phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 18:02:40 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

tracing for APIs

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-11-26 14:07:48 -08:00
parent c2a4850a79
commit af8a1fe5b3
8 changed files with 126 additions and 63 deletions
Download patch file Download diff file Expand all files Collapse all files

5
llama_stack/apis/inference/inference.py
View file

@ -21,7 +21,7 @@ from llama_models.schema_utils import json_schema_type, webmethod
from pydantic import BaseModel, Field
from typing_extensions import Annotated
from llama_stack.distribution.tracing import trace_protocol
from llama_stack.distribution.tracing import trace_protocol, traced
from llama_models.llama3.api.datatypes import * # noqa: F403
from llama_stack.apis.models import * # noqa: F403
@ -227,6 +227,7 @@ class Inference(Protocol):
model_store: ModelStore
@webmethod(route="/inference/completion")
@traced(input="content")
async def completion(
self,
model_id: str,
@ -238,6 +239,7 @@ class Inference(Protocol):
) -> Union[CompletionResponse, AsyncIterator[CompletionResponseStreamChunk]]: ...
@webmethod(route="/inference/chat-completion")
@traced(input="messages")
async def chat_completion(
self,
model_id: str,
@ -255,6 +257,7 @@ class Inference(Protocol):
]: ...
@webmethod(route="/inference/embeddings")
@traced(input="contents")
async def embeddings(
self,
model_id: str,