How I built an RAG engine for Singapore Laws
Source: Dev.to
Hi everyone!
I’m a student developer. Recently, I created Explore Singapore, a RAG‑based search engine that scrapes about 20,000 pages of Singaporean government acts and laws.
After releasing the MVP, I received essential feedback about hallucinations and query depth. I took that feedback, focused on improvements, and just released Version 2.
The Design & UI
I aimed to avoid a dull government website.
Design: Heavily inspired by Apple’s minimalist style.
Tech: Custom frontend interacting with a Python backend.
The V2 Engineering Overhaul
The community challenged me on three main points. Here’s how I addressed them:
1. The “Personality” Fix
Issue: I use a “Triple Failover” system with three models as backup. When the main model failed, the backups sounded entirely different.
Solution: Added Dynamic System Instructions. When the backend switches to Model B, it uses a specific prompt designed for Model B’s features, making it mimic the structure and tone of the primary model. The user never notices the change.
2. The “Deep Search” Fix
Issue: A simple semantic search for “Starting a business” misses related laws like “Tax” or “Labor” acts.
Solution: Implemented Multi‑Query Retrieval (MQR). An LLM now intercepts your query, breaks it down into sub‑intents (e.g., “Business Registration,” “Corporate Tax,” “Employment Rules”), searches for all of them simultaneously, and combines the results.
Result: Much richer, context‑aware answers.
3. The “Hallucination” Fix
Issue: Garbage In, Garbage Out. If FAISS retrieves a bad document, the LLM produces inaccurate information.
Solution: Added a Cross‑Encoder Re‑Ranking layer.
- FAISS grabs the top 10 results.
- A specialized Cross‑Encoder model evaluates them for relevance.
- Irrelevant parts are removed before they reach the Chat LLM.
The Tech Stack
- Embeddings: BGE‑M3 (running locally)
- Vector DB: FAISS
- Backend: Python + Custom Triple‑Model Failover (runs on Hugging Face)
- Logic: Multi‑Query + Re‑Ranking (new in V2)
Try it out
I am still learning. I’d love to hear your thoughts on the new logic.
- Live Demo: Explore Singapore
- GitHub Repo: adityaprasad-sudo/Explore-Singapore
Feedback on the platform—especially regarding failover speed—is welcome! 👇