phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-18 01:09:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

indicate to mypy that InferenceProvider.rerank is concrete

Browse source
This commit is contained in:
Matthew Farrellee 2025-08-22 14:55:12 -04:00
parent f520e244d9
commit 34d96c21bf
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/remote/inference/ollama/ollama.py
View file

@ -37,14 +37,11 @@ from llama_stack.apis.inference import (
Message,
OpenAIChatCompletion,
OpenAIChatCompletionChunk,
OpenAIChatCompletionContentPartImageParam,
OpenAIChatCompletionContentPartTextParam,
OpenAICompletion,
OpenAIEmbeddingsResponse,
OpenAIEmbeddingUsage,
OpenAIMessageParam,
OpenAIResponseFormatParam,
RerankResponse,
ResponseFormat,
SamplingParams,
TextTruncation,
@ -644,15 +641,6 @@ 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: