ci: test safety with starter

We are now testing the safety capability with the starter image. This
includes a few changes:

* Enable the safety integration test
* Relax the shield model requirements from llama-guard to make it work
  with llama-guard3:8b coming from Ollama
* Expose a shield for each inference provider in the starter distro. The
  shield will only be registered if the provider is enabled. Shields
  will be added if the provider claims to support a safety model
* Missing providers models have been added too
* Pointers to official documentation pages for provider models support
  have been added

Closes: https://github.com/meta-llama/llama-stack/issues/2528
Signed-off-by: Sébastien Han <seb@redhat.com>
This commit is contained in:
Sébastien Han 2025-07-04 17:07:11 +02:00
parent cd0ad21111
commit 11c912da0a
No known key found for this signature in database
20 changed files with 621 additions and 126 deletions

View file

@ -47,7 +47,10 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
from .config import DatabricksImplConfig
model_entries = [
SAFETY_MODELS_ENTRIES = []
# https://docs.databricks.com/aws/en/machine-learning/model-serving/foundation-model-overview
MODEL_ENTRIES = [
build_hf_repo_model_entry(
"databricks-meta-llama-3-1-70b-instruct",
CoreModelId.llama3_1_70b_instruct.value,
@ -56,7 +59,7 @@ model_entries = [
"databricks-meta-llama-3-1-405b-instruct",
CoreModelId.llama3_1_405b_instruct.value,
),
]
] + SAFETY_MODELS_ENTRIES
class DatabricksInferenceAdapter(
@ -66,7 +69,7 @@ class DatabricksInferenceAdapter(
OpenAICompletionToLlamaStackMixin,
):
def __init__(self, config: DatabricksImplConfig) -> None:
ModelRegistryHelper.__init__(self, model_entries=model_entries)
ModelRegistryHelper.__init__(self, model_entries=MODEL_ENTRIES)
self.config = config
async def initialize(self) -> None: