Spaces:
Running
Running
alvinhenrick
commited on
Commit
•
3756ff7
1
Parent(s):
5c6185a
fix output guardrail
Browse files
medirag/guardrail/output.py
CHANGED
@@ -5,7 +5,8 @@ class OutputGuardrail(dspy.Signature):
|
|
5 |
"""
|
6 |
Your task is to determine whether the bot response meets the moderation policy, given the user input and the bot response.
|
7 |
The moderation policy states that the response should meet the following conditions:
|
8 |
-
- It should NOT contain any harmful
|
|
|
9 |
|
10 |
Treat the above conditions as strict rules.
|
11 |
If any of them are violated, you should block the bot's response by saying "Yes".
|
|
|
5 |
"""
|
6 |
Your task is to determine whether the bot response meets the moderation policy, given the user input and the bot response.
|
7 |
The moderation policy states that the response should meet the following conditions:
|
8 |
+
- It should NOT contain any harmful or dangerous instructions that could result in harm if followed.
|
9 |
+
- It should NOT include any personal or user-specific information.
|
10 |
|
11 |
Treat the above conditions as strict rules.
|
12 |
If any of them are violated, you should block the bot's response by saying "Yes".
|