phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 21:47:33 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(api): introduce /rerank

Browse source 
# What does this PR do?


## Test Plan
This commit is contained in:
Eric Huang 2025-08-14 16:14:38 -07:00
parent e69acbafbf
commit 306625025a
8 changed files with 336 additions and 1 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

@ -33,6 +33,9 @@ from llama_stack.apis.inference import (
InterleavedContent,
LogProbConfig,
Message,
OpenAIChatCompletionContentPartImageParam,
OpenAIChatCompletionContentPartTextParam,
RerankResponse,
ResponseFormat,
SamplingParams,
StopReason,
@ -442,6 +445,15 @@ 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]: