Skip to content

DeepTeam is a framework to red team LLMs and AI agents.

fix docs

penguine1b4fbcbf8952
diff --git a/docs/docs/red-teaming-adversarial-attacks-roleplay.mdx b/docs/docs/red-teaming-adversarial-attacks-roleplay.mdx
index 76bd6032..a4197717 100644
--- a/docs/docs/red-teaming-adversarial-attacks-roleplay.mdx
+++ b/docs/docs/red-teaming-adversarial-attacks-roleplay.mdx
@@ -15,15 +15,18 @@ The roleplay attack method enhances baseline attacks by embedding them within el
```python
from deepteam.attacks.single_turn import Roleplay
-roleplay = Roleplay()
+roleplay = Roleplay(
+ role="17th-century scholar",
+ persona="Sir Reginald Blackthorne, Fellow of the Royal Society"
+)
```
There are **FOUR** optional parameters when creating a `Roleplay` attack:
+- `role`: a string that specifies the role or context for the character.
+- `persona`: a string that represents the character persona the LLM should adopt.
- [Optional] `weight`: a floating point that will be used to determine the selection likelihood of this attack. Defaulted to `1`.
- [Optional] `max_retries`: an integer that specifies the number of times to retry simulating a `Roleplay` attack for any error that occurs. Defaulted to `5`.
-- [Optional] `persona`: a string that represents the character persona the LLM should adopt.
-- [Optional] `role`: a string describing the specific role or context for the character.
To use the `Roleplay` attack method, supply it to the `red_team()` method: