mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 02:53:30 +00:00
efe791bab7
# What does this PR do?
* Changes the registry to store only one RoutableObject per identifier.
Before it was a list, which is not really required.
* Adds impl for updates and deletes
* Updates routing table to handle updates correctly
## Test Plan
```
❯ llama-stack-client models list
+------------------------+---------------+------------------------------------+------------+
| identifier | provider_id | provider_resource_id | metadata |
+========================+===============+====================================+============+
| Llama3.1-405B-Instruct | fireworks-0 | fireworks/llama-v3p1-405b-instruct | {} |
+------------------------+---------------+------------------------------------+------------+
| Llama3.1-8B-Instruct | fireworks-0 | fireworks/llama-v3p1-8b-instruct | {} |
+------------------------+---------------+------------------------------------+------------+
| Llama3.2-3B-Instruct | fireworks-0 | fireworks/llama-v3p2-1b-instruct | {} |
+------------------------+---------------+------------------------------------+------------+
❯ llama-stack-client models register dineshyv-model --provider-model-id=fireworks/llama-v3p1-70b-instruct
Successfully registered model dineshyv-model
❯ llama-stack-client models list
+------------------------+---------------+------------------------------------+------------+
| identifier | provider_id | provider_resource_id | metadata |
+========================+===============+====================================+============+
| Llama3.1-405B-Instruct | fireworks-0 | fireworks/llama-v3p1-405b-instruct | {} |
+------------------------+---------------+------------------------------------+------------+
| Llama3.1-8B-Instruct | fireworks-0 | fireworks/llama-v3p1-8b-instruct | {} |
+------------------------+---------------+------------------------------------+------------+
| Llama3.2-3B-Instruct | fireworks-0 | fireworks/llama-v3p2-1b-instruct | {} |
+------------------------+---------------+------------------------------------+------------+
| dineshyv-model | fireworks-0 | fireworks/llama-v3p1-70b-instruct | {} |
+------------------------+---------------+------------------------------------+------------+
❯ llama-stack-client models update dineshyv-model --provider-model-id=fireworks/llama-v3p1-405b-instruct
Successfully updated model dineshyv-model
❯ llama-stack-client models list
+------------------------+---------------+------------------------------------+------------+
| identifier | provider_id | provider_resource_id | metadata |
+========================+===============+====================================+============+
| Llama3.1-405B-Instruct | fireworks-0 | fireworks/llama-v3p1-405b-instruct | {} |
+------------------------+---------------+------------------------------------+------------+
| Llama3.1-8B-Instruct | fireworks-0 | fireworks/llama-v3p1-8b-instruct | {} |
+------------------------+---------------+------------------------------------+------------+
| Llama3.2-3B-Instruct | fireworks-0 | fireworks/llama-v3p2-1b-instruct | {} |
+------------------------+---------------+------------------------------------+------------+
| dineshyv-model | fireworks-0 | fireworks/llama-v3p1-405b-instruct | {} |
+------------------------+---------------+------------------------------------+------------+
llama-stack-client models delete dineshyv-model
❯ llama-stack-client models list
+------------------------+---------------+------------------------------------+------------+
| identifier | provider_id | provider_resource_id | metadata |
+========================+===============+====================================+============+
| Llama3.1-405B-Instruct | fireworks-0 | fireworks/llama-v3p1-405b-instruct | {} |
+------------------------+---------------+------------------------------------+------------+
| Llama3.1-8B-Instruct | fireworks-0 | fireworks/llama-v3p1-8b-instruct | {} |
+------------------------+---------------+------------------------------------+------------+
| Llama3.2-3B-Instruct | fireworks-0 | fireworks/llama-v3p2-1b-instruct | {} |
+------------------------+---------------+------------------------------------+------------+
```
---------
Co-authored-by: Dinesh Yeduguru <dineshyv@fb.com>
68 lines
2 KiB
Python
68 lines
2 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# 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, Dict, List, Literal, Optional, Protocol, runtime_checkable
|
|
|
|
from llama_models.schema_utils import json_schema_type, webmethod
|
|
from pydantic import BaseModel, Field
|
|
|
|
from llama_stack.apis.resource import Resource, ResourceType
|
|
|
|
|
|
class CommonModelFields(BaseModel):
|
|
metadata: Dict[str, Any] = Field(
|
|
default_factory=dict,
|
|
description="Any additional metadata for this model",
|
|
)
|
|
|
|
|
|
@json_schema_type
|
|
class Model(CommonModelFields, Resource):
|
|
type: Literal[ResourceType.model.value] = ResourceType.model.value
|
|
|
|
@property
|
|
def model_id(self) -> str:
|
|
return self.identifier
|
|
|
|
@property
|
|
def provider_model_id(self) -> str:
|
|
return self.provider_resource_id
|
|
|
|
|
|
class ModelInput(CommonModelFields):
|
|
model_id: str
|
|
provider_id: Optional[str] = None
|
|
provider_model_id: Optional[str] = None
|
|
|
|
|
|
@runtime_checkable
|
|
class Models(Protocol):
|
|
@webmethod(route="/models/list", method="GET")
|
|
async def list_models(self) -> List[Model]: ...
|
|
|
|
@webmethod(route="/models/get", method="GET")
|
|
async def get_model(self, identifier: str) -> Optional[Model]: ...
|
|
|
|
@webmethod(route="/models/register", method="POST")
|
|
async def register_model(
|
|
self,
|
|
model_id: str,
|
|
provider_model_id: Optional[str] = None,
|
|
provider_id: Optional[str] = None,
|
|
metadata: Optional[Dict[str, Any]] = None,
|
|
) -> Model: ...
|
|
|
|
@webmethod(route="/models/update", method="POST")
|
|
async def update_model(
|
|
self,
|
|
model_id: str,
|
|
provider_model_id: Optional[str] = None,
|
|
provider_id: Optional[str] = None,
|
|
metadata: Optional[Dict[str, Any]] = None,
|
|
) -> Model: ...
|
|
|
|
@webmethod(route="/models/delete", method="POST")
|
|
async def delete_model(self, model_id: str) -> None: ...
|