phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-28 19:04:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

OpenAI compat embeddings API

Browse source
This commit is contained in:
Hardik Shah 2025-05-29 15:27:59 -07:00
parent 2603f10f95
commit f2c2a05f58
20 changed files with 706 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

11
llama_stack/providers/inline/inference/vllm/vllm.py
View file

@ -40,6 +40,7 @@ from llama_stack.apis.inference import (
JsonSchemaResponseFormat,
LogProbConfig,
Message,
OpenAIEmbeddingsResponse,
ResponseFormat,
SamplingParams,
TextTruncation,
@ -410,6 +411,16 @@ class VLLMInferenceImpl(
) -> EmbeddingsResponse:
raise NotImplementedError()
async def openai_embeddings(
self,
model: str,
input: str | list[str],
encoding_format: str | None = "float",
dimensions: int | None = None,
user: str | None = None,
) -> OpenAIEmbeddingsResponse:
raise NotImplementedError()
async def chat_completion(
self,
model_id: str,