The Hook (The Problem) I’ve always been interested in the relationship between code and “The Code” – the legal systems that govern our world. In Singapore, the laws are specific, but for the layman or legal researcher, wading through thick legislation and past changes can be like looking for a needle in a digital haystack.
I chose to create a custom RAG (Retrieval-Augmented Generation) engine to address this problem. But I soon realized that when working with legal data, hallucinations are not just frustrating – they can be costly.
The Technical Challenge (Solving RAG Hallucinations in LegalTech) Traditional RAG architectures are brittle. What if your main model goes down or your context window gets congested? The system breaks. I wanted to create something** that was “Apple-level” in its polish but “Industrial-grade” in its robustness.**
This prompted me to create a Triple-AI Failover Backend.
Gemini I have this my primary AI in my webpage.
Llama 3 If Gemini hits the rate limit the webpage AI seamlessly switches to Llama 3.
Groq If both of those two fail it switches to Groq.
As the engine uses FAISS for semantic embeddings, it not only searches for keywords but also comprehends the meaning of Singaporean legislative language.
The “Aha!” Moment The moment of truth wasn’t only in the search results but also in the UI. I shifted away from the “chatbox” style and opted for a high-precision, interactive UI that resembles more of a research tool than a playground.
Check Out the Project I have decided to open-source the engine. Whether you are interested in LegalTech, analyzing RAG architectures, or simply want to see how a multi-model failover is implemented in Python, I would be delighted if you took a look.
]
Live Experience: [https://adityaprasad-sudo.github.io/Explore-Singapore/]
Deep Dive into the Code: [https://github.com/adityaprasad-sudo/Explore-Singapore]
The Future This is only the beginning. As Singapore’s policies change, so will the engine. I am currently researching [How to build a accurate text embedding model] to further increase the autonomy of the research.
Top comments (0)