phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-29 03:14:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: Structured output for Responses API

Browse source 
This adds the missing `text` parameter to the Responses API that is
how users control structured outputs. All we do with that parameter is
map it to the corresponding chat completion response_format.

The unit tests exercise the various permutations allowed for this
property, while a couple of new verification tests actually use it for
real to verify the model outputs are following the format as expected.

Signed-off-by: Ben Browning <bbrownin@redhat.com>
This commit is contained in:
Ben Browning 2025-05-31 13:44:20 -04:00
parent 4540c9b3e5
commit badf8594d1
8 changed files with 323 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/apis/agents/agents.py
View file

@ -37,6 +37,7 @@ from .openai_responses import (
OpenAIResponseInputTool,
OpenAIResponseObject,
OpenAIResponseObjectStream,
OpenAIResponseText,
)
# TODO: use enum.StrEnum when we drop support for python 3.10
@ -603,6 +604,7 @@ class Agents(Protocol):
store: bool | None = True,
stream: bool | None = False,
temperature: float | None = None,
text: OpenAIResponseText | None = None,
tools: list[OpenAIResponseInputTool] | None = None,
max_infer_iters: int | None = 10, # this is an extension to the OpenAI API
) -> OpenAIResponseObject | AsyncIterator[OpenAIResponseObjectStream]: