mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 10:54:19 +00:00
9487ad8294
* API Keys passed from Client instead of distro configuration * delete distribution registry * Rename the "package" word away * Introduce a "Router" layer for providers Some providers need to be factorized and considered as thin routing layers on top of other providers. Consider two examples: - The inference API should be a routing layer over inference providers, routed using the "model" key - The memory banks API is another instance where various memory bank types will be provided by independent providers (e.g., a vector store is served by Chroma while a keyvalue memory can be served by Redis or PGVector) This commit introduces a generalized routing layer for this purpose. * update `apis_to_serve` * llama_toolchain -> llama_stack * Codemod from llama_toolchain -> llama_stack - added providers/registry - cleaned up api/ subdirectories and moved impls away - restructured api/api.py - from llama_stack.apis.<api> import foo should work now - update imports to do llama_stack.apis.<api> - update many other imports - added __init__, fixed some registry imports - updated registry imports - create_agentic_system -> create_agent - AgenticSystem -> Agent * Moved some stuff out of common/; re-generated OpenAPI spec * llama-toolchain -> llama-stack (hyphens) * add control plane API * add redis adapter + sqlite provider * move core -> distribution * Some more toolchain -> stack changes * small naming shenanigans * Removing custom tool and agent utilities and moving them client side * Move control plane to distribution server for now * Remove control plane from API list * no codeshield dependency randomly plzzzzz * Add "fire" as a dependency * add back event loggers * stack configure fixes * use brave instead of bing in the example client * add init file so it gets packaged * add init files so it gets packaged * Update MANIFEST * bug fix --------- Co-authored-by: Hardik Shah <hjshah@fb.com> Co-authored-by: Xi Yan <xiyan@meta.com> Co-authored-by: Ashwin Bharambe <ashwin@meta.com>
65 lines
2.1 KiB
Python
65 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 List
|
|
|
|
from llama_models.llama3.api.datatypes import Message, Role, UserMessage
|
|
|
|
from llama_stack.apis.safety import (
|
|
OnViolationAction,
|
|
RunShieldRequest,
|
|
Safety,
|
|
ShieldDefinition,
|
|
ShieldResponse,
|
|
)
|
|
from termcolor import cprint
|
|
|
|
|
|
class SafetyException(Exception): # noqa: N818
|
|
def __init__(self, response: ShieldResponse):
|
|
self.response = response
|
|
super().__init__(response.violation_return_message)
|
|
|
|
|
|
class ShieldRunnerMixin:
|
|
def __init__(
|
|
self,
|
|
safety_api: Safety,
|
|
input_shields: List[ShieldDefinition] = None,
|
|
output_shields: List[ShieldDefinition] = None,
|
|
):
|
|
self.safety_api = safety_api
|
|
self.input_shields = input_shields
|
|
self.output_shields = output_shields
|
|
|
|
async def run_shields(
|
|
self, messages: List[Message], shields: List[ShieldDefinition]
|
|
) -> List[ShieldResponse]:
|
|
messages = messages.copy()
|
|
# some shields like llama-guard require the first message to be a user message
|
|
# since this might be a tool call, first role might not be user
|
|
if len(messages) > 0 and messages[0].role != Role.user.value:
|
|
messages[0] = UserMessage(content=messages[0].content)
|
|
|
|
res = await self.safety_api.run_shields(
|
|
RunShieldRequest(
|
|
messages=messages,
|
|
shields=shields,
|
|
)
|
|
)
|
|
|
|
results = res.responses
|
|
for shield, r in zip(shields, results):
|
|
if r.is_violation:
|
|
if shield.on_violation_action == OnViolationAction.RAISE:
|
|
raise SafetyException(r)
|
|
elif shield.on_violation_action == OnViolationAction.WARN:
|
|
cprint(
|
|
f"[Warn]{shield.__class__.__name__} raised a warning",
|
|
color="red",
|
|
)
|
|
|
|
return results
|