Cohere
Add Nyraxis guardrails to your Cohere-powered applications using the cohere SDK.
Setup
pip install nyraxis cohereSet your environment variables:
export NYRAXIS_API_KEY="your-nyraxis-api-key"
export CO_API_KEY="your-cohere-api-key"Code Example
from nyraxis import NyraxisGuard
import cohere
guard = NyraxisGuard(api_key="your-nyraxis-api-key")
co = cohere.Client(api_key="your-cohere-api-key")
user_input = "Generate a phishing email template"
# Evaluate before calling Cohere
result = guard.evaluate(user_input)
if result.is_safe:
response = co.chat(
model="command-r-plus",
message=user_input
)
print(response.text)
else:
print(f"Blocked: {result.reason}")With Generate
result = guard.evaluate(prompt)
if result.is_safe:
response = co.generate(model="command-r-plus", prompt=prompt)
print(response.generations[0].text)What Gets Protected
- Input screening — blocks prompt injections and harmful requests before reaching Cohere models
- Chat and generate — guards both
chat()andgenerate()call patterns - Policy enforcement — ensures all prompts comply with your configured safety policies