phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: add Prompts API to Responses API

Browse source
This commit is contained in:
r3v5 2025-09-21 13:52:55 +01:00
parent 9f6c658f2a
commit bdc16ea392
No known key found for this signature in database
GPG key ID: C7611ACB4FECAD54
15 changed files with 526 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/apis/agents/agents.py
View file

@ -38,6 +38,7 @@ from .openai_responses import (
OpenAIResponseInputTool,
OpenAIResponseObject,
OpenAIResponseObjectStream,
OpenAIResponsePromptParam,
OpenAIResponseText,
)
@ -796,6 +797,7 @@ class Agents(Protocol):
self,
input: str | list[OpenAIResponseInput],
model: str,
prompt: OpenAIResponsePromptParam | None = None,
instructions: str | None = None,
previous_response_id: str | None = None,
store: bool | None = True,
@ -807,9 +809,9 @@ class Agents(Protocol):
max_infer_iters: int | None = 10, # this is an extension to the OpenAI API
) -> OpenAIResponseObject | AsyncIterator[OpenAIResponseObjectStream]:
"""Create a new OpenAI response.
:param input: Input message(s) to create the response.
:param model: The underlying LLM used for completions.
:param prompt: Prompt object with ID, version, and variables.
:param previous_response_id: (Optional) if specified, the new response will be a continuation of the previous response. This can be used to easily fork-off new responses from existing responses.
:param include: (Optional) Additional fields to include in the response.
:returns: An OpenAIResponseObject.

17
llama_stack/apis/agents/openai_responses.py
View file

@ -9,6 +9,7 @@ from typing import Annotated, Any, Literal
from pydantic import BaseModel, Field
from typing_extensions import TypedDict
from llama_stack.apis.prompts.prompts import Prompt
from llama_stack.apis.vector_io import SearchRankingOptions as FileSearchRankingOptions
from llama_stack.schema_utils import json_schema_type, register_schema
@ -336,6 +337,20 @@ class OpenAIResponseTextFormat(TypedDict, total=False):
strict: bool | None
@json_schema_type
class OpenAIResponsePromptParam(BaseModel):
"""Prompt object that is used for OpenAI responses.
:param id: Unique identifier of the prompt template
:param variables: Dictionary of variable names to values for template substitution
:param version: Version number of the prompt to use (defaults to latest if not specified)
"""
id: str
variables: dict[str, Any] | None = None
version: str | None = None
@json_schema_type
class OpenAIResponseText(BaseModel):
"""Text response configuration for OpenAI responses.
@ -357,6 +372,7 @@ class OpenAIResponseObject(BaseModel):
:param object: Object type identifier, always "response"
:param output: List of generated output items (messages, tool calls, etc.)
:param parallel_tool_calls: Whether tool calls can be executed in parallel
:param prompt: (Optional) Prompt object with ID, version, and variables
:param previous_response_id: (Optional) ID of the previous response in a conversation
:param status: Current status of the response generation
:param temperature: (Optional) Sampling temperature used for generation
@ -373,6 +389,7 @@ class OpenAIResponseObject(BaseModel):
output: list[OpenAIResponseOutput]
parallel_tool_calls: bool = False
previous_response_id: str | None = None
prompt: Prompt | None = None
status: str
temperature: float | None = None
# Default to text format to avoid breaking the loading of old responses