The biggest achievement of my life so far
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…
What it does
In the maker’s words, at launch
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 provides legal information faster and reliable(due to RAG) without going through long PDFs of goverment websites and helps travellers get insights faster about Singapore. Target Audience:- Python developers who keep hearing about "RAG" and AI agents but haven't build one yet or building one and are stuck somewhere also Singaporean people(obviously!) Comparison:- RAW LLM vs RAG based LLM to test the rag implementation i compared output of my logic code against the standard(gemini/Arcee AI/groq) and custom system instructions with rag(gemini/Arcee AI/groq) results were shocking query:- "can I fly in a drone in public park" standard llm response :- ""gave generic advice about "checking local laws" and safety guidelines"" Customized llm with RAG :- ""cited the air navigation act,specified the 5km no fly zones,and linked to the CAAS permit page"" the difference was clear and it was sure that the ai was not hallucinating. Ingestion:- I have the RAG Architecture about 594 PDFs about Singaporian laws and acts which rougly contains 33000 pages. How did I do it :- I used google Collab to build vector database and metadata which nearly took me 1 hour to do so ie convert PDFs to vectors. How accurate is it:- It's still in development phase but still it provides near accurate information as it contains multi query retrieval ie if a user asks ("ease of doing business in Singapore") the logic would break the keywords "ease", "business", "Singapore" and provide the required documents from the PDFs with the page number also it's a little hard to explain but you can check it on my webpage.Its not perfect but hey i am still learning. The Tech Stack: Ingestion: Python scripts using PyPDF2 to parse various PDF formats. Embeddings: Hugging Face BGE-M3(1024 dimensions) Vector Database: FAISS for similarity search. Orchestration: LangChain. Backend: Flask Frontend: React and Framer. The RAG Pipeline operates through the following process: Chunking: The source text is divided into chunks of 150 with an overlap of 50 tokens to maintain context across boundaries. Retrieval: When a user asks a question (e.g., "What is the policy on HDB grants?"), the system queries the vector database for the top k chunks (k=1). Synthesis: The system adds these chunks to the prompt of LLMs which produces the final response that includes citation information. Why did I say llms :- because I wanted the system to be as non crashable as possible so I am using gemini as my primary llm to provide responses but if it fails to do so due to api requests or any other reasons the backup model(Arcee AI trinity large) can handle the requests. Don't worry :- I have implemented different system instructions for different models so that result is a good quality product. Current Challenges: I am working on optimizing the the ranking strategy of the RAG architecture. I would value insights from anyone who has encountered RAG returning unrelevant documents. Feedbacks are the backbone of improving a platform so they are most Repository:- https://github.com/adityaprasad-sudo/Explore-Singapore
Does the same job
all alternatives →- IBI built a RAG engine to search Singaporean lawsFeb 2026 · github.com · ▲5
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…
- ILI learned to code to launch my new startup2013 · uncover.com · ▲178
Please check it out. I spent all of 2012 learning to code to launch what would eventually become Uncover. I'm super excited to announce that we're finally live. Here's a blog post I wrote on how we got there and a little story behind the startup: http://spencerfry.com/introducing-uncover
- 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.
- ISI started a repo for sharing algorithm implementations2013 · github.com · ▲52
Everything that would be here is in the README. I hope this gets big, it has tons of potential.
- ILI launched my first solo side project2011 · ▲14
Sysadmin is my bread and butter, but I taught myself PHP and have been coding on and off for the past 6 years. I've worked on numerous freelance gigs, but mainly internal apps that I use for my real job. I worked on this project (on and off) for the past year and I'm happy to finally release it to the public. Even if it doesn't succeed, I'm happy that I was able to "scratch an itch" I've had for the past couple of years. I wanted to make something and prove to myself that I can program. I'm not the greatest, but I'm proud of what I've achieved. http://www.ikeepm.com
- SLsoft-launching one of my pet projects2011 · ▲27
So a while ago I was thinking it would be neat to build a site that had the most absolute utility. The idea I came up with was a site to store those little protips that are super useful, if you know them ahead of time. I hired a guy to work on it with me, and ClueDB was born: http://cluedb.com/ Please give it a whirl (it uses Twitter auth as login but doesn't tweet anything) and tell me what you think! (Various trivia: My first try at a project coded by someone else and "product managed" by me. Runs on Flask + MongoDB. Also, this is totally unrelated to my startup.)
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
