lunaai 0.3.0

A retrieval-based QnA and code generation chatbot using sentence-transformer embeddings.

LunaAI

LunaAI is a retrieval-based QnA and code generation chatbot built using SentenceTransformer embeddings and cosine similarity.
It can answer natural language questions and retrieve highly relevant answers from a preloaded CSV dataset — no fine-tuning required. Current Dataset size 100K.

---

Features

• Embedding-based search using SentenceTransformers
• Cosine similarity + fuzzy matching fallback
• Loads embeddings and CSV from Google Drive
• Clean CLI interface with feedback saving
• Lightweight and fast — works offline after setup

---

Avilable Topics

• National Bird (212 unique rows)
• National Flower (141 unique rows)
• National Tree (191 unique rows)
• National fruit (198 unique rows)
• National Flag (206 unique rows)
• Capital City (197 unique rows)
• National Emblem (191 unique rows)
• National Anthem (186 unique rows)
• National Language (197 unique rows)
• National Animal (197 unique rows)
• National Motto (198 unique rows)
• National Dish (192 unique rows)
• Special Days (1187 unique rows)
• National Currency (198 unique rows)
• National Monument (193 unique rows)
• National Costume (192 unique rows)
• National Music (191 unique rows)
• National River (197 unique rows)
• National Heritage Site (195 unique rows)
• National Festivals (196 unique rows)
• National Symbolic Objects (190 unique rows)
• National Park (179 unique rows)
• Historic Landmark (193 unique rows)
• Languages Spoken (194 unique rows)
• Famous Historical Figures (197 unique rows)
• National Literature (196 unique rows)
• Popular Tourist Attractions (196 unique rows)
• Traditional Festivals (191 unique rows)
• Independence Day (196 unique rows)
• Religions Practiced (196 unique rows)
• Political System (193 unique rows)
• Economic Indicators (1475 unique rows)
• Country (194 unique rows)
• Cultural Heritage (1000 unique rows)
• Topic (1 unique rows)
• Longest river (196 unique rows)
• Shortest river (200 unique rows)
• Highest Peak (196 unique rows)
• Longest & Shortest River (8 unique rows)
• Deepest lake (209 unique rows)
• Largest lake (196 unique rows)
• Highest waterfall (187 unique rows)
• Endangered species (201 unique rows)
• Endangered birds (202 unique rows)
• Endangered Trees (202 unique rows)
• Endangered Fish (198 unique rows)
• Largest Desert (208 unique rows)
• Endangered Animals (201 unique rows)
• UNESCO World Heritage Sites (182 unique rows)
• Endangered Mammals (202 unique rows)
• National Mammal (195 unique rows)
• National Reptile (204 unique rows)
• Endangered Reptile (194 unique rows)
• Famous Years (251 unique rows)
• Longest coastline (203 unique rows)
• Largest forest (201 unique rows)
• Natural Wonders (198 unique rows)
• National Insect (205 unique rows)
• National Amphibian (195 unique rows)
• Endangered Amphibian (202 unique rows)
• Medicinal Plants (191 unique rows)
• Most Famous Historical Event (202 unique rows)
• Most Significant War (196 unique rows)
• Oldest Monument (195 unique rows)
• Major Scientific Discovery (146 unique rows)
• Oldest University (201 unique rows)
• Most Advanced Technology (193 unique rows)
• Main Economic Sector (202 unique rows)
• Most Exported Product (201 unique rows)
• Largest Company (202 unique rows)
• Most Popular Sport (203 unique rows)
• Most Famous Athlete (194 unique rows)
• Biggest Stadium (199 unique rows)
• Predicted Major Events (76 unique rows)
• Cure for Cancer & Genetic Diseases (76 unique rows)
• Mind Uploading & Digital Consciousness (76 unique rows)
• Most Endangered Animal (185 unique rows)
• National Fish (190 unique rows)
• Unique Wildlife Species (195 unique rows)
• Most Common Tree Species (190 unique rows)
• Biodiversity Hotspot (193 unique rows)
