mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
983d6ce2df
# What does this PR do?
This PR kills the notion of "ShieldType". The impetus for this is the
realization:
> Why is keyword llama-guard appearing so many times everywhere,
sometimes with hyphens, sometimes with underscores?
Now that we have a notion of "provider specific resource identifiers"
and "user specific aliases" for those and the fact that this works with
models ("Llama3.1-8B-Instruct" <> "fireworks/llama-3pv1-..."), we can
follow the same rules for Shields.
So each Safety provider can make up a notion of identifiers it has
registered. This already happens with Bedrock correctly. We just
generalize it for Llama Guard, Prompt Guard, etc.
For Llama Guard, we further simplify by just adopting the underlying
model name itself as the identifier! No confusion necessary.
While doing this, I noticed a bug in our DistributionRegistry where we
weren't scoping identifiers by type. Fixed.
## Feature/Issue validation/testing/test plan
Ran (inference, safety, memory, agents) tests with ollama and fireworks
providers.
87 lines
2.5 KiB
Python
87 lines
2.5 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.
|
|
|
|
import asyncio
|
|
|
|
from typing import List, Optional
|
|
|
|
import fire
|
|
import httpx
|
|
from termcolor import cprint
|
|
|
|
from .shields import * # noqa: F403
|
|
|
|
|
|
class ShieldsClient(Shields):
|
|
def __init__(self, base_url: str):
|
|
self.base_url = base_url
|
|
|
|
async def initialize(self) -> None:
|
|
pass
|
|
|
|
async def shutdown(self) -> None:
|
|
pass
|
|
|
|
async def list_shields(self) -> List[Shield]:
|
|
async with httpx.AsyncClient() as client:
|
|
response = await client.get(
|
|
f"{self.base_url}/shields/list",
|
|
headers={"Content-Type": "application/json"},
|
|
)
|
|
response.raise_for_status()
|
|
return [Shield(**x) for x in response.json()]
|
|
|
|
async def register_shield(
|
|
self,
|
|
shield_id: str,
|
|
provider_shield_id: Optional[str],
|
|
provider_id: Optional[str],
|
|
params: Optional[Dict[str, Any]],
|
|
) -> None:
|
|
async with httpx.AsyncClient() as client:
|
|
response = await client.post(
|
|
f"{self.base_url}/shields/register",
|
|
json={
|
|
"shield_id": shield_id,
|
|
"provider_shield_id": provider_shield_id,
|
|
"provider_id": provider_id,
|
|
"params": params,
|
|
},
|
|
headers={"Content-Type": "application/json"},
|
|
)
|
|
response.raise_for_status()
|
|
|
|
async def get_shield(self, shield_id: str) -> Optional[Shield]:
|
|
async with httpx.AsyncClient() as client:
|
|
response = await client.get(
|
|
f"{self.base_url}/shields/get",
|
|
params={
|
|
"shield_id": shield_id,
|
|
},
|
|
headers={"Content-Type": "application/json"},
|
|
)
|
|
response.raise_for_status()
|
|
|
|
j = response.json()
|
|
if j is None:
|
|
return None
|
|
|
|
return Shield(**j)
|
|
|
|
|
|
async def run_main(host: str, port: int, stream: bool):
|
|
client = ShieldsClient(f"http://{host}:{port}")
|
|
|
|
response = await client.list_shields()
|
|
cprint(f"list_shields response={response}", "green")
|
|
|
|
|
|
def main(host: str, port: int, stream: bool = True):
|
|
asyncio.run(run_main(host, port, stream))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
fire.Fire(main)
|