forked from phoenix-oss/llama-stack-mirror
8de8eb03c8
## What does this PR do?
This is a long-pending change and particularly important to get done
now.
Specifically:
- we cannot "localize" (aka download) any URLs from media attachments
anywhere near our modeling code. it must be done within llama-stack.
- `PIL.Image` is infesting all our APIs via `ImageMedia ->
InterleavedTextMedia` and that cannot be right at all. Anything in the
API surface must be "naturally serializable". We need a standard `{
type: "image", image_url: "<...>" }` which is more extensible
- `UserMessage`, `SystemMessage`, etc. are moved completely to
llama-stack from the llama-models repository.
See https://github.com/meta-llama/llama-models/pull/244 for the
corresponding PR in llama-models.
## Test Plan
```bash
cd llama_stack/providers/tests
pytest -s -v -k "fireworks or ollama or together" inference/test_vision_inference.py
pytest -s -v -k "(fireworks or ollama or together) and llama_3b" inference/test_text_inference.py
pytest -s -v -k chroma memory/test_memory.py \
--env EMBEDDING_DIMENSION=384 --env CHROMA_DB_PATH=/tmp/foobar
pytest -s -v -k fireworks agents/test_agents.py \
--safety-shield=meta-llama/Llama-Guard-3-8B \
--inference-model=meta-llama/Llama-3.1-8B-Instruct
```
Updated the client sdk (see PR ...), installed the SDK in the same
environment and then ran the SDK tests:
```bash
cd tests/client-sdk
LLAMA_STACK_CONFIG=together pytest -s -v agents/test_agents.py
LLAMA_STACK_CONFIG=ollama pytest -s -v memory/test_memory.py
# this one needed a bit of hacking in the run.yaml to ensure I could register the vision model correctly
INFERENCE_MODEL=llama3.2-vision:latest LLAMA_STACK_CONFIG=ollama pytest -s -v inference/test_inference.py
```
70 lines
2.2 KiB
Python
70 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.
|
|
|
|
import logging
|
|
from typing import Any, Dict, List
|
|
|
|
from llama_stack.apis.safety import * # noqa: F403
|
|
from llama_stack.apis.inference import Message
|
|
from llama_stack.providers.utils.inference.prompt_adapter import (
|
|
interleaved_content_as_str,
|
|
)
|
|
|
|
from .config import CodeScannerConfig
|
|
|
|
|
|
log = logging.getLogger(__name__)
|
|
|
|
ALLOWED_CODE_SCANNER_MODEL_IDS = [
|
|
"CodeScanner",
|
|
"CodeShield",
|
|
]
|
|
|
|
|
|
class MetaReferenceCodeScannerSafetyImpl(Safety):
|
|
def __init__(self, config: CodeScannerConfig, deps) -> None:
|
|
self.config = config
|
|
|
|
async def initialize(self) -> None:
|
|
pass
|
|
|
|
async def shutdown(self) -> None:
|
|
pass
|
|
|
|
async def register_shield(self, shield: Shield) -> None:
|
|
if shield.provider_resource_id not in ALLOWED_CODE_SCANNER_MODEL_IDS:
|
|
raise ValueError(
|
|
f"Unsupported Code Scanner ID: {shield.provider_resource_id}. Allowed IDs: {ALLOWED_CODE_SCANNER_MODEL_IDS}"
|
|
)
|
|
|
|
async def run_shield(
|
|
self,
|
|
shield_id: str,
|
|
messages: List[Message],
|
|
params: Dict[str, Any] = None,
|
|
) -> RunShieldResponse:
|
|
shield = await self.shield_store.get_shield(shield_id)
|
|
if not shield:
|
|
raise ValueError(f"Shield {shield_id} not found")
|
|
|
|
from codeshield.cs import CodeShield
|
|
|
|
text = "\n".join([interleaved_content_as_str(m.content) for m in messages])
|
|
log.info(f"Running CodeScannerShield on {text[50:]}")
|
|
result = await CodeShield.scan_code(text)
|
|
|
|
violation = None
|
|
if result.is_insecure:
|
|
violation = SafetyViolation(
|
|
violation_level=(ViolationLevel.ERROR),
|
|
user_message="Sorry, I found security concerns in the code.",
|
|
metadata={
|
|
"violation_type": ",".join(
|
|
[issue.pattern_id for issue in result.issues_found]
|
|
)
|
|
},
|
|
)
|
|
return RunShieldResponse(violation=violation)
|