokens: Total number of tokens processed
"""
completion_tokens: int
prompt_tokens: int
total_tokens: int
@json_schema_type
class ChatCompletionResponse(MetricResponseMixin):
"""Response from a chat completion request.
@ -475,7 +461,6 @@ class ChatCompletionResponse(MetricResponseMixin):
completion_message: CompletionMessage
logprobs: list[TokenLogProbs] | None = None
usage: UsageInfo | None = None
@json_schema_type
@ -833,21 +818,7 @@ class OpenAIChoice(BaseModel):
@json_schema_type
class OpenAIChatCompletionUsage(BaseModel):
"""Usage information for an OpenAI-compatible chat completion response.
:param prompt_tokens: The number of tokens in the prompt
:param completion_tokens: The number of tokens in the completion
:param total_tokens: The total number of tokens used
"""
prompt_tokens: int
completion_tokens: int
total_tokens: int
@json_schema_type
class OpenAIChatCompletion(MetricResponseMixin):
class OpenAIChatCompletion(BaseModel):
"""Response from an OpenAI-compatible chat completion request.
:param id: The ID of the chat completion
@ -862,7 +833,6 @@ class OpenAIChatCompletion(MetricResponseMixin):
object: Literal["chat.completion"] = "chat.completion"
created: int
model: str
usage: OpenAIChatCompletionUsage | None = None
@json_schema_type