phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-03 09:21:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

OpenAI completion prompt can also include tokens

Browse source 
The OpenAI completion API supports strings, array of strings, array of
tokens, or array of token arrays. So, expand our type hinting to
support all of these types.

Signed-off-by: Ben Browning <bbrownin@redhat.com>
This commit is contained in:
Ben Browning 2025-04-09 10:05:50 -04:00
parent a6cf8fa12b
commit fcdeb3d7bf
8 changed files with 8 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -780,7 +780,7 @@ class Inference(Protocol):
async def openai_completion(
self,
model: str,
prompt: Union[str, List[str]],
prompt: Union[str, List[str], List[int], List[List[int]]],
best_of: Optional[int] = None,
echo: Optional[bool] = None,
frequency_penalty: Optional[float] = None,

2
llama_stack/distribution/routers/routers.py
View file

@ -423,7 +423,7 @@ class InferenceRouter(Inference):
async def openai_completion(
self,
model: str,
prompt: Union[str, List[str]],
prompt: Union[str, List[str], List[int], List[List[int]]],
best_of: Optional[int] = None,
echo: Optional[bool] = None,
frequency_penalty: Optional[float] = None,

2
llama_stack/providers/remote/inference/ollama/ollama.py
View file

@ -331,7 +331,7 @@ class OllamaInferenceAdapter(
async def openai_completion(
self,
model: str,
prompt: Union[str, List[str]],
prompt: Union[str, List[str], List[int], List[List[int]]],
best_of: Optional[int] = None,
echo: Optional[bool] = None,
frequency_penalty: Optional[float] = None,

2
llama_stack/providers/remote/inference/passthrough/passthrough.py
View file

@ -206,7 +206,7 @@ class PassthroughInferenceAdapter(Inference):
async def openai_completion(
self,
model: str,
prompt: Union[str, List[str]],
prompt: Union[str, List[str], List[int], List[List[int]]],
best_of: Optional[int] = None,
echo: Optional[bool] = None,
frequency_penalty: Optional[float] = None,

2
llama_stack/providers/remote/inference/together/together.py
View file

@ -260,7 +260,7 @@ class TogetherInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProvi
async def openai_completion(
self,
model: str,
prompt: Union[str, List[str]],
prompt: Union[str, List[str], List[int], List[List[int]]],
best_of: Optional[int] = None,
echo: Optional[bool] = None,
frequency_penalty: Optional[float] = None,

2
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -424,7 +424,7 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
async def openai_completion(
self,
model: str,
prompt: Union[str, List[str]],
prompt: Union[str, List[str], List[int], List[List[int]]],
best_of: Optional[int] = None,
echo: Optional[bool] = None,
frequency_penalty: Optional[float] = None,

2
llama_stack/providers/utils/inference/litellm_openai_mixin.py
View file

@ -251,7 +251,7 @@ class LiteLLMOpenAIMixin(
async def openai_completion(
self,
model: str,
prompt: Union[str, List[str]],
prompt: Union[str, List[str], List[int], List[List[int]]],
best_of: Optional[int] = None,
echo: Optional[bool] = None,
frequency_penalty: Optional[float] = None,

2
llama_stack/providers/utils/inference/openai_compat.py
View file

@ -1088,7 +1088,7 @@ class OpenAICompletionUnsupportedMixin:
async def openai_completion(
self,
model: str,
prompt: Union[str, List[str]],
prompt: Union[str, List[str], List[int], List[List[int]]],
best_of: Optional[int] = None,
echo: Optional[bool] = None,
frequency_penalty: Optional[float] = None,