Home

Buddhist Consensus Wiki

Welcome to the Buddhist Consensus project wiki! This is a bilingual (Tibetan–English) AI platform that answers Buddhist questions with cited sources from canonical and academic texts.

🎯 Project Overview

Buddhist Consensus is an intelligent question-answering system that leverages:

• Retrieval-Augmented Generation (RAG) for accurate, source-backed responses
• Hybrid Search combining semantic and keyword-based retrieval
• Bilingual Support for Tibetan (བོད་སྐད་) and English queries
• Citation System that links every claim to canonical sources

📚 Wiki Contents

Core Documentation

• Architecture - System architecture and component overview
• Concepts-and-Terminology - Definitions of key concepts used in this project
• RAG-System - Deep dive into the Retrieval-Augmented Generation system

Technical Reference

• API-Reference - Complete API documentation
• Data-Preparation - How to prepare and process Buddhist texts
• Frontend - Chat UI implementation details

Getting Started

• Installation - Setup and deployment guide
• Usage-Guide - How to use the system

---

🏛️ Technology Stack

Component	Technology
Backend Framework	FastAPI
LLM	Google Gemini 2.0 Flash
Embeddings	Gemini Embedding 001
Vector Database	Milvus
Orchestration	LangGraph
Frontend	Vanilla HTML/CSS/JavaScript

🔗 Quick Links

• Main Repository
• API Endpoint
• OpenPecha Organization

📖 Data Sources

The system uses texts from:

• Kangyur (བཀའ་འགྱུར) - The Tibetan Buddhist Canon containing Buddha's teachings
• Tengyur (བསྟན་འགྱུར) - Commentaries and treatises by Indian and Tibetan masters
• Additional curated Buddhist academic texts

---

This project is developed by OpenPecha to make Buddhist wisdom accessible through AI technology.