Show HN: RAG Engine – Connect external data to LLM in minutes
If you’ve ever tried building an AI app that needs your own data, you know the pain — spinning up a vector database, writing scripts to fetch data from different sources, keeping data in sync… It’s a lot.
So we thought, why not simplify this process and make it as simple as couple API calls? One to add data source and another to search across all your data.
Well, that’s why we’re building RAG Engine - https://rageninge.io
To add data source to RAG Engine you make one API call, including your project API key and namespace (useful to keep data between your users separate)
curl -X POST https://ragengine.io/data-sources \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_PROJECT_API_KEY" \
-d '{
"namespace": "user:1",
"type": "website",
"url": "https://mywebsite.com"
}'
curl -X GET "https://ragengine.io/search?query=...&namespace=user:1" \
-H "Authorization: Bearer YOUR_PROJECT_API_KEY"
Response: {
"documents": [
{
"source": { "type": "website", "url": "https://mywebsite.com" },
"content": "...",
"similarity_score": 3.99
},
{
"source": { "type": "file", "filename": "pricing.txt" },
"content": "...",
"similarity_score": 3.11
}
]
That’s it! In background RAG Engine ingests, processes, stores and keeps all your data in sync.
We’re focusing on small startups and indie developers who don’t have time or resources to build RAG, that’s why we make pricing as low as possible:
1. Vector Database: Starting at $4/month for a DigitalOcean droplet (512 MB RAM, 10 GB SSD). Larger datasets require more resources, but it’s always at-cost with no markup. 2. Embeddings: We pass along the exact OpenAI rates ($0.010 to $0.065 per 1M tokens), so no extra fees here either. 3. Our fee: $4.99/month (first month free). This covers our ingestion pipeline and unified search.
If you want to give RAG Engine a try - join waitlist https://ragengine.io/
Or check our discord server (we are there right now and happy to chat) https://discord.gg/Kz6JyTXjHm