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

14
llama_stack/providers/remote/inference/llama_openai_compat/llama.py
View file

@ -3,11 +3,6 @@
#
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from llama_stack.apis.inference import (
OpenAIChatCompletionContentPartImageParam,
OpenAIChatCompletionContentPartTextParam,
RerankResponse,
)
from llama_stack.log import get_logger
from llama_stack.providers.remote.inference.llama_openai_compat.config import LlamaCompatConfig
from llama_stack.providers.utils.inference.litellm_openai_mixin import LiteLLMOpenAIMixin
@ -59,12 +54,3 @@ class LlamaCompatInferenceAdapter(OpenAIMixin, LiteLLMOpenAIMixin):
async def shutdown(self):
await super().shutdown()
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 Llama OpenAI Compat")

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:

12
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -39,15 +39,12 @@ from llama_stack.apis.inference import (
Message,
ModelStore,
OpenAIChatCompletion,
OpenAIChatCompletionContentPartImageParam,
OpenAIChatCompletionContentPartTextParam,
OpenAICompletion,
OpenAIEmbeddingData,
OpenAIEmbeddingsResponse,
OpenAIEmbeddingUsage,
OpenAIMessageParam,
OpenAIResponseFormatParam,
RerankResponse,
ResponseFormat,
SamplingParams,
TextTruncation,
@ -736,12 +733,3 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
logprobs: LogProbConfig | None = None,
):
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")