mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-17 17:59:52 +00:00
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> chore: Enable keyword search for Milvus inline (#3073) With https://github.com/milvus-io/milvus-lite/pull/294 - Milvus Lite supports keyword search using BM25. While introducing keyword search we had explicitly disabled it for inline milvus. This PR removes the need for the check, and enables `inline::milvus` for tests. <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> Run llama stack with `inline::milvus` enabled: ``` pytest tests/integration/vector_io/test_openai_vector_stores.py::test_openai_vector_store_search_modes --stack-config=http://localhost:8321 --embedding-model=all-MiniLM-L6-v2 -v ``` ``` INFO 2025-08-07 17:06:20,932 tests.integration.conftest:64 tests: Setting DISABLE_CODE_SANDBOX=1 for macOS =========================================================================================== test session starts ============================================================================================ platform darwin -- Python 3.12.11, pytest-7.4.4, pluggy-1.5.0 -- /Users/vnarsing/miniconda3/envs/stack-client/bin/python cachedir: .pytest_cache metadata: {'Python': '3.12.11', 'Platform': 'macOS-14.7.6-arm64-arm-64bit', 'Packages': {'pytest': '7.4.4', 'pluggy': '1.5.0'}, 'Plugins': {'asyncio': '0.23.8', 'cov': '6.0.0', 'timeout': '2.2.0', 'socket': '0.7.0', 'html': '3.1.1', 'langsmith': '0.3.39', 'anyio': '4.8.0', 'metadata': '3.0.0'}} rootdir: /Users/vnarsing/go/src/github/meta-llama/llama-stack configfile: pyproject.toml plugins: asyncio-0.23.8, cov-6.0.0, timeout-2.2.0, socket-0.7.0, html-3.1.1, langsmith-0.3.39, anyio-4.8.0, metadata-3.0.0 asyncio: mode=Mode.AUTO collected 3 items tests/integration/vector_io/test_openai_vector_stores.py::test_openai_vector_store_search_modes[None-None-all-MiniLM-L6-v2-None-384-vector] PASSED [ 33%] tests/integration/vector_io/test_openai_vector_stores.py::test_openai_vector_store_search_modes[None-None-all-MiniLM-L6-v2-None-384-keyword] PASSED [ 66%] tests/integration/vector_io/test_openai_vector_stores.py::test_openai_vector_store_search_modes[None-None-all-MiniLM-L6-v2-None-384-hybrid] PASSED [100%] ============================================================================================ 3 passed in 4.75s ============================================================================================= ``` Signed-off-by: Varsha Prasad Narsing <varshaprasad96@gmail.com> Co-authored-by: Francisco Arceo <arceofrancisco@gmail.com> chore: Fixup main pre commit (#3204) build: Bump version to 0.2.18 chore: Faster npm pre-commit (#3206) Adds npm to pre-commit.yml installation and caches ui Removes node installation during pre-commit. <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> <!-- Describe the tests you ran to verify your changes with result summaries. *Provide clear instructions so the plan can be easily re-executed.* --> Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> chiecking in for tonight, wip moving to agents api Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> remove log Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> updated Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> fix: disable ui-prettier & ui-eslint (#3207) chore(pre-commit): add pre-commit hook to enforce llama_stack logger usage (#3061) This PR adds a step in pre-commit to enforce using `llama_stack` logger. Currently, various parts of the code base uses different loggers. As a custom `llama_stack` logger exist and used in the codebase, it is better to standardize its utilization. Signed-off-by: Mustafa Elbehery <melbeher@redhat.com> Co-authored-by: Matthew Farrellee <matt@cs.wisc.edu> fix: fix ```openai_embeddings``` for asymmetric embedding NIMs (#3205) NVIDIA asymmetric embedding models (e.g., `nvidia/llama-3.2-nv-embedqa-1b-v2`) require an `input_type` parameter not present in the standard OpenAI embeddings API. This PR adds the `input_type="query"` as default and updates the documentation to suggest using the `embedding` API for passage embeddings. <!-- If resolving an issue, uncomment and update the line below --> Resolves #2892 ``` pytest -s -v tests/integration/inference/test_openai_embeddings.py --stack-config="inference=nvidia" --embedding-model="nvidia/llama-3.2-nv-embedqa-1b-v2" --env NVIDIA_API_KEY={nvidia_api_key} --env NVIDIA_BASE_URL="https://integrate.api.nvidia.com" ``` cleaning up Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> updating session manager to cache messages locally Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> fix linter Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> more cleanup Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
111 lines
4.1 KiB
Python
111 lines
4.1 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.
