Back to .md DirectoryData Processing (
Frame Processing (
Utilities (
TALI Project Map
๐ฏ Core Functionality
Data Processing (tali/data.py)
- Dataset loading and management
- Transform pipeline implementation
- Modality type definitions
- Configuration system
Frame Processing (tali/frames.py)
- Video frame extraction
- Frame selection methods
- Format conversion utilities
Utilities (tali/utils.py)
- Helper functions
- Logging setup
- Common utilities
๐ฆ Package Structure
Main Package
tali/
โโโ data.py # Core data processing
โโโ frames.py # Video frame handling
โโโ utils.py # Utility functions
โโโ data/ # Data-specific modules
โโโ demo/ # Demo applications
โโโ __init__.py # Package initialization
Examples and Tests
TALI/
โโโ examples.py # Usage examples
โโโ tests/ # Test suite
โโโ requirements.txt # Dependencies
๐ง Configuration Files
Development Setup
requirements.txt- Core dependenciesrequirements_dev.txt- Development dependenciessetup.py- Package setup.cursorrules- Development guidelines
Documentation
README.md- Project overviewARCHITECTURE.md- System designMILESTONES.md- Development progressMAP.md- Project navigation
Docker Support
Dockerfile- Container definitioninstall-via-conda.sh- Conda setup
๐ Quick Links
Getting Started
Development
Features
๐ Learning Resources
Documentation
Related Documents
ARCHITECTURE.md
Design Document: BharatSeva AI
BharatSeva AI is a multi-agent orchestration system built on AWS using Amazon Bedrock Agents with Claude 3.5 Sonnet as the foundation model. The system deploys 10 AI agents (1 Master Orchestrator + 9 Specialist Agents) to assist India's informal sector workers in navigating government schemes across three domains: PM Vishwakarma (artisan credit), PMFBY (crop insurance), and BOCW (construction worker welfare).
aiagentclaude
0
101
Prachet-Dev-SinghARCHITECTURE.md
OpenClaw Enterprise Transformation Plan
Transform OpenClaw from a single-user personal AI assistant into a **dual-mode platform** that is simultaneously:
aiagentrag
0
47
mholovetskyiARCHITECTURE.md
Qwen Image and Edit: Open-sourcing and Local GGUF Generations with Lightning
Daniel Sandner, for article on https://sandner.art/
aillmrag
0
19
sandner-artARCHITECTURE.md
Qwen3-TTS โ Model Reference
Models: `Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice` and `Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice`
aillm
0
19
gabriele-mastrapasqua