AI-powered news processing pipeline that converts URLs or topics into professional articles with SEO metadata.

• Multi-model AI pipeline: GPT-4.1 (extraction + SEO) → o3-mini (verification) → Claude Sonnet 4 (writing)
• Smart caching: Redis-based caching with 24-hour TTL
• Webhook support: Async processing with callback notifications
• Flexible input: Process URLs (via Firecrawl) or topics (via Brave Search)

1. Install dependencies:

pip3 install -r requirements.txt

2. Set environment variables:

cp .env.example .env
# Edit .env with your API keys

3. Run locally:

python3 main.py

4. Test the API: Visit http://localhost:8000/docs for interactive documentation.

POST /news-processor
{
  "url": "https://example.com/article"
}
# OR
{
  "topic": "AI developments 2025"
}

POST /news-processor/async
{
  "topic": "breaking news",
  "webhook_url": "https://your-app.com/callback"
}

POST /webhook/news-processor
{
  "url": "https://example.com/article"
}

1. Connect this GitHub repo to Render
2. Build Command: pip3 install -r requirements.txt
3. Start Command: python3 -m uvicorn main:app --host 0.0.0.0 --port $PORT
4. Add environment variables in Render dashboard
5. Deploy automatically on git push to main

Also supported - adjust build commands to use python3 and pip3.

{
  "success": true,
  "article": "Generated news article...",
  "seo": "SEO metadata...",
  "models_used": "GPT-4.1 (facts + SEO), o3-mini (verification), Claude Sonnet 4 (writing)",
  "processing_time": 12.34,
  "input_type": "URL",
  "cached": false,
  "extracted_facts": "Raw facts...",
  "verified_facts": "Verified facts..."
}

Input (URL/Topic) 
    ↓
Route & Extract Content (Firecrawl/Brave)
    ↓
Extract Facts (GPT-4.1)
    ↓
Verify & Organize (o3-mini)
    ↓
Write Article (Claude Sonnet 4)
    ↓
Generate SEO (GPT-4.1)
    ↓
Return/Webhook Result

MIT License