forked from phoenix-oss/llama-stack-mirror
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.
66 lines
2.1 KiB
Python
66 lines
2.1 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
|
|
|
|
from llama_models.llama3.api.datatypes import interleaved_text_media_as_str, Message
|
|
from termcolor import cprint
|
|
|
|
from .config import CodeScannerConfig
|
|
|
|
from llama_stack.apis.safety import * # noqa: F403
|
|
|
|
|
|
ALLOWED_CODE_SCANNER_MODEL_IDS = [
|
|
"CodeScanner",
|
|
"CodeShield",
|
|
]
|
|
|
|
|
|
class MetaReferenceCodeScannerSafetyImpl(Safety):
|
|
def __init__(self, config: CodeScannerConfig, deps) -> None:
|
|
self.config = config
|
|
|
|
async def initialize(self) -> None:
|
|
pass
|
|
|
|
async def shutdown(self) -> None:
|
|
pass
|
|
|
|
async def register_shield(self, shield: Shield) -> None:
|
|
if shield.provider_resource_id not in ALLOWED_CODE_SCANNER_MODEL_IDS:
|
|
raise ValueError(
|
|
f"Unsupported Code Scanner ID: {shield.provider_resource_id}. Allowed IDs: {ALLOWED_CODE_SCANNER_MODEL_IDS}"
|
|
)
|
|
|
|
async def run_shield(
|
|
self,
|
|
shield_id: str,
|
|
messages: List[Message],
|
|
params: Dict[str, Any] = None,
|
|
) -> RunShieldResponse:
|
|
shield = await self.shield_store.get_shield(shield_id)
|
|
if not shield:
|
|
raise ValueError(f"Shield {shield_id} not found")
|
|
|
|
from codeshield.cs import CodeShield
|
|
|
|
text = "\n".join([interleaved_text_media_as_str(m.content) for m in messages])
|
|
cprint(f"Running CodeScannerShield on {text[50:]}", color="magenta")
|
|
result = await CodeShield.scan_code(text)
|
|
|
|
violation = None
|
|
if result.is_insecure:
|
|
violation = SafetyViolation(
|
|
violation_level=(ViolationLevel.ERROR),
|
|
user_message="Sorry, I found security concerns in the code.",
|
|
metadata={
|
|
"violation_type": ",".join(
|
|
[issue.pattern_id for issue in result.issues_found]
|
|
)
|
|
},
|
|
)
|
|
return RunShieldResponse(violation=violation)
|