SAGE Applications
Real-world AI applications built on the SAGE framework, showcasing end-to-end solutions for various domains.
Overview
isage-apps provides production-ready applications demonstrating SAGE's capabilities:
- Video Intelligence: Multi-model video analysis pipeline with CLIP and MobileNetV3
- Medical Diagnosis: AI-assisted medical image analysis for healthcare
Installation
Basic Installation
pip install isage-apps
Install with Specific Applications
# Video intelligence only
pip install isage-apps[video]
# Medical diagnosis only
pip install isage-apps[medical]
# All applications
pip install isage-apps[all]
Development Installation
cd packages/sage-apps
pip install -e ".[dev]"
📖 Quick Start
# Run video intelligence demo
pip install isage-apps[video]
python -m sage.apps.video.video_intelligence_pipeline --video path/to/video.mp4
# Run medical diagnosis demo
pip install isage-apps[medical]
python -m sage.apps.medical_diagnosis.run_diagnosis
Applications
1. Video Intelligence
Advanced video analysis pipeline combining multiple AI models:
- Frame sampling and preprocessing
- Zero-shot scene understanding (CLIP)
- Object classification (MobileNetV3)
- Temporal anomaly detection
- Sliding-window summarization
- Keyed event aggregation
Quick Start:
pip install isage-apps[video]
python -m sage.apps.video.video_intelligence_pipeline --video path/to/video.mp4
Features:
- Multi-model inference pipeline
- Real-time processing with SAGE operators
- Structured JSON output (timeline, summary, events)
- Console progress monitoring
- Graceful degradation (works offline with cached models)
Documentation: See sage/apps/video/README_intelligence_demo.md
2. Medical Diagnosis
AI-assisted diagnostic system for medical imaging:
- Multi-agent architecture (diagnostic, image analysis, report generation)
- Knowledge-based reasoning
- Structured medical reports
- Training and evaluation tools
Quick Start:
pip install isage-apps[medical]
python -m sage.apps.medical_diagnosis.run_diagnosis
Features:
- Agent-based diagnostic workflow
- Medical knowledge base integration
- Configurable diagnostic criteria
- Report generation
Documentation: See sage/apps/medical_diagnosis/README.md
Package Structure
sage-apps/
├── src/sage/apps/
│ ├── __init__.py
│ ├── video/ # Video intelligence application
│ │ ├── video_intelligence_pipeline.py
│ │ ├── operators/ # SAGE operators for video
│ │ ├── config/ # Configuration files
│ │ └── README_intelligence_demo.md
│ └── medical_diagnosis/ # Medical diagnosis application
│ ├── run_diagnosis.py
│ ├── agents/ # Diagnostic agents
│ ├── config/ # Agent configurations
│ ├── data/ # Medical datasets
│ └── README.md
└── tests/ # Application tests
Dependencies
Core Framework
isage-common- Common utilitiesisage-kernel- Runtime and operatorsisage-middleware- Services (SageVDB, SageFlow, NeuroMem)isage-libs- Operator libraries
Application-Specific
Video Intelligence:
opencv-python- Video processingtorch- Deep learningtransformers- CLIP and language models
Medical Diagnosis:
pillow- Image processingscikit-learn- ML utilities
Usage Examples
Video Intelligence
from sage.apps.video.video_intelligence_pipeline import main
# Run with custom video
main(["--video", "my_video.mp4", "--max-frames", "100"])
Medical Diagnosis
from sage.apps.medical_diagnosis.run_diagnosis import run_diagnosis
# Run diagnostic pipeline
run_diagnosis(config_path="config/agent_config.yaml")
Development
Running Tests
pytest tests/
Code Quality
# Format code
black src/
# Lint
ruff check src/
# Type checking
mypy src/
CI/CD Notes
Video Intelligence:
- Requires HuggingFace model downloads (~170MB)
- Tagged with
@test:skipin CI due to network restrictions - Test locally with:
python -m sage.apps.video.video_intelligence_pipeline
Medical Diagnosis:
- Works in CI (uses local data)
- Test with:
pytest tests/test_medical_diagnosis.py
Contributing
See CONTRIBUTING.md for guidelines.
License
MIT License - see LICENSE for details.
Related Documentation
Metadata
Release files for isage-apps 0.2.5
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| isage_apps-0.2.5-py3-none-any.whl | Python 3 | none | any | Details for isage_apps-0.2.5-py3-none-any.whl |
Release files / isage_apps-0.2.5-py3-none-any.whl
| Download URL | isage_apps-0.2.5-py3-none-any.whl |
|---|---|
| Size | 376.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
311830ad4d20e9658ffccb2a0d9eceaab910d172881e13baec6b61c8d1cdb82c
|
|
BLAKE2b-256 checksum How to use checksums |
a1671fc48dcecfcddf400374be51d70c6369f03bbc61802a8d59bf1fc20b9aa1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.12
|
Security for isage-apps 0.2.5
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.