API Updates (#73)

* 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>

llama_stack/apis/safety/safety.py

@@ -0,0 +1,91 @@
+# 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: ...