This repository provides a comprehensive collection of examples and sample applications for building Generative AI (GenAI) solutions, focusing on Retrieval-Augmented Generation (RAG) and AI Agents. It targets developers of all skill levels, from beginners to advanced practitioners, demonstrating how MongoDB can be leveraged as a vector database, operational database, and memory provider within these AI architectures.

How It Works

The showcase utilizes Jupyter notebooks for demonstrating RAG, agentic applications, and evaluation techniques. It also includes JavaScript and Python applications and demos. The core approach emphasizes integrating MongoDB into GenAI pipelines, highlighting its capabilities in data storage, retrieval, and state management for AI agents.

Quick Start & Requirements

• Install/Run: Connect to a MongoDB cluster.
  • Register for a free MongoDB Atlas account.
  • Create a new database cluster.
  • Obtain the connection string.
• Prerequisites: MongoDB Atlas account and cluster.
• Resources: Official documentation and tutorials are available via the AI Learning Hub and GenAI Community Forum.

Highlighted Details

• Extensive examples covering RAG and AI Agents.
• Demonstrates MongoDB's role as a vector database, operational database, and memory provider.
• Includes contributions from AI partners.
• Features Jupyter notebooks for RAG, agentic applications, and evaluations.

Maintenance & Community

Support is available through opening new issues. Additional resources include the MongoDB AI Learning Hub and GenAI Community Forum.

Licensing & Compatibility

This project is licensed under the MIT License, permitting commercial use and integration with closed-source applications.

Limitations & Caveats

The examples require a connection to a MongoDB cluster, which may incur costs beyond the free tier for extensive usage.