GitHub Repository

A sophisticated RAG intelligence engine for Singaporean laws, policies, and history. Comes with a triple-AI failover backend (Gemini/Llama/Groq), semantic embeddings using FAISS, and an Apple-inspired interactive UI. Designed with precision and high availability in mind.

73 starsPython

After a lot of backlash I fixed and built it

Name: After a lot of backlash I fixed and built it
Availability: InStock
Author: dagestan

by dagestan·Mar 15, 2026·1 point·0 comments

Visit Project View on HN

AI Analysis

●●SolidNiche GemShip It

RAG engine for Singapore law with triple-AI failover and local embeddings.

Strengths

•33k pages of curated local legal data reduces hallucination significantly.
•Triple-AI failover chain ensures uptime during demo traffic spikes.
•Local embedding inference cuts latency and API costs for vectorization.

Weaknesses

•Niche audience limits broader adoption beyond Singapore residents or legal pros.
•Standard RAG stack offers no novel retrieval technique beyond FAISS.

Post Description

I just built a Singaporean legaltech with RAG and apple like webpage both for mobile and desktop. And also here is the webpage url https://exploresingapore.vercel.app/

Similar Projects

AI/ML●Mid

Built an webpage to show Singaporean infra and laws

Triple-LLM failover (Gemini → Llama 3.3 via OpenRouter → Groq), local BGE‑M3 embeddings and FAISS-backed retrieval show someone thought about latency and uptime, not just model demos. The README brags about 33k pages and 'non-hallucination' claims but stops short of evaluation details or realistic ops guidance — running 70B models and local embedding stacks is impressive on paper but a heavy lift in practice.

Niche GemWizardry

Goodguy27

324mo ago

AI/ML●●Solid

An beautiful webpage I made

There are real engineering moves here: 33k+ pages ingested, 1024-dim BGE-M3 embeddings served locally for privacy/latency, FAISS for millisecond retrieval and a clever 'triple‑AI' failover chain (Gemini → Llama via OpenRouter → Groq) to keep demos responsive. The frontend leans into Apple-style glassmorphism with Framer Motion interactions, so it actually feels like a thought-through product rather than a hack — biggest caveat is reliance on proprietary LLMs and infrastructure complexity for anyone wanting to reproduce it.

Niche GemWizardry

gigachadai

204mo ago

AI/ML●●●Banger