Offline Wikipedia with Advanced Search

A self-contained tool for creating local SQLite databases of Wikipedia articles with efficient lexical and semantic search capabilities.

Explore Features Live Demos

$ curl wikilite.eja.it|sh
Launch CLI search? (Y/n): 
1. lexical/es
2. lexical/it
3. lexical/sc
4. semantic/es.minilm
5. semantic/it.all-minilm
6. semantic/it.qwen3
7. semantic/sc.minilm
Choose a file by number or enter to exit: 7

Technical Features

Core functionalities that make Wikilite powerful and versatile.

Dual Search Modes

Combines FTS5 lexical search for exact matching with semantic search using embeddings for conceptual similarity.

Complete AI Integration

Full llama.cpp integration with GGUF models embedded directly in database files for standalone operation.

Android/Termux Support

Compatible with Termux environment using provided packages for mobile usage.

Multi-Language

Pre-built databases available for multiple languages including Italian, Spanish, German, and more.

Dual Interfaces

Command-line interface for terminal usage and web interface for browser-based access.

Single File Deployment

Requires only the Wikilite executable and database file for complete offline operation.

Advanced Search Capabilities

Two powerful ways to find the information you need.

Lexical Search

Utilizes SQLite FTS5 for efficient keyword-based searching with microsecond response times.

Full-text search of titles and content
Title-specific search
Vocabulary distance search
Ideal for exact word and phrase matching

Semantic Search

Implements ANN quantization and MRL with text embeddings to find semantically similar content.

Handles query misspellings and errors
Finds conceptual similarity
Synonym and related term matching
Morphological variations

Use Cases

Who can benefit from offline Wikipedia access?

Education & Research

Offline access for students and researchers in areas with limited internet.

Travel & Remote Work

Access content while traveling or working in areas with unreliable internet.

Privacy-Focused Usage

Search without sending queries to external servers, ensuring complete privacy.

Language Learning

Use semantic search to find related content when learning new languages.

Digital Libraries

Create specialized knowledge bases for institutions requiring offline access.

Development & Testing

Utilize as a test dataset for NLP applications and search algorithm development.

Try Wikilite

Explore live demos or download and build from source.

Sardinian Italian Spanish German Simple English

Get the Source

Clone the repository and build from source.

$ git clone --recursive https://github.com/eja/wikilite.git
$ make

View on GitHub

Download for Android

Install the Wikilite app directly on your device via the latest APK release.

Download APK

Pre-built Databases

Download ready-to-use databases for multiple languages from Hugging Face.

Databases with "lexical" support full-text search, while others include both lexical and semantic search.

Browse Databases