phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 22:09:48 +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/remote/inference/ollama/ollama.py
View file

@ -37,11 +37,14 @@ from llama_stack.apis.inference import (
Message,
OpenAIChatCompletion,
OpenAIChatCompletionChunk,
OpenAIChatCompletionContentPartImageParam,
OpenAIChatCompletionContentPartTextParam,
OpenAICompletion,
OpenAIEmbeddingsResponse,
OpenAIEmbeddingUsage,
OpenAIMessageParam,
OpenAIResponseFormatParam,
RerankResponse,
ResponseFormat,
SamplingParams,
TextTruncation,
@ -641,6 +644,15 @@ class OllamaInferenceAdapter(
):
raise NotImplementedError("Batch chat completion is not supported for Ollama")
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 Ollama")
async def convert_message_to_openai_dict_for_ollama(message: Message) -> list[dict]:
async def _convert_content(content) -> dict: