🚀 完整的生成式AI开发工具包,支持RAG、LLM和多模态AI功能
Project description
🌟 GenerativeAI-Starter-Kit
🚀 A comprehensive, beginner-friendly Generative AI development toolkit
Welcome to GenerativeAI-Starter-Kit! This repository provides everything you need to get started with Generative AI—from basic concepts to production-ready applications. Perfect for learning, rapid prototyping, and real-world deployment.
🧠 What's Included
- RAG (Retrieval-Augmented Generation): Build intelligent document Q&A systems
- Multimodal Applications: Work with text, images, and cross-modal tasks
- Model Fine-tuning: Adapt pre-trained models for specific domains
- Production-Ready APIs: FastAPI servers with full documentation
🛠️ Development Tools
- One-Click Setup: Automated environment configuration
- Interactive Notebooks: Step-by-step Jupyter tutorials
- Configuration Management: Easy YAML-based settings
- Testing Framework: Comprehensive test suites
📚 Learning Resources
- Multi-language Docs: Complete guides in English and Chinese
- Progressive Tutorials: From beginner to advanced
- Best Practices: Industry-standard approaches
- Research Examples: Latest techniques and methods
📦 Installation
✅ From PyPI (Recommended)
pip install genai-starter-kit
from genai_starter_kit import chains, utils
response = chains.run_rag_query("What is retrieval-augmented generation?")
print(response)
🧪 From Source (Development Mode)
git clone https://github.com/YY-Nexus/GenerativeAI-Starter-Kit.git
cd GenerativeAI-Starter-Kit
pip install .
🚀 Quick Start
1️⃣ Clone & Setup
git clone https://github.com/YY-Nexus/GenerativeAI-Starter-Kit.git
cd GenerativeAI-Starter-Kit
./automation/setup.sh
source venv/bin/activate
2️⃣ Try the Examples
# RAG System Demo
python examples/rag/simple_rag.py
# Multimodal Web App
python examples/multimodal/image_text_app.py --web
# Fine-tuning Demo
python examples/fine-tuning/text_classification_tuning.py
# Start API Server
python automation/api_server.py
📚 Batch Run All Notebooks
pip install jupyter nbconvert
find RAG/notebooks -name "*.ipynb" -exec jupyter nbconvert --to notebook --execute --inplace {} \;
🗂️ Directory Structure
docs/ # Documentation and usage guides (with Chinese docs in docs-zh) RAG/ # Retrieval-Augmented Generation module community/ # Community contributions and experimental resources examples/ # Example scripts and demos scripts/ # Automation and lint/test/release scripts tests/ # Unit tests automation/ # Setup and API server scripts setup.py # Build configuration
🔧 Core Features
- End-to-end RAG examples (basic & advanced)
- Multimodal and industry-specific AI agents (text, speech, image, healthcare, finance, security)
- Model fine-tuning, training, evaluation, and safety (Llama, NeMo, Nemotron)
- Community resources, open-source contributions, and tutorials
- Comprehensive documentation (Chinese & English), one-click scripts, batch notebook execution
💼 Typical Use Cases
- Intelligent Q&A, knowledge retrieval, document analysis
- Multimodal interaction (speech, image, text)
- Industry-specific agents (healthcare, finance, security)
- Large model fine-tuning and safety evaluation
❓ FAQ & Help
- Dependency install failed? Check Python version or use a local mirror.
- API service won't start? Check port usage or run
python main.py --helpfor options. - Notebooks won't batch run? Ensure Jupyter and nbconvert are installed.
📖 See docs/README.md or open a GitHub Issue for more help.
🤝 Contributing & Feedback
- Pull Requests welcome for code, docs, or examples
- Report issues with clear steps and environment details
- All contributions must comply with the LICENSE
📐 Standardization & Usability Commitment
- Unified script and doc formats with clear comments and step-by-step instructions
- Modular directory structure for easy navigation and extension
- Chinese and English documentation for global accessibility
- Continuous improvement—feedback is welcome!
This project is committed to making generative AI development easy for everyone.
Join our community and start building today!
Project details
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 genai_starter_kit-0.2.0.tar.gz.
File metadata
- Download URL: genai_starter_kit-0.2.0.tar.gz
- Upload date:
- Size: 76.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
1128366c7e4d2ac0dbe39be54305bb4718fff728cc2b615794bf4dd9e338931f
|
|
| MD5 |
5998257f3f6c9af4ea66f60993edd6eb
|
|
| BLAKE2b-256 |
9143f6adbd725a3d01eb1aa2ce5c0414923b994475f97ba55cdda08690b9a9b9
|
File details
Details for the file genai_starter_kit-0.2.0-py3-none-any.whl.
File metadata
- Download URL: genai_starter_kit-0.2.0-py3-none-any.whl
- Upload date:
- Size: 28.2 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 |
9820c9cac4b00d2aeabf366c5e46aa353d11c8a3d7680d1aef5287fd6d67867d
|
|
| MD5 |
9803777c6a5da2b1952ff59fb85138d3
|
|
| BLAKE2b-256 |
25a20c6842cd7d4db5bd90bf4c17e971808d3dce01fc3bffe6667ba00b16c303
|