phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-18 00:59:47 +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

14
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -39,12 +39,15 @@ from llama_stack.apis.inference import (
Message,
ModelStore,
OpenAIChatCompletion,
OpenAIChatCompletionContentPartImageParam,
OpenAIChatCompletionContentPartTextParam,
OpenAICompletion,
OpenAIEmbeddingData,
OpenAIEmbeddingsResponse,
OpenAIEmbeddingUsage,
OpenAIMessageParam,
OpenAIResponseFormatParam,
RerankResponse,
ResponseFormat,
SamplingParams,
TextTruncation,
@ -732,4 +735,13 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
response_format: ResponseFormat | None = None,
logprobs: LogProbConfig | None = None,
):
raise NotImplementedError("Batch chat completion is not supported for Ollama")
raise NotImplementedError("Batch chat completion is not supported for vLLM")
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 vLLM")