phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore(api): remove deprecated embeddings impls

Browse source
This commit is contained in:
Matthew Farrellee 2025-09-02 02:02:02 -04:00
parent 478b4ff1e6
commit 30998fd1ff
20 changed files with 3 additions and 927 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -11,14 +11,11 @@ from huggingface_hub import AsyncInferenceClient, HfApi
from llama_stack.apis.common.content_types import (
InterleavedContent,
InterleavedContentItem,
)
from llama_stack.apis.inference import (
ChatCompletionRequest,
ChatCompletionResponse,
CompletionRequest,
EmbeddingsResponse,
EmbeddingTaskType,
Inference,
LogProbConfig,
Message,
@ -26,7 +23,6 @@ from llama_stack.apis.inference import (
ResponseFormat,
ResponseFormatType,
SamplingParams,
TextTruncation,
ToolChoice,
ToolConfig,
ToolDefinition,
@ -282,16 +278,6 @@ class _HfAdapter(
**self._build_options(request.sampling_params, request.response_format),
)
async def embeddings(
self,
model_id: str,
contents: list[str] | list[InterleavedContentItem],
text_truncation: TextTruncation | None = TextTruncation.none,
output_dimension: int | None = None,
task_type: EmbeddingTaskType | None = None,
) -> EmbeddingsResponse:
raise NotImplementedError()
async def openai_embeddings(
self,
model: str,