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

27
llama_stack/providers/remote/inference/ollama/ollama.py
View file

@ -14,7 +14,6 @@ from ollama import AsyncClient as AsyncOllamaClient
from llama_stack.apis.common.content_types import (
ImageContentItem,
InterleavedContent,
InterleavedContentItem,
TextContentItem,
)
from llama_stack.apis.common.errors import UnsupportedModelError
@ -25,8 +24,6 @@ from llama_stack.apis.inference import (
CompletionRequest,
CompletionResponse,
CompletionResponseStreamChunk,
EmbeddingsResponse,
EmbeddingTaskType,
GrammarResponseFormat,
InferenceProvider,
JsonSchemaResponseFormat,
@ -34,7 +31,6 @@ from llama_stack.apis.inference import (
Message,
ResponseFormat,
SamplingParams,
TextTruncation,
ToolChoice,
ToolConfig,
ToolDefinition,
@ -66,9 +62,7 @@ from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
from llama_stack.providers.utils.inference.prompt_adapter import (
chat_completion_request_to_prompt,
completion_request_to_prompt,
content_has_media,
convert_image_content_to_url,
interleaved_content_as_str,
request_has_media,
)
@ -363,27 +357,6 @@ class OllamaInferenceAdapter(
async for chunk in process_chat_completion_stream_response(stream, request):
yield chunk
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)
assert all(not content_has_media(content) for content in contents), (
"Ollama does not support media for embeddings"
)
response = await self.ollama_client.embed(
model=model.provider_resource_id,
input=[interleaved_content_as_str(content) for content in contents],
)
embeddings = response["embeddings"]
return EmbeddingsResponse(embeddings=embeddings)
async def register_model(self, model: Model) -> Model:
if await self.check_model_availability(model.provider_model_id):
return model