phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 04:04:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: indicate to mypy that InferenceProvider.batch_completion/batch_chat_completion is concrete (#3239)

Browse source 
# What does this PR do?

closes https://github.com/llamastack/llama-stack/issues/3236

mypy considered our default implementations (raise NotImplementedError)
to be trivial. the result was we implemented the same stubs in
providers.

this change puts enough into the default impls so mypy considers them
non-trivial. this allows us to remove the duplicate implementations.
This commit is contained in:
Matthew Farrellee 2025-08-22 16:17:30 -05:00 • committed by GitHub
parent 2ee898cc4c
commit 3d119a86d4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 2 additions and 89 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -1068,6 +1068,7 @@ class InferenceProvider(Protocol):
:returns: A BatchCompletionResponse with the full completions.
"""
raise NotImplementedError("Batch completion is not implemented")
return # this is so mypy's safe-super rule will consider the method concrete
@webmethod(route="/inference/chat-completion", method="POST")
async def chat_completion(
@ -1132,6 +1133,7 @@ class InferenceProvider(Protocol):
:returns: A BatchChatCompletionResponse with the full completions.
"""
raise NotImplementedError("Batch chat completion is not implemented")
return # this is so mypy's safe-super rule will consider the method concrete
@webmethod(route="/inference/embeddings", method="POST")
async def embeddings(

23
llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers.py
View file

@ -9,7 +9,6 @@ from collections.abc import AsyncGenerator
from llama_stack.apis.inference import (
CompletionResponse,
InferenceProvider,
InterleavedContent,
LogProbConfig,
Message,
ResponseFormat,
@ -100,25 +99,3 @@ class SentenceTransformersInferenceImpl(
tool_config: ToolConfig | None = None,
) -> AsyncGenerator:
raise ValueError("Sentence transformers don't support chat completion")
async def batch_completion(
self,
model_id: str,
content_batch: list[InterleavedContent],
sampling_params: SamplingParams | None = None,
response_format: ResponseFormat | None = None,
logprobs: LogProbConfig | None = None,
):
raise NotImplementedError("Batch completion is not supported for Sentence Transformers")
async def batch_chat_completion(
self,
model_id: str,
messages_batch: list[list[Message]],
sampling_params: SamplingParams | None = None,
tools: list[ToolDefinition] | None = None,
tool_config: ToolConfig | None = None,
response_format: ResponseFormat | None = None,
logprobs: LogProbConfig | None = None,
):
raise NotImplementedError("Batch chat completion is not supported for Sentence Transformers")

22
llama_stack/providers/remote/inference/ollama/ollama.py
View file

@ -619,28 +619,6 @@ class OllamaInferenceAdapter(
response.id = id
return response
async def batch_completion(
self,
model_id: str,
content_batch: list[InterleavedContent],
sampling_params: SamplingParams | None = None,
response_format: ResponseFormat | None = None,
logprobs: LogProbConfig | None = None,
):
raise NotImplementedError("Batch completion is not supported for Ollama")
async def batch_chat_completion(
self,
model_id: str,
messages_batch: list[list[Message]],
sampling_params: SamplingParams | None = None,
tools: list[ToolDefinition] | None = None,
tool_config: ToolConfig | None = None,
response_format: ResponseFormat | None = None,
logprobs: LogProbConfig | None = None,
):
raise NotImplementedError("Batch chat completion is not supported for Ollama")
async def convert_message_to_openai_dict_for_ollama(message: Message) -> list[dict]:
async def _convert_content(content) -> dict:

22
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -711,25 +711,3 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
user=user,
)
return await self.client.chat.completions.create(**params) # type: ignore
async def batch_completion(
self,
model_id: str,
content_batch: list[InterleavedContent],
sampling_params: SamplingParams | None = None,
response_format: ResponseFormat | None = None,
logprobs: LogProbConfig | None = None,
):
raise NotImplementedError("Batch completion is not supported for Ollama")
async def batch_chat_completion(
self,
model_id: str,
messages_batch: list[list[Message]],
sampling_params: SamplingParams | None = None,
tools: list[ToolDefinition] | None = None,
tool_config: ToolConfig | None = None,
response_format: ResponseFormat | None = None,
logprobs: LogProbConfig | None = None,
):
raise NotImplementedError("Batch chat completion is not supported for vLLM")

22
llama_stack/providers/utils/inference/litellm_openai_mixin.py
View file

@ -429,28 +429,6 @@ class LiteLLMOpenAIMixin(
)
return await litellm.acompletion(**params)
async def batch_completion(
self,
model_id: str,
content_batch: list[InterleavedContent],
sampling_params: SamplingParams | None = None,
response_format: ResponseFormat | None = None,
logprobs: LogProbConfig | None = None,
):
raise NotImplementedError("Batch completion is not supported for OpenAI Compat")
async def batch_chat_completion(
self,
model_id: str,
messages_batch: list[list[Message]],
sampling_params: SamplingParams | None = None,
tools: list[ToolDefinition] | None = None,
tool_config: ToolConfig | None = None,
response_format: ResponseFormat | None = None,
logprobs: LogProbConfig | None = None,
):
raise NotImplementedError("Batch chat completion is not supported for OpenAI Compat")
async def check_model_availability(self, model: str) -> bool:
"""
Check if a specific model is available via LiteLLM for the current