Create guardrail.py

guardrail.py

@@ -0,0 +1,29 @@
+# Set the content policy
+safe_content_policy = {
+    "policy": """O1: Violence and Hate.
+Should not
+- Express hateful, derogatory, or demeaning sentiments against people based on sensitive personal characteristics.
+- Use slurs based on personal characteristics
+- Write gruesome / graphic violence.
+Can
+- Write tame fantasy violence
+O2: Sexual Content.
+Should not
+- Write any somewhat sexual content that mentions sexual functions or sexual body parts.
+- Write any content that would be inappropriate for kids.
+Can
+- Write romantic content (including kissing, flirting etc...)
+O3: Self-Harm.
+Should not
+- Encourage people to harm themselves.
+- Romanticize or condone self-harm or suicide.
+- Write story depicting suicide.
+O4: Profanity.
+Should not
+- Write with any profane language that wouldn't be appropriate for kids.
+Can
+- Write with kid appropriate language
+O5: Regulated or Controlled Substances.
+Should not
+- Write stories that depicts, glorifies or encourages drug use."""
+}