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: remove /v1/inference/completion and implementations

Browse source
This commit is contained in:
Matthew Farrellee 2025-09-30 03:46:07 -04:00
parent 606f4cf281
commit 4b641d7127
78 changed files with 16143 additions and 17755 deletions
Download patch file Download diff file Expand all files Collapse all files

16
llama_stack/providers/remote/inference/databricks/databricks.py
View file

@ -9,14 +9,9 @@ from typing import Any
from databricks.sdk import WorkspaceClient
from llama_stack.apis.common.content_types import (
InterleavedContent,
)
from llama_stack.apis.inference import (
ChatCompletionResponse,
ChatCompletionResponseStreamChunk,
CompletionResponse,
CompletionResponseStreamChunk,
Inference,
LogProbConfig,
Message,
@ -63,17 +58,6 @@ class DatabricksInferenceAdapter(
async def shutdown(self) -> None:
pass
async def completion(
self,
model_id: str,
content: InterleavedContent,
sampling_params: SamplingParams | None = None,
response_format: ResponseFormat | None = None,
stream: bool | None = False,
logprobs: LogProbConfig | None = None,
) -> CompletionResponse | AsyncIterator[CompletionResponseStreamChunk]:
raise NotImplementedError()
async def openai_completion(
self,
model: str,