mongodb-developer/GenAI-Showcase

MongoDB's Generative AI Showcase: an exhaustive collection of examples and sample applications covering Retrieval-Augmented Generation (RAG), AI agents, and industry-specific use cases.

What it is

MongoDB's GenAI Showcase is a public collection of example code and sample applications for building Generative AI (GenAI) software. It's aimed at both beginners and advanced developers, and it focuses on how MongoDB's database products fit into AI workflows.

The examples demonstrate two main AI techniques: Retrieval-Augmented Generation (RAG) — a way to give AI models access to your own data — and AI Agents — programs that use AI to perform multi-step tasks. The repo also shows MongoDB being used in three roles: as a vector database (storing data in a way that lets AI find similar items), as a regular operational database, and as a memory provider (letting AI remember past interactions).

What's inside

The repository is organized into four folders:

  • notebooks — Jupyter notebooks (interactive coding documents) covering RAG, agentic applications, and evaluation of AI systems.
  • apps — JavaScript and Python applications and demos.
  • workshops — Self-paced, hands-on tutorials you can follow on your own.
  • partners — Contributions from MongoDB's AI partners.

How to run it

To use any of the examples, you need a MongoDB database cluster. The README gives three steps:

  1. Register for a free MongoDB Atlas account (MongoDB's cloud service).
  2. Create a new database cluster.
  3. Get the connection string (the address your code uses to talk to the database).

Contributing

Contributions are welcome. The project has a separate file, CONTRIBUTING.md, that explains how to participate.

License

This project is licensed under the MIT License — a permissive open-source license that allows reuse with few restrictions.

Getting support

If you run into problems while working through the examples, you can open a new issue on the project's GitHub page.

Additional resources

The README points to three extra places for help:

  • An AI Learning Hub on MongoDB's website.
  • A GenAI Community Forum for asking questions.
  • A separate GitHub repository (mongodb/docs-notebooks) with tutorials and code examples from MongoDB's official documentation.

Related

  • Project
    MaartenGr/KeyBERT

    KeyBERT is a lightweight Python library that extracts keywords/keyphrases from any text by comparing BERT‑based document embeddings with embeddings of candidate n‑grams. It works out‑of‑the‑box with a single `pip install` and three lines of code, supports multiple embedding back‑ends, and offers diversity controls (max‑sum, MMR) and an optional LLM‑based mode.

  • Project
    SylphAI-Inc/AdalFlow

    AdalFlow is a PyTorch-like library for building and auto-optimizing LLM workflows, including chatbots, RAG, and agents, by replacing manual prompting with automated textual gradient descent.

  • Project
    KKKKhazix/human-writing

    A framework and toolset for AI agents to eliminate "AI-style" Chinese writing by enforcing human-like rhythms, factual substance, and structural checks.

  • Project
    Adkid-Zephyr/anti-defensive-writing-Skill

    A collection of AI prompts and agent skills designed to help researchers rewrite academic papers by eliminating defensive, self-doubting language and focusing on clear, persuasive arguments.