llama-stack-mirror/llama_stack/apis/safety/safety.py
Dinesh Yeduguru d800a16acd
Resource oriented design for shields (#399)
* init

* working bedrock tests

* bedrock test for inference fixes

* use env vars for bedrock guardrail vars

* add register in meta reference

* use correct shield impl in meta ref

* dont add together fixture

* right naming

* minor updates

* improved registration flow

* address feedback

---------

Co-authored-by: Dinesh Yeduguru <dineshyv@fb.com>
2024-11-08 12:16:11 -08:00

55 lines
1.4 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 enum import Enum
from typing import Any, Dict, List, Protocol, runtime_checkable
from llama_models.schema_utils import json_schema_type, webmethod
from pydantic import BaseModel
from llama_models.llama3.api.datatypes import * # noqa: F403
from llama_stack.apis.shields import * # noqa: F403
@json_schema_type
class ViolationLevel(Enum):
INFO = "info"
WARN = "warn"
ERROR = "error"
@json_schema_type
class SafetyViolation(BaseModel):
violation_level: ViolationLevel
# what message should you convey to the user
user_message: Optional[str] = None
# additional metadata (including specific violation codes) more for
# debugging, telemetry
metadata: Dict[str, Any] = Field(default_factory=dict)
@json_schema_type
class RunShieldResponse(BaseModel):
violation: Optional[SafetyViolation] = None
class ShieldStore(Protocol):
async def get_shield(self, identifier: str) -> Shield: ...
@runtime_checkable
class Safety(Protocol):
shield_store: ShieldStore
@webmethod(route="/safety/run_shield")
async def run_shield(
self,
shield_id: str,
messages: List[Message],
params: Dict[str, Any] = None,
) -> RunShieldResponse: ...