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.rerank is concrete (#3238)

Browse source
This commit is contained in:
Matthew Farrellee 2025-08-22 14:02:13 -05:00 • committed by GitHub
parent da73f1a180
commit 2ee898cc4c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 1 additions and 62 deletions
Download patch file Download diff file Expand all files Collapse all files

12
llama_stack/providers/inline/inference/meta_reference/inference.py
View file

@ -33,9 +33,6 @@ from llama_stack.apis.inference import (
InterleavedContent,
LogProbConfig,
Message,
OpenAIChatCompletionContentPartImageParam,
OpenAIChatCompletionContentPartTextParam,
RerankResponse,
ResponseFormat,
SamplingParams,
StopReason,
@ -445,15 +442,6 @@ class MetaReferenceInferenceImpl(
results = await self._nonstream_chat_completion(request_batch)
return BatchChatCompletionResponse(batch=results)
async def rerank(
self,
model: str,
query: str | OpenAIChatCompletionContentPartTextParam | OpenAIChatCompletionContentPartImageParam,
items: list[str | OpenAIChatCompletionContentPartTextParam | OpenAIChatCompletionContentPartImageParam],
max_num_results: int | None = None,
) -> RerankResponse:
raise NotImplementedError("Reranking is not supported for Meta Reference")
async def _nonstream_chat_completion(
self, request_batch: list[ChatCompletionRequest]
) -> list[ChatCompletionResponse]:

12
llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers.py
View file

@ -12,9 +12,6 @@ from llama_stack.apis.inference import (
InterleavedContent,
LogProbConfig,
Message,
OpenAIChatCompletionContentPartImageParam,
OpenAIChatCompletionContentPartTextParam,
RerankResponse,
ResponseFormat,
SamplingParams,
ToolChoice,
@ -125,12 +122,3 @@ class SentenceTransformersInferenceImpl(
logprobs: LogProbConfig | None = None,
):
raise NotImplementedError("Batch chat completion is not supported for Sentence Transformers")
async def rerank(
self,
model: str,
query: str | OpenAIChatCompletionContentPartTextParam | OpenAIChatCompletionContentPartImageParam,
items: list[str | OpenAIChatCompletionContentPartTextParam | OpenAIChatCompletionContentPartImageParam],
max_num_results: int | None = None,
) -> RerankResponse:
raise NotImplementedError("Reranking is not supported for Sentence Transformers")