phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-13 13:02:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(api)!: support passing extra_body to embeddings and vector_stores APIs

Browse source 
Applies the same pattern from #3777 to embeddings and vector_stores.create() endpoints.

Breaking change: Method signatures now accept a single params object with Pydantic extra="allow" instead of individual parameters. Provider-specific params can be passed via extra_body and accessed through params.model_extra.

Updated APIs: openai_embeddings(), openai_create_vector_store(), openai_create_vector_store_file_batch()
This commit is contained in:
Ashwin Bharambe 2025-10-11 15:27:47 -07:00
parent cfd2e303db
commit 74e2976c1e
20 changed files with 364 additions and 297 deletions
Download patch file Download diff file Expand all files Collapse all files

23
llama_stack/core/routers/inference.py
View file

@ -40,6 +40,7 @@ from llama_stack.apis.inference import (
OpenAICompletion,
OpenAICompletionRequestWithExtraBody,
OpenAICompletionWithInputMessages,
OpenAIEmbeddingsRequestWithExtraBody,
OpenAIEmbeddingsResponse,
OpenAIMessageParam,
Order,
@ -279,26 +280,18 @@ class InferenceRouter(Inference):
async def openai_embeddings(
self,
model: str,
input: str | list[str],
encoding_format: str | None = "float",
dimensions: int | None = None,
user: str | None = None,
params: Annotated[OpenAIEmbeddingsRequestWithExtraBody, Body(...)],
) -> OpenAIEmbeddingsResponse:
logger.debug(
f"InferenceRouter.openai_embeddings: {model=}, input_type={type(input)}, {encoding_format=}, {dimensions=}",
)
model_obj = await self._get_model(model, ModelType.embedding)
params = dict(
model=model_obj.identifier,
input=input,
encoding_format=encoding_format,
dimensions=dimensions,
user=user,
f"InferenceRouter.openai_embeddings: model={params.model}, input_type={type(params.input)}, encoding_format={params.encoding_format}, dimensions={params.dimensions}",
)
model_obj = await self._get_model(params.model, ModelType.embedding)
# Update model to use resolved identifier
params.model = model_obj.identifier
provider = await self.routing_table.get_provider_impl(model_obj.identifier)
return await provider.openai_embeddings(**params)
return await provider.openai_embeddings(params)
async def list_chat_completions(
self,