This package is designed to facilitate the creation of Retrieval-Augmented Generation (RAG) chatbot applications, specifically tailored for educational purposes. It leverages the capabilities of LangGraph, a powerful tool for serving RAG pipelines, to provide a robust backend for chatbot interactions.

Detailed documentation can be found here.

• RAG Pipeline Integration: Utilizes LangGraph to seamlessly integrate RAG pipelines into the chatbot, enhancing its ability to generate informative and contextually relevant responses.
• Session Management: Comes equipped with a session manager to handle interactions efficiently, ensuring a smooth and coherent conversation flow.
• Web Interface: Includes optional prebuilt Flask applications, making it easy to deploy the chatbot on a web browser for accessible and interactive user experiences.
• Terminal Interface: Offers a simple terminal interface for users who prefer a more straightforward method of interaction, making it versatile for different use cases.

• Help students study for an exam
  • Generate example problems
• Provide guided help for students completing homework
  • Not giving them the answers but providing hints and guided help to step them through the problems
  • Pointing the students back to the textbook or slides when guiding them
• Assist them in completing the labs
  • Review their code and provide feedback
  • Help them resolve common issues such as issues with the Vivado tools

To begin using the Maeser Chatbot, follow the development setup instructions. This page includes instructions for cloning the repository and running the app.

NOTE: This application is intended to run on Unix-based systems. For help running Maeser on Windows, follow the development setup using Windows Subsystem Linux instructions.

For a fully working example application, follow the documentation for the example application.

Follow the documentation for embedding custom content here.

An understanding of langchain and langgraph is necessary for customizing the application for any use case. Follow documentation and tutorials here.

• maeser contains the source code for the application.
• dist contains configuration and code for distributing the module.
• requirements contains python requirements files.
• sphinx_docs contains sphinx related code and various documentation files.
• tests contains unit test files for the application's source code.

Maeser is licensed on the LGPL version 3 or later: you can redistribute it and/or modify it under the terms of the GNU Lesser General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version. Maeser is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.

See COPYING.LESSER.md and COPYING.md for more details on the GNU Lesser General Public License. Other resources may be licensed under different compatible licenses, such as the MIT License (Bootstrap Icons), CC0 1.0 (normalize.css), or CC-BY-SA 4.0 (images and vector stores).