mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-16 23:03:49 +00:00
working tests
This commit is contained in:
parent
4f5c4d1e3b
commit
23777abeb7
4 changed files with 54 additions and 13 deletions
|
@ -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,
|
||||
|
|
|
@ -202,7 +202,35 @@ class ModelsRoutingTable(CommonRoutingTableImpl, Models):
|
|||
async def get_model(self, identifier: str) -> Optional[Model]:
|
||||
return await self.get_object_by_identifier(identifier)
|
||||
|
||||
async def register_model(self, model: Model) -> None:
|
||||
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:
|
||||
if provider_model_id is None:
|
||||
provider_model_id = model_id
|
||||
if provider_id is None:
|
||||
# If provider_id not specified, use the only provider if it supports this model
|
||||
if len(self.impls_by_provider_id) == 1:
|
||||
provider_id = list(self.impls_by_provider_id.keys())[0]
|
||||
else:
|
||||
raise ValueError(
|
||||
"No provider specified and multiple providers available. Please specify a provider_id."
|
||||
)
|
||||
if metadata is None:
|
||||
metadata = {}
|
||||
if llama_model is None:
|
||||
llama_model = model_id
|
||||
model = Model(
|
||||
identifier=model_id,
|
||||
provider_resource_id=provider_model_id,
|
||||
provider_id=provider_id,
|
||||
llama_model=llama_model,
|
||||
metadata=metadata,
|
||||
)
|
||||
await self.register_object(model)
|
||||
|
||||
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue