I built a RAG engine to search Singaporean laws
I built a "Triple Failover" RAG for Singapore Laws, then rewrote the logic based on your feedback. 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. I recently posted the MVP and received some tough but essential feedback about hallucinations and query depth. I took that feedback, focused on improvements, and just released Version 2. Here is how I upgraded the system from a basic RAG to a production-grade one. The Design & UI I aimed to avoid a dull government…
What it does
In the maker’s words, at launch
I built a "Triple Failover" RAG for Singapore Laws, then rewrote the logic based on your feedback. 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. I recently posted the MVP and received some tough but essential feedback about hallucinations and query depth. I took that feedback, focused on improvements, and just released Version 2. Here is how I upgraded the system from a basic RAG to a production-grade one. 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. The Solution: I added Dynamic System Instructions. Now, if 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. The Solution: I implemented Multi-Query Retrieval (MQR). An LLM now intercepts your query. It breaks it down into sub-intents (e.g., “Business Registration,” “Corporate Tax,” “Employment Rules”). It searches for all of them at the same time 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. The Solution: I added a Cross-Encoder Re-Ranking layer. Step 1: FAISS grabs the top 10 results. Step 2: A specialized Cross-Encoder model evaluates them for relevance. Step 3: 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 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: https://adityaprasad-sudo.github.io/Explore-Singapore/ GitHub Repo: https://github.com/adityaprasad-sudo/Explore-Singapore Feedback, especially on the failover speed, is welcome!
Does the same job
all alternatives →- TBThe biggest achievement of my life so farFeb 2026 · github.com · ▲9
Hello everyone, I have always loved coding and in the couple I was thinking of making an open source project and it turned out to be awesome I hope you guys like it. I present Explore Singapore which I created as an open-source intelligence engine to execute retrieval-augmented generation (RAG) on Singapore's public policy documents and legal statutes and historical archives. The objective required building a domain-specific search engine which enables LLM systems to decrease errors by using government documents as their exclusive information source. What my Project does :- basically it…
- MWmy weekend project, understanding the Silk Road anonymous marketplace2011 · burntbrunch.github.com · ▲40
This was more of a sandbox to play with Raphael and Flot than anything else but I think there are some interesting statistics in there. It'd be awesome to do this over time but I really don't have the spare time required.
- IBI built a 2B-page search engine, independent of Google/Bing2025 · ▲8
Hi HN, For the last 18 months, I've been working solo on building a completely independent search engine from scratch. Today, I'm opening it up for beta testing and would love to get your feedback. The project powers two public sites from the same 2-billion-page index: Searcha.Page: A session-aware search engine that uses a persistent browser key (not a cookie) for better context. Seek.Ninja: A 100% stateless, privacy-first version with no identifiers at all. The entire stack is self-hosted on a single ~$4k bare-metal EPYC server in my laundry room (no cloud, no VC funding). The search…
- MSMy side project that searches the web for technologies2011 · ▲22
Hello HN! I've been working on http://underthesite.com for the last month and now think it is ready for some full strength HN feedback. What do you guys think? It crawls up to 10 pages of a given site while you wait, looking for community-provided CSS / XPath selectors and regular expressions. Additionally, I'd like to appeal to you to submit matchers for technologies that you care about. Technologies are easy to add, so add your favorite jQuery plugins, analytics tools, client-side node.js wrappers, what have you. I'm going to be running a large crawl in the next few days and want to make…
- AEAn extensive set of RAG implementations+many different strategies2024 · github.com · ▲6
Hi all, Sharing a repo I was working on for a while. It’s open-source and includes many different strategies for RAG (currently 17), including tutorials, and visualizations. This is great learning and reference material. Open issues, suggest more strategies, and use as needed. Enjoy!
- HBHigh Browse independent “surf engine”2022 · highbrow.se · ▲7
Hi HN, I’m pleased to release my “surf engine” to the public for you to try. This is might be for you if you’ve grown frustrated with commercialised SERPs, and want to find the other websites are (still) out there. Kudos to Marginalia Search for showing that it’s possible to build a search engine as a hobbyist: https://search.marginalia.nu/ Feedback of all kinds very welcome! Ali
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
