ScanDrixScanDrix
How to useHow to deployKnowledge BaseCookbookChangelog

Novita AI Integration

Learn how to connect Novita AI's serverless GPU infrastructure to ScanDrix for cost-efficient AI code reviews.

Novita AI provides serverless GPU infrastructure for open-source AI models, offering low latency, aggressive pricing, and an OpenAI-compatible API interface. Novita supports popular open-weights models like DeepSeek V3/R1 and Llama 3.3 without requiring infrastructure provisioning.

We recommend high-context coding and reasoning models with reliable token throughput:

ModelContext WindowSpeedBest For
deepseek/deepseek_v3 recommended128k tokens110+ tpsStandard PR diff reviews, security audits & taint tracing
deepseek/deepseek-r1128k tokens75+ tpsDeep logic verification, concurrency safety & crypto checks
meta-llama/llama-3.3-70b-instruct128k tokens135+ tpsFast syntax checks, style conventions & test suggestions

For the most up-to-date model identifiers and context limits, consult the Novita AI LLM Catalog.

Creating an API Key

A verified Novita AI account is required to generate API credentials.

  1. Navigate to the Novita AI Console.
  2. Sign in or create an account.
  3. Go to Settings → Key Management.
  4. Click Add New Key, name it scandrix-code-review, and copy the secret key.

Configuration options

You can configure Novita AI either via the ScanDrix dashboard, in your repository's .scandrix.yaml, or in self-hosted backend environment variables.

  1. Open the ScanDrix dashboard and navigate to Settings → AI Providers.
  2. Click Add Provider and select Novita AI (or Generic OpenAI-Compatible).
  3. Set Base URL to https://api.novita.ai/v3/openai.
  4. Paste your Novita API Key.
  5. Select deepseek/deepseek_v3 as your default review model.
  6. Click Test Connection to send a synthetic health verification ping.

Option 2: Via Repository Config (.scandrix.yaml)

To enforce Novita AI as the review engine for a specific repository:

yaml
# .scandrix.yaml
version: 1

ai:
  provider: novita
  endpoint: "https://api.novita.ai/v3/openai"
  model: "deepseek/deepseek_v3"
  api_key: "env:NOVITA_API_KEY"
  temperature: 0.1
  max_tokens: 4096

review:
  severity_threshold: warning
  patch_suggestions: true

Option 3: Via Self-Hosted Backend (.env)

If deploying the self-hosted ScanDrix Go backend, configure your environment file:

env
# ScanDrix Core Service Configuration
PORT=8080
SCANDRIX_API_URL=https://api.scandrix.yourdomain.com
SCANDRIX_WEB_URL=https://scandrix.yourdomain.com

# Database Connection (PostgreSQL 16+)
DATABASE_URL=postgres://scandrix:yourpassword@postgres:5432/scandrix?sslmode=require

# Novita AI LLM Configuration
SCANDRIX_LLM_PROVIDER=novita
OPENAI_BASE_URL=https://api.novita.ai/v3/openai
OPENAI_API_KEY=your_novita_api_key_here
SCANDRIX_DEFAULT_MODEL=deepseek/deepseek_v3

# Webhook Secret for HMAC verification
GITHUB_WEBHOOK_SECRET=your_github_webhook_secret

Production Reverse Proxy Setup

For self-hosted instances with external Git webhooks, configure Nginx to forward requests to the Next.js frontend (port 3000) and the Go backend API (port 8080):

nginx
# ScanDrix Web Dashboard (port 3000)
server {
    listen 443 ssl http2;
    server_name scandrix.yourdomain.com;

    ssl_certificate /etc/letsencrypt/live/scandrix.yourdomain.com/fullchain.pem;
    ssl_certificate_key /etc/letsencrypt/live/scandrix.yourdomain.com/privkey.pem;

    location / {
        proxy_pass http://127.0.0.1:3000;
        proxy_set_header Host $host;
        proxy_set_header X-Real-IP $remote_addr;
        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
        proxy_set_header X-Forwarded-Proto $scheme;
    }
}

# ScanDrix Go API & Webhooks (port 8080)
server {
    listen 443 ssl http2;
    server_name api.scandrix.yourdomain.com;

    ssl_certificate /etc/letsencrypt/live/api.scandrix.yourdomain.com/fullchain.pem;
    ssl_certificate_key /etc/letsencrypt/live/api.scandrix.yourdomain.com/privkey.pem;

    location / {
        proxy_pass http://127.0.0.1:8080;
        proxy_set_header Host $host;
        proxy_set_header X-Real-IP $remote_addr;
        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
        proxy_set_header X-Forwarded-Proto $scheme;
    }
}

Verifying Novita AI integration

Verify that Novita AI is processing review tasks:

bash
# Test local review via CLI
scandrix review --staged

# Or inspect worker container logs
docker logs scandrix-worker | grep -i "novita"

Expected log output:

code
[INFO] provider=novita model=deepseek/deepseek_v3 latency=1050ms tokens=1980 status=200

Troubleshooting

PreviousTogether AI IntegrationNextChangelog