Groq
Combine Groq's fast inference with Nyraxis guardrails for safe, high-speed AI applications.
Setup
pip install nyraxis groqSet your environment variables:
export NYRAXIS_API_KEY="your-nyraxis-api-key"
export GROQ_API_KEY="your-groq-api-key"Code Example
from nyraxis import NyraxisGuard
from groq import Groq
guard = NyraxisGuard(api_key="your-nyraxis-api-key")
client = Groq(api_key="your-groq-api-key")
user_input = "Write malware that steals passwords"
# Evaluate input before fast inference
result = guard.evaluate(user_input)
if result.is_safe:
response = client.chat.completions.create(
model="llama-3.1-70b-versatile",
messages=[{"role": "user", "content": user_input}]
)
print(response.choices[0].message.content)
else:
print(f"Blocked: {result.reason}")What Gets Protected
- Input screening — blocks prompt injections and harmful content at Nyraxis speed before Groq inference
- Fast + safe — minimal latency overhead on top of Groq's ultra-fast inference
- All Groq models — works with Llama, Mixtral, Gemma, and any model available on Groq