forked from phoenix-oss/llama-stack-mirror
ec4fc800cc
This is yet another of those large PRs (hopefully we will have less and less of them as things mature fast). This one introduces substantial improvements and some simplifications to the stack. Most important bits: * Agents reference implementation now has support for session / turn persistence. The default implementation uses sqlite but there's also support for using Redis. * We have re-architected the structure of the Stack APIs to allow for more flexible routing. The motivating use cases are: - routing model A to ollama and model B to a remote provider like Together - routing shield A to local impl while shield B to a remote provider like Bedrock - routing a vector memory bank to Weaviate while routing a keyvalue memory bank to Redis * Support for provider specific parameters to be passed from the clients. A client can pass data using `x_llamastack_provider_data` parameter which can be type-checked and provided to the Adapter implementations.
64 lines
1.9 KiB
Python
64 lines
1.9 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 abc import ABC, abstractmethod
|
|
from typing import List
|
|
|
|
from llama_models.llama3.api.datatypes import interleaved_text_media_as_str, Message
|
|
from pydantic import BaseModel
|
|
from llama_stack.apis.safety import * # noqa: F403
|
|
|
|
CANNED_RESPONSE_TEXT = "I can't answer that. Can I help with something else?"
|
|
|
|
|
|
# TODO: clean this up; just remove this type completely
|
|
class ShieldResponse(BaseModel):
|
|
is_violation: bool
|
|
violation_type: Optional[str] = None
|
|
violation_return_message: Optional[str] = None
|
|
|
|
|
|
# TODO: this is a caller / agent concern
|
|
class OnViolationAction(Enum):
|
|
IGNORE = 0
|
|
WARN = 1
|
|
RAISE = 2
|
|
|
|
|
|
class ShieldBase(ABC):
|
|
def __init__(
|
|
self,
|
|
on_violation_action: OnViolationAction = OnViolationAction.RAISE,
|
|
):
|
|
self.on_violation_action = on_violation_action
|
|
|
|
@abstractmethod
|
|
async def run(self, messages: List[Message]) -> ShieldResponse:
|
|
raise NotImplementedError()
|
|
|
|
|
|
def message_content_as_str(message: Message) -> str:
|
|
return interleaved_text_media_as_str(message.content)
|
|
|
|
|
|
# For shields that operate on simple strings
|
|
class TextShield(ShieldBase):
|
|
def convert_messages_to_text(self, messages: List[Message]) -> str:
|
|
return "\n".join([message_content_as_str(m) for m in messages])
|
|
|
|
async def run(self, messages: List[Message]) -> ShieldResponse:
|
|
text = self.convert_messages_to_text(messages)
|
|
return await self.run_impl(text)
|
|
|
|
@abstractmethod
|
|
async def run_impl(self, text: str) -> ShieldResponse:
|
|
raise NotImplementedError()
|
|
|
|
|
|
class DummyShield(TextShield):
|
|
async def run_impl(self, text: str) -> ShieldResponse:
|
|
# Dummy return LOW to test e2e
|
|
return ShieldResponse(is_violation=False)
|