mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +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>
91 lines
2.3 KiB
Python
91 lines
2.3 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 Dict, List, Optional, Protocol, Union
|
|
|
|
from llama_models.schema_utils import json_schema_type, webmethod
|
|
from pydantic import BaseModel, validator
|
|
|
|
from llama_models.llama3.api.datatypes import * # noqa: F403
|
|
from llama_stack.apis.common.deployment_types import RestAPIExecutionConfig
|
|
|
|
|
|
@json_schema_type
|
|
class BuiltinShield(Enum):
|
|
llama_guard = "llama_guard"
|
|
code_scanner_guard = "code_scanner_guard"
|
|
third_party_shield = "third_party_shield"
|
|
injection_shield = "injection_shield"
|
|
jailbreak_shield = "jailbreak_shield"
|
|
|
|
|
|
ShieldType = Union[BuiltinShield, str]
|
|
|
|
|
|
@json_schema_type
|
|
class OnViolationAction(Enum):
|
|
IGNORE = 0
|
|
WARN = 1
|
|
RAISE = 2
|
|
|
|
|
|
@json_schema_type
|
|
class ShieldDefinition(BaseModel):
|
|
shield_type: ShieldType
|
|
description: Optional[str] = None
|
|
parameters: Optional[Dict[str, ToolParamDefinition]] = None
|
|
on_violation_action: OnViolationAction = OnViolationAction.RAISE
|
|
execution_config: Optional[RestAPIExecutionConfig] = None
|
|
|
|
@validator("shield_type", pre=True)
|
|
@classmethod
|
|
def validate_field(cls, v):
|
|
if isinstance(v, str):
|
|
try:
|
|
return BuiltinShield(v)
|
|
except ValueError:
|
|
return v
|
|
return v
|
|
|
|
|
|
@json_schema_type
|
|
class ShieldResponse(BaseModel):
|
|
shield_type: ShieldType
|
|
# TODO(ashwin): clean this up
|
|
is_violation: bool
|
|
violation_type: Optional[str] = None
|
|
violation_return_message: Optional[str] = None
|
|
|
|
@validator("shield_type", pre=True)
|
|
@classmethod
|
|
def validate_field(cls, v):
|
|
if isinstance(v, str):
|
|
try:
|
|
return BuiltinShield(v)
|
|
except ValueError:
|
|
return v
|
|
return v
|
|
|
|
|
|
@json_schema_type
|
|
class RunShieldRequest(BaseModel):
|
|
messages: List[Message]
|
|
shields: List[ShieldDefinition]
|
|
|
|
|
|
@json_schema_type
|
|
class RunShieldResponse(BaseModel):
|
|
responses: List[ShieldResponse]
|
|
|
|
|
|
class Safety(Protocol):
|
|
@webmethod(route="/safety/run_shields")
|
|
async def run_shields(
|
|
self,
|
|
messages: List[Message],
|
|
shields: List[ShieldDefinition],
|
|
) -> RunShieldResponse: ...
|