phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-02 07:44:31 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Revert "fix: Revert "feat: record token usage for inference API (#1300)" (#1476)"

Browse source 
This reverts commit 60e7f3d705.
This commit is contained in:
Dinesh Yeduguru 2025-03-11 08:35:27 -07:00
parent 2370e826bc
commit 0cac53ab30
5 changed files with 162 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_stack/apis/inference/inference.py
View file

@ -285,7 +285,7 @@ class CompletionRequest(BaseModel):
@json_schema_type
class CompletionResponse(BaseModel):
class CompletionResponse(MetricResponseMixin):
"""Response from a completion request.
:param content: The generated completion text
@ -299,7 +299,7 @@ class CompletionResponse(BaseModel):
@json_schema_type
class CompletionResponseStreamChunk(BaseModel):
class CompletionResponseStreamChunk(MetricResponseMixin):
"""A chunk of a streamed completion response.
:param delta: New content generated since last chunk. This can be one or more tokens.
@ -368,7 +368,7 @@ class ChatCompletionRequest(BaseModel):
@json_schema_type
class ChatCompletionResponseStreamChunk(MetricResponseMixin, BaseModel):
class ChatCompletionResponseStreamChunk(MetricResponseMixin):
"""A chunk of a streamed chat completion response.
:param event: The event containing the new content
@ -378,7 +378,7 @@ class ChatCompletionResponseStreamChunk(MetricResponseMixin, BaseModel):
@json_schema_type
class ChatCompletionResponse(MetricResponseMixin, BaseModel):
class ChatCompletionResponse(MetricResponseMixin):
"""Response from a chat completion request.
:param completion_message: The complete response message