• Astronomy (582 unique rows)
• Flower Names (26 unique rows)
• Tree Names (26 unique rows)
• Color Names (26 unique rows)
• Aromatic Flower Names (26 unique rows)
• Country names (51 unique rows)
• Fruit names (26 unique rows)
• Protected National Park (194 unique rows)
• Marine Reserve (194 unique rows)
• Deforestation Rate (189 unique rows)
• Reforestation & Conservation Efforts (189 unique rows)
• Popuation (188 unique rows)
• Area (189 unique rows)
• Average Temperature (189 unique rows)
• Major Climate Zone (189 unique rows)
• Largest Glacier (189 unique rows)
• Fastest Train (185 unique rows)
• Largest Railway Platform (202 unique rows)
• National Game (168 unique rows)
• Plastic Waste Generation by Countries (Kaggle) (168 unique rows)
• Total Water Consumption by Countries (Kaggle) (500 unique rows)
• Industrialal Water Usage (Kaggle) (500 unique rows)
• Groundwater Depletion Rate (Kaggle) (500 unique rows)
• Agricultural Water use (Kaggle) (500 unique rows)
• Household Water use (Kaggle) (500 unique rows)
• Annual Precipitation (Kaggle) (500 unique rows)
• Clash of Clans (1971 unique rows)
• Painting Color Types (54 unique rows)
• Art Components (44 unique rows)
• AI (154 unique rows)
• Greeting (96 unique rows)
• History (1 unique rows)
• Fun & Casual Conversation (57 unique rows)
• Help & Guidance (271 unique rows)
• Whats App Help & Guidance (238 unique rows)
• Facebook Help & Guide (491 unique rows)
• Google Help & Guide (273 unique rows)
• Emergency Assistant (340 unique rows)
• Instagram Help & Guide (738 unique rows)
• YouTube Help & Guide (552 unique rows)
• Free fire characters (53 unique rows)
• Free fire weapons (41 unique rows)
• Free fire maps (21 unique rows)
• Affection (2 unique rows)
• Physics (14 unique rows)
• Geography (30 unique rows)
• Context Sense AI (2 unique rows)
• Full forms (519 unique rows)
• Fun (1 unique rows)
• Travel Tips (9 unique rows)
• Transportation Tips (7 unique rows)
• Accommodations (7 unique rows)
• Food and Dining (7 unique rows)
• Destinations (12 unique rows)
• About the Model (12 unique rows)
• Plant Care (1214 unique rows)
• Programming Language (24 unique rows)
• Python (187 unique rows)
• Regression Models (50 unique rows)
• Classifiers (63 unique rows)
• Machine Learning (78 unique rows)
• General Knowledge (3191 unique rows)
• Cricketer Name (Kaggle) (1542 unique rows)
• Mobiles (Kaggle) (908 unique rows)
• Cars (Kaggle) (720 unique rows)
• Miscellaneous (251 unique rows)
• Amazon Rainforest (126 unique rows)
• Pyramids (145 unique rows)
• Chemistry - Atomic Numbers (119 unique rows)
• Periodic Table (177 unique rows)
• Mesopotamian Civilization (256 unique rows)
• Indus Valley Civilization (84 unique rows)
• Grand Canyon (303 unique rows)
• Great Barrier Reef (114 unique rows)
• Moon Landings (329 unique rows)
• Gemini (288 unique rows)
• Mars Mission (346 unique rows)
• Mythology (459 unique rows)
• Scientific Discoveries (250 unique rows)
• Modern Inventions (371 unique rows)
• Historical Events (200 unique rows)
• Space Exploration (107 unique rows)
• Great World Leaders (319 unique rows)
• World Wonders (101 unique rows)
• Industrial Revolution (178 unique rows)
• Global Conflicts (79 unique rows)
• Human Evolution (31 unique rows)
• Different types of Fishes (229 unique rows)
• Different Apps (48 unique rows)
• WikiPedia Dataset (2118 unique rows)
• IPL (3252 unique rows)
• Top Rated Movies (Kaggle) (9554 unique rows)
• Popular Youtube Videos (Kaggle) (992 unique rows)
• Google Quaries (7785 unique rows)
• Products (998 unique rows)
• Quora Questions (1693 unique rows)
• HFRL (135 unique rows)
• Smallest river (2 unique rows)
• Visual Studio Code Help & Guidance (16 unique rows)
• Taste (2 unique rows)
• Color (1 unique rows)

---

Installation

pip install lunaai