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(api): remove deprecated embeddings impls (#3301)
Some checks failed
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 0s
Details
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
Details
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 1s
Details
Python Package Build Test / build (3.12) (push) Failing after 1s
Details
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Details
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 3s
Details
Vector IO Integration Tests / test-matrix (push) Failing after 4s
Details
API Conformance Tests / check-schema-compatibility (push) Successful in 7s
Details
Unit Tests / unit-tests (3.13) (push) Failing after 4s
Details
Test External API and Providers / test-external (venv) (push) Failing after 4s
Details
Python Package Build Test / build (3.13) (push) Failing after 9s
Details
Unit Tests / unit-tests (3.12) (push) Failing after 10s
Details
UI Tests / ui-tests (22) (push) Successful in 39s
Details
Pre-commit / pre-commit (push) Successful in 1m25s
Details

Browse source 
# What does this PR do?

remove deprecated embeddings implementations
This commit is contained in:
Matthew Farrellee 2025-09-29 14:45:09 -04:00 • committed by GitHub
parent aab22dc759
commit 975ead1d6a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
19 changed files with 3 additions and 632 deletions
Download patch file Download diff file Expand all files Collapse all files

30
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -16,7 +16,6 @@ from openai.types.chat.chat_completion_chunk import (
from llama_stack.apis.common.content_types import (
InterleavedContent,
InterleavedContentItem,
TextDelta,
ToolCallDelta,
ToolCallParseStatus,
@ -31,8 +30,6 @@ from llama_stack.apis.inference import (
CompletionRequest,
CompletionResponse,
CompletionResponseStreamChunk,
EmbeddingsResponse,
EmbeddingTaskType,
GrammarResponseFormat,
Inference,
JsonSchemaResponseFormat,
@ -41,7 +38,6 @@ from llama_stack.apis.inference import (
ModelStore,
ResponseFormat,
SamplingParams,
TextTruncation,
ToolChoice,
ToolConfig,
ToolDefinition,
@ -74,8 +70,6 @@ from llama_stack.providers.utils.inference.openai_compat import (
from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
from llama_stack.providers.utils.inference.prompt_adapter import (
completion_request_to_prompt,
content_has_media,
interleaved_content_as_str,
request_has_media,
)
@ -550,27 +544,3 @@ class VLLMInferenceAdapter(OpenAIMixin, LiteLLMOpenAIMixin, Inference, ModelsPro
"stream": request.stream,
**options,
}
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:
model = await self._get_model(model_id)
kwargs = {}
assert model.model_type == ModelType.embedding
assert model.metadata.get("embedding_dimension")
kwargs["dimensions"] = model.metadata.get("embedding_dimension")
assert all(not content_has_media(content) for content in contents), "VLLM does not support media for embeddings"
response = await self.client.embeddings.create(
model=model.provider_resource_id,
input=[interleaved_content_as_str(content) for content in contents],
**kwargs,
)
embeddings = [data.embedding for data in response.data]
return EmbeddingsResponse(embeddings=embeddings)