phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-31 08:43:52 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge-related changes.

Browse source
This commit is contained in:
ilya-kolchinsky 2025-03-11 17:05:13 +01:00
commit a714bbac9d
95 changed files with 11044 additions and 4639 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(MetricResponseMixin):
class CompletionResponse(BaseModel):
"""Response from a completion request.
:param content: The generated completion text
@ -299,7 +299,7 @@ class CompletionResponse(MetricResponseMixin):
@json_schema_type
class CompletionResponseStreamChunk(MetricResponseMixin):
class CompletionResponseStreamChunk(BaseModel):
"""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):
class ChatCompletionResponseStreamChunk(MetricResponseMixin, BaseModel):
"""A chunk of a streamed chat completion response.
:param event: The event containing the new content
@ -378,7 +378,7 @@ class ChatCompletionResponseStreamChunk(MetricResponseMixin):
@json_schema_type
class ChatCompletionResponse(MetricResponseMixin):
class ChatCompletionResponse(MetricResponseMixin, BaseModel):
"""Response from a chat completion request.
:param completion_message: The complete response message