phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 20:14:13 +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

1
llama_stack/apis/inference/inference.py
View file

@ -1170,6 +1170,7 @@ class InferenceProvider(Protocol):
:returns: RerankResponse with indices sorted by relevance score (descending). :returns: RerankResponse with indices sorted by relevance score (descending).
""" """
raise NotImplementedError("Reranking is not implemented") raise NotImplementedError("Reranking is not implemented")
return # this is so mypy's safe-super rule will consider the method concrete
@webmethod(route="/openai/v1/completions", method="POST") @webmethod(route="/openai/v1/completions", method="POST")
async def openai_completion( async def openai_completion(

12
llama_stack/providers/inline/inference/meta_reference/inference.py
View file

@ -33,9 +33,6 @@ from llama_stack.apis.inference import (
InterleavedContent, InterleavedContent,
LogProbConfig, LogProbConfig,
Message, Message,
OpenAIChatCompletionContentPartImageParam,
OpenAIChatCompletionContentPartTextParam,
RerankResponse,
ResponseFormat, ResponseFormat,
SamplingParams, SamplingParams,
StopReason, StopReason,
@ -445,15 +442,6 @@ class MetaReferenceInferenceImpl(
results = await self._nonstream_chat_completion(request_batch) results = await self._nonstream_chat_completion(request_batch)
return BatchChatCompletionResponse(batch=results) 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( async def _nonstream_chat_completion(
self, request_batch: list[ChatCompletionRequest] self, request_batch: list[ChatCompletionRequest]
) -> list[ChatCompletionResponse]: ) -> list[ChatCompletionResponse]:

12
llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers.py
View file

@ -12,9 +12,6 @@ from llama_stack.apis.inference import (
InterleavedContent, InterleavedContent,
LogProbConfig, LogProbConfig,
Message, Message,
OpenAIChatCompletionContentPartImageParam,
OpenAIChatCompletionContentPartTextParam,
RerankResponse,
ResponseFormat, ResponseFormat,
SamplingParams, SamplingParams,
ToolChoice, ToolChoice,
@ -125,12 +122,3 @@ class SentenceTransformersInferenceImpl(
logprobs: LogProbConfig | None = None, logprobs: LogProbConfig | None = None,
): ):
raise NotImplementedError("Batch chat completion is not supported for Sentence Transformers") raise NotImplementedError("Batch chat completion is not supported for Sentence Transformers")
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 Sentence Transformers")

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 # This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree. # 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.log import get_logger
from llama_stack.providers.remote.inference.llama_openai_compat.config import LlamaCompatConfig from llama_stack.providers.remote.inference.llama_openai_compat.config import LlamaCompatConfig
from llama_stack.providers.utils.inference.litellm_openai_mixin import LiteLLMOpenAIMixin from llama_stack.providers.utils.inference.litellm_openai_mixin import LiteLLMOpenAIMixin
@ -59,12 +54,3 @@ class LlamaCompatInferenceAdapter(OpenAIMixin, LiteLLMOpenAIMixin):
async def shutdown(self): async def shutdown(self):
await super().shutdown() 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, Message,
OpenAIChatCompletion, OpenAIChatCompletion,
OpenAIChatCompletionChunk, OpenAIChatCompletionChunk,
OpenAIChatCompletionContentPartImageParam,
OpenAIChatCompletionContentPartTextParam,
OpenAICompletion, OpenAICompletion,
OpenAIEmbeddingsResponse, OpenAIEmbeddingsResponse,
OpenAIEmbeddingUsage, OpenAIEmbeddingUsage,
OpenAIMessageParam, OpenAIMessageParam,
OpenAIResponseFormatParam, OpenAIResponseFormatParam,
RerankResponse,
ResponseFormat, ResponseFormat,
SamplingParams, SamplingParams,
TextTruncation, TextTruncation,
@ -644,15 +641,6 @@ class OllamaInferenceAdapter(
): ):
raise NotImplementedError("Batch chat completion is not supported for Ollama") 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_message_to_openai_dict_for_ollama(message: Message) -> list[dict]:
async def _convert_content(content) -> 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, Message,
ModelStore, ModelStore,
OpenAIChatCompletion, OpenAIChatCompletion,
OpenAIChatCompletionContentPartImageParam,
OpenAIChatCompletionContentPartTextParam,
OpenAICompletion, OpenAICompletion,
OpenAIEmbeddingData, OpenAIEmbeddingData,
OpenAIEmbeddingsResponse, OpenAIEmbeddingsResponse,
OpenAIEmbeddingUsage, OpenAIEmbeddingUsage,
OpenAIMessageParam, OpenAIMessageParam,
OpenAIResponseFormatParam, OpenAIResponseFormatParam,
RerankResponse,
ResponseFormat, ResponseFormat,
SamplingParams, SamplingParams,
TextTruncation, TextTruncation,
@ -736,12 +733,3 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
logprobs: LogProbConfig | None = None, logprobs: LogProbConfig | None = None,
): ):
raise NotImplementedError("Batch chat completion is not supported for vLLM") 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")