FireSense
FireSense is a video feed analyzer that detects fires, powered by the Gemma 3N vision model.
Pipeline
Quick Start
Installation
# Install pypi package
pip install firesense
or
# Install from source code:
uv pip install -e .
Command Line Usage
# Analyze a YouTube video
firesense analyze <youtube_video_id>
# Launch demo with local server
firesense demo <youtube_video_id> --local
https://github.com/user-attachments/assets/b8fdba5b-bd2d-44c6-be4e-8fb6499b62a8
Ngrok Integration
# setup ngrok
ngrok config add-authtoken <your_ngrok_auth_key>
# Launch demo with local server and ngrok tunnel
firesense demo <youtube_video_id> --local --ngrok
Python Usage
from firesense import setup_model, infer
# Setup model
model, tokenizer = setup_model()
# Run inference
inference_result = infer(model, tokenizer, system_prompt, user_prompt, image_path)
Features
- 🚀 Fast Development: Leverages uv for 10-100x faster dependency installation
- 📦 Modern Packaging: PEP 621 compliant with pyproject.toml
- 🔍 Type Safety: Full mypy strict mode support (uv run mypy src)
- ✅ Testing: Comprehensive pytest setup with coverage
Contributing
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature) - Make your changes
- Run tests and checks (
make check) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
Testing
# Install the project with development dependencies using:
uv pip install -e ".[dev]"
# Run the tests with:
uv run pytest
Type Safety
# Full mypy strict mode support
uv run mypy src
Releasing
New releases are manually pushed to pypi:
make publish
License
This project is licensed under the MIT License - see the LICENSE file for details.
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
firesense-0.10.2.tar.gz
(1.1 MB
view details)
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 firesense-0.10.2.tar.gz.
File metadata
- Download URL: firesense-0.10.2.tar.gz
- Upload date:
- Size: 1.1 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.1.0 CPython/3.11.8
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
f60d378e65bd77a4eaff2a02f04a934ac5e01bf0682638e3d0e52850982a2cbc
|
|
| MD5 |
3f1931f670e70699185e15c0ff0ff1d0
|
|
| BLAKE2b-256 |
e40a099a7868cf4bb446a35081798e2c3d051b80a507e69bc34d931028e6bd93
|
File details
Details for the file firesense-0.10.2-py3-none-any.whl.
File metadata
- Download URL: firesense-0.10.2-py3-none-any.whl
- Upload date:
- Size: 75.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.1.0 CPython/3.11.8
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
00e789bd3018655edfe79cea3608a14e386e60fe2cc43148edb45da41318947f
|
|
| MD5 |
d1e73e9edbadd988fe80f9ae7a51c7fe
|
|
| BLAKE2b-256 |
c207aa4f391d528739112725411aa5f719e314959166f2a6f4bc6e6e968059e4
|
