phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

Resource oriented design for shields (#399)

Browse source 
* init

* working bedrock tests

* bedrock test for inference fixes

* use env vars for bedrock guardrail vars

* add register in meta reference

* use correct shield impl in meta ref

* dont add together fixture

* right naming

* minor updates

* improved registration flow

* address feedback

---------

Co-authored-by: Dinesh Yeduguru <dineshyv@fb.com>
This commit is contained in:
Dinesh Yeduguru 2024-11-08 12:16:11 -08:00 • committed by GitHub
parent 7ee9f8d8ac
commit d800a16acd
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
20 changed files with 262 additions and 124 deletions
Download patch file Download diff file Expand all files Collapse all files

7
llama_stack/apis/safety/safety.py
View file

@ -39,7 +39,7 @@ class RunShieldResponse(BaseModel):
class ShieldStore(Protocol):
async def get_shield(self, identifier: str) -> ShieldDef: ...
async def get_shield(self, identifier: str) -> Shield: ...
@runtime_checkable
@ -48,5 +48,8 @@ class Safety(Protocol):
@webmethod(route="/safety/run_shield")
async def run_shield(
self, identifier: str, messages: List[Message], params: Dict[str, Any] = None
self,
shield_id: str,
messages: List[Message],
params: Dict[str, Any] = None,
) -> RunShieldResponse: ...