Bielik — Local-first AI assistant with HuggingFace and SpeakLeash models
Project description
🦅 Bielik
Polish AI Assistant CLI - Advanced command-line interface for local HuggingFace model execution with Context Provider Commands.
Bielik is a groundbreaking Polish language model created by Speakleash - a foundation dedicated to the development of Polish artificial intelligence.
🇵🇱 Bielik models are available on HuggingFace Hub
🚀 Quick Start
One-liner Installation
curl -sSL https://install.bielik.ai | bash
Basic Usage
# Interactive mode
bielik
# Single prompt
bielik -p "Jak się masz?"
# Context Provider Commands (instant execution)
bielik -p "calc: 2 + 3 * 4"
bielik -p "folder: ."
✨ Key Features
- 🎯 Local Execution - Complete privacy, no external API calls
- 💬 Polish Language Optimized - Built for Polish conversation and analysis
- ⚡ Context Provider Commands - Instant data processing without AI model loading
- 🖼️ Vision Capabilities - Image analysis and visual question answering
- 📁 Document Processing - PDF, DOCX, web content analysis
- 🐳 Docker Ready - Comprehensive multiplatform testing
- 🔧 Extensible - Easy custom command development
📚 Complete Documentation
📖 For detailed information, visit our comprehensive documentation:
📋 Core Documentation
- 📖 Documentation Home - Navigation and overview
- 📥 Installation Guide - Conda, manual, Docker, troubleshooting
- 🏗️ System Architecture - Design, components, data flow
- ⚡ Usage Guide - Commands, examples, best practices
🛠️ Development
- 🤝 Contributing Guide - Development setup, standards, PR process
- 🔌 Python API - Client usage, WebSocket, error handling
- 🎯 Context Provider Commands - Custom command development
- 🐳 Docker Testing - Multiplatform testing framework
🤝 Contributing
We welcome contributions! See our Contributing Guide for:
- Development setup and standards
- Pull request process
- Code quality guidelines
- Testing requirements
📄 License
This project is licensed under the Apache License 2.0 - see the LICENSE file for details.
Author: Tom Sapletta
🏢 Founder & CEO at Telemonit - Edge computing power solutions
🌍 Based in Germany | Open to collaboration
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file bielik-0.2.8.tar.gz.
File metadata
- Download URL: bielik-0.2.8.tar.gz
- Upload date:
- Size: 71.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
5a9ad6ce9d1f82dedb0d17c6798f9b79c62ae130d619b6d775ca3c11c649cd48
|
|
| MD5 |
3d2ee30e734e977bd65593565eeecb3d
|
|
| BLAKE2b-256 |
edb7322c84555d08d5fa206982d59e97f46808bf1bf8057102950a4f61a78b61
|
File details
Details for the file bielik-0.2.8-py3-none-any.whl.
File metadata
- Download URL: bielik-0.2.8-py3-none-any.whl
- Upload date:
- Size: 41.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
6a5aa790cf5c79246286d99c7acc7e6b8cf811c062883c67d7d51372e354037f
|
|
| MD5 |
504023080d01b4760351f906af9af699
|
|
| BLAKE2b-256 |
676415ec75d736d55bc947df150d36e2c713739cf9c8bba8c11f9bd940462b1e
|
