This repository serves as a central hub for the RAGHack, a virtual event focused on building Retrieval Augmented Generation (RAG) applications. It targets developers interested in leveraging LLMs with their own data, offering guidance, code samples, and a platform for learning and competition. The primary benefit is hands-on experience with RAG implementation across various languages and data sources.

How It Works

The RAGHack provides a structured learning path through a series of live streams covering RAG fundamentals, popular frameworks like LangChain and Semantic Kernel, and integration with Azure AI services. It emphasizes practical application by demonstrating RAG implementation with diverse data sources such as Azure AI Search, PostgreSQL, Azure SQL, and Cosmos DB, across multiple programming languages (Python, Java, JS, C#).

Quick Start & Requirements

• Registration: Participants must register via session links on the Reactor series home page.
• Resources: Code samples are available in various repositories (e.g., azure-search-openai-demo, rag-postgres-openai-python).
• Dependencies: Many samples require Azure deployments and specific Azure services. Some can be run locally with tools like Ollama or Azure SQL Database free tier.
• Community Support: Office hours are available on the AI Discord channel.
• Submission: Hack submissions are due September 16th, 11:59 PM PST.

Highlighted Details

• Over 25 live streams covering RAG development in Python, Java, JS, C#.
• Demonstrates integration with Azure AI Search, PostgreSQL, Azure SQL, and Cosmos DB.
• Explores frameworks like LangChain, Semantic Kernel, and concepts like agents and vision models.
• Offers prizes for winning hack submissions across various categories.

Maintenance & Community

The hackathon is organized by Microsoft, with numerous Microsoft engineers, product managers, and developer advocates involved as hosts and judges. Community support is available via an AI Discord channel.

Licensing & Compatibility

The repository itself is licensed under the MIT License. However, the individual code samples may have different licensing terms or dependencies on Azure services, which should be reviewed on a per-repository basis.

Limitations & Caveats

The hackathon has specific dates for streams and submissions. Many code samples require Azure cloud resources, which may incur costs if not managed carefully within free tiers. The event is time-bound, with submissions due September 16th.