Skip to content

Latest commit

 

History

History
139 lines (98 loc) · 5.58 KB

README.md

File metadata and controls

139 lines (98 loc) · 5.58 KB
Raw
Use dark mode!

Glimpser

Introduction

Glimpser is a straightforward yet powerful real-time monitoring application designed to capture, analyze, and summarize live data from various sources such as cameras, dashboards, and video streams. Utilizing advanced image processing techniques and AI models, Glimpser provides insightful summaries and alerts. It’s highly configurable, allowing users to tailor it to their specific monitoring needs through an easy-to-use interface.

Glimpser August 2024

Features

  • Real-time Monitoring: Continuously captures data from multiple sources. Whether it's a traffic camera or a weather dashboard, Glimpser ensures you’re always up-to-date with the latest information.

  • Image Processing: Employs advanced techniques to compare images and detect even subtle changes, making it ideal for monitoring evolving situations effectively.

  • Motion Detection: Automatically detects motion in the captured images and videos, triggering alerts and actions as configured by the user.

  • AI Integration: Integrates with models like LLaVA and ChatGPT to provide intelligent insights. It can summarize data, detect anomalies, and generate alerts based on predefined rules.

  • Auto-captioning: Automatically generates concise and informative captions for images and videos, providing quick insights into the content.

  • Auto-summarization: Summarizes data from multiple sources into a coherent and concise format, highlighting the most important information.

  • Customizable Configuration: Easily configure different data sources and processing rules through the user-friendly interface. Glimpser’s configuration is fully database-driven, ensuring flexibility and ease of use.

  • Data Retention Policies: Automatically manages storage by cleaning up old data, ensuring the system remains efficient without requiring constant manual intervention.

  • Web Interface: A user-friendly web interface allows for easy monitoring and configuration. Users can view live feeds, summaries, and configure settings without delving into the code.

Installation

Prerequisites

  • Python 3.8 or higher

Steps

  1. Install the Package

    pip install glimpser

    Or, if you want to install from source:

    git clone https://github.com/KristopherKubicki/glimpser.git
cd glimpser
pip install .

  2. Run the Application

    glimpser

    You will be prompted to create a secret key to initialize the local sqlite database. Follow the rest of the guided setup and then direct your browser to http://127.0.0.1:8082 to finish the rest of the setup.

Usage

Configuration

Glimpser uses a database-driven configuration to manage data sources and processing rules. Users can easily add, update, or remove configurations through the web interface.

Capturing Screenshots

The preferred method for capturing screenshots is through the Glimpser web interface. Simply navigate to the capture section, select your desired source, and click the capture button. This ensures a seamless and user-friendly experience.

Running Tests

To ensure everything works as expected, you can run the included unit tests:

python -m coverage run -m pytest

Motion Detection

Glimpser automatically detects motion in the captured images and videos. When motion is detected, the system can trigger alerts, capture additional data, and generate relevant summaries and captions.

Auto-captioning

Using advanced AI models, Glimpser generates concise and informative captions for images and videos. This feature helps users quickly understand the content and context of the captured data.

Auto-summarization

Glimpser can summarize data from multiple sources into a coherent and concise format. The summaries highlight the most important information, making it easier for users to stay informed.

Development

To set up the project for development:

  1. Clone the repository:

    git clone https://github.com/KristopherKubicki/glimpser.git
cd glimpser

  2. Create a virtual environment and activate it:

    python -m venv venv
source venv/bin/activate  # On Windows, use `venv\Scripts\activate`

  3. Install the package in editable mode with development dependencies:

    pip install -e ".[dev]"

  4. Run tests:

    pytest

Contributing

Contributions are always welcome. If you have an idea to improve Glimpser, feel free to fork the repository and submit a pull request.

License

This project is licensed under the MIT License. See the LICENSE file for details.

Steps to Contribute

  1. Fork the repository.
  2. Create a feature branch. 
    git checkout -b feature-branch
  3. Commit your changes. 
    git commit -m "Description of changes"
  4. Push to the branch. 
    git push origin feature-branch
  5. Open a pull request.

Recommendations

For detailed suggestions on how to use Glimpser effectively, please check out our Recommendations guide.

License

This project is licensed under the MIT License. See the LICENSE file for details.

Acknowledgements

We are grateful to the contributors and the open-source community. Special thanks to OpenAI for their powerful models that enable Glimpser's advanced features.