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

Merge branch 'main' into pr1573

Browse source
This commit is contained in:
Xi Yan 2025-03-12 12:31:49 -07:00
commit f840018088
12 changed files with 402 additions and 64 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