phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-28 10:54:19 +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

30
llama_stack/apis/agents/openai_responses.py
View file

@ -7,6 +7,7 @@
from typing import Annotated, Any, Literal
from pydantic import BaseModel, Field
from typing_extensions import TypedDict
from llama_stack.schema_utils import json_schema_type, register_schema
@ -126,6 +127,32 @@ OpenAIResponseOutput = Annotated[
register_schema(OpenAIResponseOutput, name="OpenAIResponseOutput")
# This has to be a TypedDict because we need a "schema" field and our strong
# typing code in the schema generator doesn't support Pydantic aliases. That also
# means we can't use a discriminator field here, because TypedDicts don't support
# default values which the strong typing code requires for discriminators.
class OpenAIResponseTextFormat(TypedDict, total=False):
"""Configuration for Responses API text format.
:param type: Must be "text", "json_schema", or "json_object" to identify the format type
:param name: The name of the response format. Only used for json_schema.
:param schema: The JSON schema the response should conform to. In a Python SDK, this is often a `pydantic` model. Only used for json_schema.
:param description: (Optional) A description of the response format. Only used for json_schema.
:param strict: (Optional) Whether to strictly enforce the JSON schema. If true, the response must match the schema exactly. Only used for json_schema.
"""
type: Literal["text"] | Literal["json_schema"] | Literal["json_object"]
name: str | None
schema: dict[str, Any] | None
description: str | None
strict: bool | None
@json_schema_type
class OpenAIResponseText(BaseModel):
format: OpenAIResponseTextFormat | None = None
@json_schema_type
class OpenAIResponseObject(BaseModel):
created_at: int
@ -138,6 +165,9 @@ class OpenAIResponseObject(BaseModel):
previous_response_id: str | None = None
status: str
temperature: float | None = None
# Default to text format to avoid breaking the loading of old responses
# before the field was added. New responses will have this set always.
text: OpenAIResponseText = OpenAIResponseText(format=OpenAIResponseTextFormat(type="text"))
top_p: float | None = None
truncation: str | None = None
user: str | None = None