phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 11:12:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

use provider resource id to validate for models

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-11-12 08:21:37 -08:00
parent e4f14eafe2
commit 95b7f57d92
7 changed files with 75 additions and 46 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/apis/inference/inference.py
View file

@ -226,7 +226,7 @@ class Inference(Protocol):
@webmethod(route="/inference/completion")
async def completion(
self,
model: str,
model_id: str,
content: InterleavedTextMedia,
sampling_params: Optional[SamplingParams] = SamplingParams(),
response_format: Optional[ResponseFormat] = None,
@ -237,7 +237,7 @@ class Inference(Protocol):
@webmethod(route="/inference/chat_completion")
async def chat_completion(
self,
model: str,
model_id: str,
messages: List[Message],
sampling_params: Optional[SamplingParams] = SamplingParams(),
# zero-shot tool definitions as input to the model
@ -254,6 +254,6 @@ class Inference(Protocol):
@webmethod(route="/inference/embeddings")
async def embeddings(
self,
model: str,
model_id: str,
contents: List[InterleavedTextMedia],
) -> EmbeddingsResponse: ...