phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-16 06:53:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

working tests

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-11-08 14:10:40 -08:00
parent 4f5c4d1e3b
commit 23777abeb7
4 changed files with 54 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

15
llama_stack/distribution/routers/routers.py
View file

@ -4,7 +4,7 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from typing import Any, AsyncGenerator, Dict, List
from typing import Any, AsyncGenerator, Dict, List, Optional
from llama_stack.apis.datasetio.datasetio import DatasetIO
from llama_stack.distribution.datatypes import RoutingTable
@ -71,8 +71,17 @@ class InferenceRouter(Inference):
async def shutdown(self) -> None:
pass
async def register_model(self, model: Model) -> None:
await self.routing_table.register_model(model)
async def register_model(
self,
model_id: str,
provider_model_id: Optional[str] = None,
provider_id: Optional[str] = None,
llama_model: Optional[str] = None,
metadata: Optional[Dict[str, Any]] = None,
) -> None:
await self.routing_table.register_model(
model_id, provider_model_id, provider_id, llama_model, metadata
)
async def chat_completion(
self,