Two Waterloo Engineering and computer science students organized a day-long hackathon with more than 50 participants at the Pearl Sullivan Engineering IDEAs Clinic.
Led by Faraz Khoubsirat, a third-year software engineering student, and Bing Hu, a computer science PhD student, the hackathon challenged participants to solve real-world problems using Cohere's powerful AI engines and Retrieval Augmented Generation (RAG) APIs.
RAG is the next-generation framework for large language models. AI models such as Cohere’s Coral use RAG to retrieve facts from an external knowledge base to ground itself on the most accurate, up-to-date information and to give users insights into its generative process.
During the hackathon, students had full access to Cohere’s powerful models including Command, a generative AI model competitive with ChatGPT, Embed, a top-performing embedding model that converts text to vectors, and Rerank, a top-performing model that improves the relevance of search systems. With these highly capable AI tools, students were able to harness their creativity to develop innovative solutions to challenging problems.
First-place winner — MedChat: Bridging AI and Medical Practice, $1,000 prize
Second-place winner — SVG-Gen, $400 prize
Third-place winner — CoWhere: AI-Powered Codebase Assistant, $200 prize
Go to Cohere hackathon challenges students to use AI to solve pressing problems for the full story.