New Course: How to Build a Responsible AI Chatbot Using Open Technologies

Today we’re excited to launch our new course, How to Build a Responsible AI Chatbot Using Open Technologies, now available on Open Knowledge’s learning platform School of Data.

AI chatbots are everywhere, but too few people understand how they actually work — or how to build one that is accurate, transparent and grounded in trusted knowledge. This course came out of the Responsible Climate Chatbot Lab, part of Open Knowledge’s AI Learning Labs initiative.

In this Lab, the #semanticClimate team developed CABot, a climate chatbot that answers questions using the Climate Academy as its knowledge base. Now they turned what they learned into this course: a step-by-step guide for educators, researchers, students, and open knowledge and community practitioners who want to do the same for their own domains.

The course is hands-on and practical. Over 5 modules and 35 lessons, you’ll move from the fundamentals of how Large Language Models (LLMs) generate language (and why they hallucinate), through the concepts behind Retrieval-Augmented Generation (RAG) — embeddings, semantic search and vector databases — to the full architecture of a working chatbot, from the browser interface all the way through to the model.

Along the way, the course keeps responsibility at the centre: how to reduce hallucinations, why every answer should cite its sources, and what fairness, privacy and environmental sustainability mean for AI systems. The course ends with a capstone on building multilingual chatbots and evaluating them across languages.

Everything is built with open technologies and open source code, and the full repository is available on GitHub, so you can explore, reuse and adapt the materials for your own community.

What You Will Learn

• Understand different approaches to building chatbots using Retrieval-Augmented Generation (RAG).
• Replicate a chatbot workflow using open, lightweight technologies.
• Make informed design decisions around trust, multi-linguality and sustainability.
• Build responsible chatbots grounded in curated knowledge.

Who is This For?

• Data, software, and civic-tech practitioners building responsible AI tools
• Climate, environmental, and sustainability educators, researchers, and students
• Open knowledge, NGO, library, and community capacity-building practitioners

The course was developed by Udita Agarwal and Renu Kumari on behalf of the CABot project team: Aleena Harold Peter, Ali Mehdi Naqvi, Bui Doan Khanh Linh, Gitanjali Yadav, Parth Kadam, Peter Murray-Rust, Saarthak Patwal, Samyukta Nair and Shreya Bhat.

We’re launching the course in English first. A multilingual version is on its way — we’re working on translations so that more communities can access the course in their own languages. Watch this space for announcements.

About

Open Knowledge’s AI Learning Labs is an initiative that aims to experiment with AI, translate knowledge from social sector organisations around the world, and produce public, multilingual AI-literacy resources tailored for organisations addressing similar issues elsewhere.

Together, we will catalyse learning and develop replicable methods to help organisations build AI skills, use AI responsibly, and develop their own AI projects. All resources will be openly available at School of Data.

Join the conversation:

This project has been made possible thanks to the generous support of the Patrick J. McGovern Foundation (PJMF). We are grateful for our ongoing partnership in promoting digital literacy and investing in AI for the public good. Learn more about its funding programmes here.