perfecXion.ai

Installation Guide

Install PromptShield SDKs and tools for your preferred platform and environment.

System Requirements

Python SDK

  • Python 3.7 or higher
  • pip 19.0+
  • 2GB RAM minimum
  • SSL/TLS support

Node.js SDK

  • Node.js 14.0 or higher
  • npm 6+ or yarn 1.22+
  • 2GB RAM minimum
  • TypeScript 4.0+ (optional)

Python SDK Installation

Using pip

pip install prompt-shield

Using Poetry

poetry add prompt-shield

Using Conda

conda install -c perfecxion prompt-shield

Optional Dependencies

For async support:

pip install "prompt-shield[async]"

For framework integrations:

pip install "prompt-shield[frameworks]"

For all features:

pip install "prompt-shield[all]"

Node.js SDK Installation

Using npm

npm install @prompt-shield/sdk

Using yarn

yarn add @prompt-shield/sdk

Using pnpm

pnpm add @prompt-shield/sdk

TypeScript Support

TypeScript definitions are included. No additional @types package needed.

// tsconfig.json
{
  "compilerOptions": {
    "types": ["@prompt-shield/sdk"]
  }
}

CLI Tool Installation

Global Installation

npm install -g @prompt-shield/cli

Verify Installation

promptshield --version
# Output: PromptShield CLI v1.0.0

promptshield --help
# Shows all available commands

promptshield test --help
# Shows testing options

Docker Installation

Pull the Docker Image

docker pull promptshield/promptshield:latest

Run with Docker Compose

# docker-compose.yml
version: '3.8'
services:
  promptshield:
    image: promptshield/promptshield:latest
    environment:
      - PROMPTSHIELD_API_KEY=your-api-key
      - PROMPTSHIELD_LOG_LEVEL=info
      - PROMPTSHIELD_PORT=8080
    ports:
      - "8080:8080"
      - "9090:9090"  # Metrics endpoint
    volumes:
      - ./config:/app/config
      - ./logs:/app/logs
    deploy:
      resources:
        limits:
          cpus: '2'
          memory: 2G
        reservations:
          cpus: '1'
          memory: 1G
          
  # Optional: Local Redis for caching
  redis:
    image: redis:7-alpine
    ports:
      - "6379:6379"
    volumes:
      - redis-data:/data

volumes:
  redis-data:

Kubernetes Deployment

Helm Chart Installation

# Add Helm repository
helm repo add promptshield https://charts.perfecxion.ai
helm repo update

# Install PromptShield
helm install promptshield promptshield/promptshield \
  --set apiKey=your-api-key \
  --set replicas=3 \
  --set resources.requests.memory=1Gi \
  --set resources.requests.cpu=500m \
  --namespace promptshield \
  --create-namespace

Custom Values Configuration

# values.yaml
replicaCount: 3

image:
  repository: promptshield/promptshield
  tag: "1.0.0"
  pullPolicy: IfNotPresent

service:
  type: LoadBalancer
  port: 80
  metricsPort: 9090

ingress:
  enabled: true
  className: nginx
  annotations:
    cert-manager.io/cluster-issuer: letsencrypt
  hosts:
    - host: promptshield.your-domain.com
      paths:
        - path: /
          pathType: Prefix

autoscaling:
  enabled: true
  minReplicas: 3
  maxReplicas: 10
  targetCPUUtilizationPercentage: 70
  targetMemoryUtilizationPercentage: 80

cache:
  enabled: true
  type: redis
  redis:
    host: redis-master
    port: 6379
    
monitoring:
  prometheus:
    enabled: true
    serviceMonitor:
      enabled: true

Environment Configuration

Environment Variables

# .env file
PROMPTSHIELD_API_KEY=your-api-key-here
PROMPTSHIELD_API_URL=https://api.perfecxion.ai/v1
PROMPTSHIELD_LOG_LEVEL=info
PROMPTSHIELD_CACHE_ENABLED=true
PROMPTSHIELD_CACHE_TTL=3600
PROMPTSHIELD_TIMEOUT_MS=5000
PROMPTSHIELD_MAX_RETRIES=3
PROMPTSHIELD_BATCH_SIZE=100

Configuration File

# promptshield.config.yaml
api:
  key: ${PROMPTSHIELD_API_KEY}
  endpoint: https://api.perfecxion.ai/v1
  timeout: 5s
  retries: 3

detection:
  default_mode: "standard"
  sensitivity: "balanced"
  
  layers:
    heuristic:
      enabled: true
      patterns_update: "auto"
      
    llm:
      enabled: true
      model: "gpt-3.5-turbo"
      fallback: "heuristic_only"
      
    canary:
      enabled: true
      token_rotation: "daily"

performance:
  cache:
    enabled: true
    ttl: 3600
    max_size: 1000
    
  batching:
    enabled: true
    max_batch_size: 100
    max_wait_ms: 100
    
monitoring:
  metrics:
    enabled: true
    port: 9090
    path: /metrics
    
  logging:
    level: info
    format: json
    output: stdout

Verify Your Installation

Python

import prompt_shield

# Check version
print(prompt_shield.__version__)

# Test connection
from prompt_shield import PromptShield

shield = PromptShield(api_key="your-api-key")
health = shield.health_check()
print(f"Connection status: {health.status}")
print(f"API version: {health.api_version}")
print(f"Detection layers: {', '.join(health.active_layers)}")

Node.js

const { PromptShield } = require('@prompt-shield/sdk');

// Check version
console.log(PromptShield.VERSION);

// Test connection
const shield = new PromptShield({ apiKey: 'your-api-key' });
const health = await shield.healthCheck();
console.log(`Connection status: ${health.status}`);
console.log(`API version: ${health.apiVersion}`);
console.log(`Detection layers: ${health.activeLayers.join(', ')}`);

CLI

# Test CLI connection
promptshield test-connection

# Run detection test
promptshield detect "Sample text to test"

# Validate configuration
promptshield config validate

Framework-Specific Installation

React

npm install @prompt-shield/react

# Usage
import { PromptShieldProvider } from '@prompt-shield/react';

<PromptShieldProvider apiKey={process.env.REACT_APP_PROMPTSHIELD_KEY}>
  <App />
</PromptShieldProvider>

Django

pip install prompt-shield[django]

# settings.py
INSTALLED_APPS = [
    # ...
    'prompt_shield.django',
]

PROMPTSHIELD_API_KEY = 'your-api-key'

FastAPI

pip install prompt-shield[fastapi]

# main.py
from prompt_shield.fastapi import PromptShieldMiddleware

app.add_middleware(
    PromptShieldMiddleware,
    api_key="your-api-key"
)

Common Installation Issues

SSL Certificate Errors

For corporate proxies: export NODE_TLS_REJECT_UNAUTHORIZED=0

Permission Denied

Use sudo for global installs or use a virtual environment

Network Timeouts

Configure proxy settings or increase timeout values in configuration

Version Conflicts

Check compatibility matrix in documentation for framework versions

Next Steps

Follow the Quick Start Guide →Explore the API Reference →View Integration Guides →