|
|
|
|
import json
|
|
from typing import Any
|
|
|
|
from llama_stack.apis.inference import Message
|
|
from llama_stack.apis.safety import (
|
|
RunShieldResponse,
|
|
Safety,
|
|
SafetyViolation,
|
|
ViolationLevel,
|
|
)
|
|
from llama_stack.apis.shields import Shield
|
|
from llama_stack.log import get_logger
|
|
from llama_stack.providers.datatypes import ShieldsProtocolPrivate
|
|
from llama_stack.providers.utils.bedrock.client import create_bedrock_client
|
|
|
|
from .config import BedrockSafetyConfig
|
|
|
|
logger = get_logger(name=__name__, category="safety")
|
|
|
|
|
|
class BedrockSafetyAdapter(Safety, ShieldsProtocolPrivate):
|
|
def __init__(self, config: BedrockSafetyConfig) -> None:
|
|
self.config = config
|
|
self.registered_shields = []
|
|
|
|
async def initialize(self) -> None:
|
|
try:
|
|
self.bedrock_runtime_client = create_bedrock_client(self.config)
|
|
self.bedrock_client = create_bedrock_client(self.config, "bedrock")
|
|
except Exception as e:
|
|
raise RuntimeError("Error initializing BedrockSafetyAdapter") from e
|
|
|
|
async def shutdown(self) -> None:
|
|
pass
|
|
|
|
async def register_shield(self, shield: Shield) -> None:
|
|
response = self.bedrock_client.list_guardrails(
|
|
guardrailIdentifier=shield.provider_resource_id,
|
|
)
|
|
if (
|
|
not response["guardrails"]
|
|
or len(response["guardrails"]) == 0
|
|
or response["guardrails"][0]["version"] != shield.params["guardrailVersion"]
|
|
):
|
|
raise ValueError(
|
|
f"Shield {shield.provider_resource_id} with version {shield.params['guardrailVersion']} not found in Bedrock"
|
|
)
|
|
|
|
async def unregister_shield(self, identifier: str) -> None:
|
|
pass
|
|
|
|
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")
|
|
|
|
"""
|
|
This is the implementation for the bedrock guardrails. The input to the guardrails is to be of this format
|
|
```content = [
|
|
{
|
|
"text": {
|
|
"text": "Is the AB503 Product a better investment than the S&P 500?"
|
|
}
|
|
}
|
|
]```
|
|
Incoming messages contain content, role . For now we will extract the content and
|
|
default the "qualifiers": ["query"]
|
|
"""
|
|
|
|
shield_params = shield.params
|
|
logger.debug(f"run_shield::{shield_params}::messages={messages}")
|
|
|
|
# - convert the messages into format Bedrock expects
|
|
content_messages = []
|
|
for message in messages:
|
|
content_messages.append({"text": {"text": message.content}})
|
|
logger.debug(f"run_shield::final:messages::{json.dumps(content_messages, indent=2)}:")
|
|
|
|
response = self.bedrock_runtime_client.apply_guardrail(
|
|
guardrailIdentifier=shield.provider_resource_id,
|
|
guardrailVersion=shield_params["guardrailVersion"],
|
|
source="OUTPUT", # or 'INPUT' depending on your use case
|
|
content=content_messages,
|
|
)
|
|
if response["action"] == "GUARDRAIL_INTERVENED":
|
|
user_message = ""
|
|
metadata = {}
|
|
for output in response["outputs"]:
|
|
# guardrails returns a list - however for this implementation we will leverage the last values
|
|
user_message = output["text"]
|
|
for assessment in response["assessments"]:
|
|
# guardrails returns a list - however for this implementation we will leverage the last values
|
|
metadata = dict(assessment)
|
|
|
|
return RunShieldResponse(
|
|
violation=SafetyViolation(
|
|
user_message=user_message,
|
|
violation_level=ViolationLevel.ERROR,
|
|
metadata=metadata,
|
|
)
|
|
)
|
|
|
|
return RunShieldResponse()
|