mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 02:53:30 +00:00
e830814399
* Add distribution CLI scaffolding * More progress towards `llama distribution install` * getting closer to a distro definition, distro install + configure works * Distribution server now functioning * read existing configuration, save enums properly * Remove inference uvicorn server entrypoint and llama inference CLI command * updated dependency and client model name * Improved exception handling * local imports for faster cli * undo a typo, add a passthrough distribution * implement full-passthrough in the server * add safety adapters, configuration handling, server + clients * cleanup, moving stuff to common, nuke utils * Add a Path() wrapper at the earliest place * fixes * Bring agentic system api to toolchain Add adapter dependencies and resolve adapters using a topological sort * refactor to reduce size of `agentic_system` * move straggler files and fix some important existing bugs * ApiSurface -> Api * refactor a method out * Adapter -> Provider * Make each inference provider into its own subdirectory * installation fixes * Rename Distribution -> DistributionSpec, simplify RemoteProviders * dict key instead of attr * update inference config to take model and not model_dir * Fix passthrough streaming, send headers properly not part of body :facepalm * update safety to use model sku ids and not model dirs * Update cli_reference.md * minor fixes * add DistributionConfig, fix a bug in model download * Make install + start scripts do proper configuration automatically * Update CLI_reference * Nuke fp8_requirements, fold fbgemm into common requirements * Update README, add newline between API surface configurations * Refactor download functionality out of the Command so can be reused * Add `llama model download` alias for `llama download` * Show message about checksum file so users can check themselves * Simpler intro statements * get ollama working * Reduce a bunch of dependencies from toolchain Some improvements to the distribution install script * Avoid using `conda run` since it buffers everything * update dependencies and rely on LLAMA_TOOLCHAIN_DIR for dev purposes * add validation for configuration input * resort imports * make optional subclasses default to yes for configuration * Remove additional_pip_packages; move deps to providers * for inline make 8b model the default * Add scripts to MANIFEST * allow installing from test.pypi.org * Fix #2 to help with testing packages * Must install llama-models at that same version first * fix PIP_ARGS --------- Co-authored-by: Hardik Shah <hjshah@fb.com> Co-authored-by: Hardik Shah <hjshah@meta.com>
65 lines
2.2 KiB
Python
65 lines
2.2 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_1.api.datatypes import Message, Role
|
|
from llama_toolchain.safety.api.datatypes import (
|
|
OnViolationAction,
|
|
ShieldDefinition,
|
|
ShieldResponse,
|
|
)
|
|
from llama_toolchain.safety.api.endpoints import RunShieldRequest, Safety
|
|
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]:
|
|
# 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:
|
|
# TODO(ashwin): we need to change the type of the message, this kind of modification
|
|
# is no longer appropriate
|
|
messages[0].role = Role.user.value
|
|
|
|
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
|