phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-31 03:23:53 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix OpenAI API response format handling

Browse source 
This fixes the schema of OpenAI API chat completion response formats,
including how those response formats (and other nested parameters in
the chat completion request) get translated into paramters for calls
to the backend OpenAI-compatible providers.

Signed-off-by: Ben Browning <bbrownin@redhat.com>
This commit is contained in:
Ben Browning 2025-04-12 16:29:02 -04:00
parent 1e673010e4
commit a4b573d750
12 changed files with 307 additions and 30 deletions
Download patch file Download diff file Expand all files Collapse all files

9
llama_stack/providers/remote/inference/ollama/ollama.py
View file

@ -39,7 +39,12 @@ from llama_stack.apis.inference import (
ToolDefinition,
ToolPromptFormat,
)
from llama_stack.apis.inference.inference import OpenAIChatCompletion, OpenAICompletion, OpenAIMessageParam
from llama_stack.apis.inference.inference import (
OpenAIChatCompletion,
OpenAICompletion,
OpenAIMessageParam,
OpenAIResponseFormatParam,
)
from llama_stack.apis.models import Model, ModelType
from llama_stack.log import get_logger
from llama_stack.providers.datatypes import ModelsProtocolPrivate
@ -393,7 +398,7 @@ class OllamaInferenceAdapter(
n: Optional[int] = None,
parallel_tool_calls: Optional[bool] = None,
presence_penalty: Optional[float] = None,
response_format: Optional[Dict[str, str]] = None,
response_format: Optional[OpenAIResponseFormatParam] = None,
seed: Optional[int] = None,
stop: Optional[Union[str, List[str]]] = None,
stream: Optional[bool] = None,