phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-15 14:08:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

update documentation with required categories

Browse source
This commit is contained in:
Swapna Lekkala 2025-08-05 21:56:56 -07:00
parent 3f25eb4fb1
commit 817cbc8a42
3 changed files with 19 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
docs/_static/llama-stack-spec.html vendored
View file

@ -16530,7 +16530,7 @@
"additionalProperties": {
"type": "number"
},
"description": "A list of the categories along with their scores as predicted by model."
"description": "A list of the categories along with their scores as predicted by model. Required set of categories that need to be in response - violence - violence/graphic - harassment - harassment/threatening - hate - hate/threatening - illicit - illicit/violent - sexual - sexual/minors - self-harm - self-harm/intent - self-harm/instructions"
},
"user_message": {
"type": "string"

4
docs/_static/llama-stack-spec.yaml vendored
View file

@ -12286,6 +12286,10 @@ components:
type: number
description: >-
A list of the categories along with their scores as predicted by model.
Required set of categories that need to be in response - violence - violence/graphic
- harassment - harassment/threatening - hate - hate/threatening - illicit
- illicit/violent - sexual - sexual/minors - self-harm - self-harm/intent
- self-harm/instructions
user_message:
type: string
metadata:

14
llama_stack/apis/safety/safety.py
View file

@ -22,6 +22,20 @@ class ModerationObjectResults(BaseModel):
:param categories: A list of the categories, and whether they are flagged or not.
:param category_applied_input_types: A list of the categories along with the input type(s) that the score applies to.
:param category_scores: A list of the categories along with their scores as predicted by model.
Required set of categories that need to be in response
- violence
- violence/graphic
- harassment
- harassment/threatening
- hate
- hate/threatening
- illicit
- illicit/violent
- sexual
- sexual/minors
- self-harm
- self-harm/intent
- self-harm/instructions
"""
flagged: bool