mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-27 01:25:32 +00:00
chore: support default model in moderations API (#3890)
Some checks failed
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 2s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Vector IO Integration Tests / test-matrix (push) Failing after 5s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 5s
Python Package Build Test / build (3.12) (push) Failing after 1s
Python Package Build Test / build (3.13) (push) Failing after 2s
Test Llama Stack Build / build-single-provider (push) Failing after 3s
Test Llama Stack Build / generate-matrix (push) Successful in 5s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 4s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 3s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 7s
Test External API and Providers / test-external (venv) (push) Failing after 4s
API Conformance Tests / check-schema-compatibility (push) Successful in 12s
Unit Tests / unit-tests (3.13) (push) Failing after 4s
Test Llama Stack Build / build (push) Failing after 3s
Unit Tests / unit-tests (3.12) (push) Failing after 5s
UI Tests / ui-tests (22) (push) Successful in 41s
Pre-commit / pre-commit (push) Successful in 1m33s
Some checks failed
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 2s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Vector IO Integration Tests / test-matrix (push) Failing after 5s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 5s
Python Package Build Test / build (3.12) (push) Failing after 1s
Python Package Build Test / build (3.13) (push) Failing after 2s
Test Llama Stack Build / build-single-provider (push) Failing after 3s
Test Llama Stack Build / generate-matrix (push) Successful in 5s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 4s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 3s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 7s
Test External API and Providers / test-external (venv) (push) Failing after 4s
API Conformance Tests / check-schema-compatibility (push) Successful in 12s
Unit Tests / unit-tests (3.13) (push) Failing after 4s
Test Llama Stack Build / build (push) Failing after 3s
Unit Tests / unit-tests (3.12) (push) Failing after 5s
UI Tests / ui-tests (22) (push) Successful in 41s
Pre-commit / pre-commit (push) Successful in 1m33s
# What does this PR do? https://platform.openai.com/docs/api-reference/moderations supports optional model parameter. This PR adds support for using moderations API with model=None if a default shield id is provided via safety config. ## Test Plan added tests manual test: ``` > SAFETY_MODEL='together/meta-llama/Llama-Guard-4-12B' uv run llama stack run starter > curl http://localhost:8321/v1/moderations \ -H "Content-Type: application/json" \ -d '{ "input": [ "hello" ] }' ```
This commit is contained in:
parent
d12e5f0999
commit
9916cb3b17
23 changed files with 189 additions and 36 deletions
|
|
@ -35,7 +35,7 @@ from llama_stack.apis.telemetry import Telemetry
|
|||
from llama_stack.apis.tools import RAGToolRuntime, ToolGroups, ToolRuntime
|
||||
from llama_stack.apis.vector_io import VectorIO
|
||||
from llama_stack.core.conversations.conversations import ConversationServiceConfig, ConversationServiceImpl
|
||||
from llama_stack.core.datatypes import Provider, StackRunConfig, VectorStoresConfig
|
||||
from llama_stack.core.datatypes import Provider, SafetyConfig, StackRunConfig, VectorStoresConfig
|
||||
from llama_stack.core.distribution import get_provider_registry
|
||||
from llama_stack.core.inspect import DistributionInspectConfig, DistributionInspectImpl
|
||||
from llama_stack.core.prompts.prompts import PromptServiceConfig, PromptServiceImpl
|
||||
|
|
@ -175,6 +175,30 @@ async def validate_vector_stores_config(vector_stores_config: VectorStoresConfig
|
|||
logger.debug(f"Validated default embedding model: {default_model_id} (dimension: {embedding_dimension})")
|
||||
|
||||
|
||||
async def validate_safety_config(safety_config: SafetyConfig | None, impls: dict[Api, Any]):
|
||||
if safety_config is None or safety_config.default_shield_id is None:
|
||||
return
|
||||
|
||||
if Api.shields not in impls:
|
||||
raise ValueError("Safety configuration requires the shields API to be enabled")
|
||||
|
||||
if Api.safety not in impls:
|
||||
raise ValueError("Safety configuration requires the safety API to be enabled")
|
||||
|
||||
shields_impl = impls[Api.shields]
|
||||
response = await shields_impl.list_shields()
|
||||
shields_by_id = {shield.identifier: shield for shield in response.data}
|
||||
|
||||
default_shield_id = safety_config.default_shield_id
|
||||
# don't validate if there are no shields registered
|
||||
if shields_by_id and default_shield_id not in shields_by_id:
|
||||
available = sorted(shields_by_id)
|
||||
raise ValueError(
|
||||
f"Configured default_shield_id '{default_shield_id}' not found among registered shields."
|
||||
f" Available shields: {available}"
|
||||
)
|
||||
|
||||
|
||||
class EnvVarError(Exception):
|
||||
def __init__(self, var_name: str, path: str = ""):
|
||||
self.var_name = var_name
|
||||
|
|
@ -412,6 +436,7 @@ class Stack:
|
|||
await register_resources(self.run_config, impls)
|
||||
await refresh_registry_once(impls)
|
||||
await validate_vector_stores_config(self.run_config.vector_stores, impls)
|
||||
await validate_safety_config(self.run_config.safety, impls)
|
||||
self.impls = impls
|
||||
|
||||
def create_registry_refresh_task(self):
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue