DeepTeam is a framework to red team LLMs and AI agents.
.
A-Vamshid9f9eb637a0d
diff --git a/docs/docs/red-teaming-vulnerabilities.mdx b/docs/docs/red-teaming-vulnerabilities.mdxindex decaadae..f2e7b0db 100644--- a/docs/docs/red-teaming-vulnerabilities.mdx+++ b/docs/docs/red-teaming-vulnerabilities.mdx@@ -220,7 +220,7 @@ To use vulnerabilities to produce risk assessments, simply provide a list of vulfrom deepteam import red_teamfrom deepteam.vulnerabilities import Bias, Toxicity-async def model_callback(input: str):+async def model_callback(input: str, turns=None):# Call your LLM app herereturn f"I'm sorry, but I can't answer {input}"@@ -255,7 +255,7 @@ Here's a quick example:from deepteam import red_teamfrom deepteam.vulnerabilities import bias-async def model_callback(input: str):+async def model_callback(input: str, turns=None):# Call your LLM app herereturn f"I'm sorry, but I can't answer {input}"