phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-27 18:50:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: Add temperature support to responses API (#2065)

Browse source 
# What does this PR do?
Add support for the temperature to the responses API 


## Test Plan
Manually tested simple case
unit tests added for simple case and tool calls

Signed-off-by: Derek Higgins <derekh@redhat.com>
This commit is contained in:
Derek Higgins 2025-05-01 19:47:58 +01:00 • committed by GitHub
parent f36f68c590
commit 64829947d0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 220 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

1
llama_stack/apis/agents/agents.py
View file

@ -628,6 +628,7 @@ class Agents(Protocol):
previous_response_id: Optional[str] = None,
store: Optional[bool] = True,
stream: Optional[bool] = False,
temperature: Optional[float] = None,
tools: Optional[List[OpenAIResponseInputTool]] = None,
) -> Union[OpenAIResponseObject, AsyncIterator[OpenAIResponseObjectStream]]:
"""Create a new OpenAI response.

3
llama_stack/providers/inline/agents/meta_reference/agents.py
View file

@ -270,8 +270,9 @@ class MetaReferenceAgentsImpl(Agents):
previous_response_id: Optional[str] = None,
store: Optional[bool] = True,
stream: Optional[bool] = False,
temperature: Optional[float] = None,
tools: Optional[List[OpenAIResponseInputTool]] = None,
) -> OpenAIResponseObject:
return await self.openai_responses_impl.create_openai_response(
input, model, previous_response_id, store, stream, tools
input, model, previous_response_id, store, stream, temperature, tools
)

12
llama_stack/providers/inline/agents/meta_reference/openai_responses.py
View file

@ -106,6 +106,7 @@ class OpenAIResponsesImpl:
previous_response_id: Optional[str] = None,
store: Optional[bool] = True,
stream: Optional[bool] = False,
temperature: Optional[float] = None,
tools: Optional[List[OpenAIResponseInputTool]] = None,
):
stream = False if stream is None else stream
@ -141,6 +142,7 @@ class OpenAIResponsesImpl:
messages=messages,
tools=chat_tools,
stream=stream,
temperature=temperature,
)
if stream:
@ -180,7 +182,7 @@ class OpenAIResponsesImpl:
output_messages: List[OpenAIResponseOutput] = []
if chat_response.choices[0].message.tool_calls:
output_messages.extend(
await self._execute_tool_and_return_final_output(model, stream, chat_response, messages)
await self._execute_tool_and_return_final_output(model, stream, chat_response, messages, temperature)
)
else:
output_messages.extend(await _openai_choices_to_output_messages(chat_response.choices))
@ -241,7 +243,12 @@ class OpenAIResponsesImpl:
return chat_tools
async def _execute_tool_and_return_final_output(
self, model_id: str, stream: bool, chat_response: OpenAIChatCompletion, messages: List[OpenAIMessageParam]
self,
model_id: str,
stream: bool,
chat_response: OpenAIChatCompletion,
messages: List[OpenAIMessageParam],
temperature: float,
) -> List[OpenAIResponseOutput]:
output_messages: List[OpenAIResponseOutput] = []
choice = chat_response.choices[0]
@ -295,6 +302,7 @@ class OpenAIResponsesImpl:
model=model_id,
messages=messages,
stream=stream,
temperature=temperature,
)
# type cast to appease mypy
tool_results_chat_response = cast(OpenAIChatCompletion, tool_results_chat_response)