Data Infrastructure

Traditional data systems are often built around institutions, departments, or available databases. However, Lanka Data Net Citizen-Centric Data infrastructure do not think in terms of ministries, agencies, or disconnected records. They think in terms of needs, problems, rights, services, and opportunities.

The LDN Data infrastructure reimagines national data architecture by placing the citizen at the center of the ecosystem. Instead of starting with what data exists, this model begins with what people need to know, access, solve, or improve.

Open Public Information Network (OpenPIN) is the backend layer designed to harvest, collect, organize, and structure data from publicly available digital sources. It continuously indexes websites, records, publications, and open datasets, transforming fragmented information into a unified and searchable knowledge network. This is the core backend component within Lanka Data Net that powers the intelligent layer to deliver trusted, structured, and scalable intelligence for search, analytics, research, compliance, and decision-making.

OpenPIN

Open Public Information Network (OpenPIN) is the core backend framework of Lanka Data Net, designed to harvest, collect, and store Sri Lanka’s public data.

Lanka Data Net (LDN) brings together a powerful Sri Lanka-focused data corpus exceeding 10 billion data points, forming the foundation for accurate trilingual capabilities across Sinhala, Tamil, and English. This is complemented by high-quality conversational and structured datasets spanning key domains enabling precise, context-aware insights for real-world applications.

Data Corpus

The Chat2Find Corpus is a high-quality trilingual conversational dataset derived from real-world interactions on the Chat2Find platform. It contains approximately 255 Million tokens in Sinhala (සිංහල), Tamil (தமிழ்), and English, including significant instances of Singlish and Tanglish 

Conversational Data

The full dataset is a premium, high-logic instruction dataset designed for training state-of-the-art conversational AI models. It contains 279,260 trilingual records optimized for complex problem-solving, chain-of-thought reasoning, and sophisticated tool-calling interactions in Sinhala, Tamil, and English.

Data Archives

Lanka Data provides a comprehensive suite of structured, high-quality downloadable datasets covering Sri Lanka’s legal, economic, taxation, business and regulatory landscape for for access via Lanka Data Search

At its core, the Chat2Find base model is a robust large language model trained on extensive localized data, delivering strong multilingual understanding, while its fine-tuned trilingual models further enhance performance by capturing linguistic nuances and cultural context, resulting in highly natural, accurate, and reliable AI interactions.

LDN Search

Lanka Data Search is the intelligent search layer of Lanka Data Net, providing access to data archive of over 90,000 Sri Lankan documents through fast contextual search.

Base Model

At the heart of Chat2Find lies a robust base model pre-trained on rich, localized data corpus enabling powerful multilingual understanding tailored specifically for Sri Lanka.

Fine Tuned LLM

Refined to perfection, Chat2Find’s fine-tuned models capture linguistic nuance and cultural depth, delivering seamless, natural, and highly accurate interactions in Sinhala, Tamil, and English.

Lanka Data Net (LDN) delivers real-time data retrieval through intelligent layers built across legal, taxation, business, and other key sectors. Using advanced Retrieval-Augmented Generation (RAG) models, these layers dynamically fetch and interpret authoritative data at query time, ensuring accurate, context-aware, and up-to-date responses seamlessly delivered through AI interface. All Expert models are now accessible through the AIMart mobile app, available on Google Play.

LankaLaw

Digital repository of Sri Lankan legislation, case law, and legal resources with responses delivered seamlessly through AI interface

LankaTax

Digital repository of Sri Lankan tax laws, regulations, forms, and guidance, with responses delivered seamlessly through AI interface

LankaBIZ

Digital repository of Sri Lankan business data, including company profiles and disclosures,delivered seamlessly through AI interface.