The following projects were reviewed to gain a better understanding of what RAG can achieve and to identify areas that we need to work on to make our project multimodal.

• Verba

  Verba is an open-source RAG app that allows users to interact with a multimodal interface. It is very close to what we are trying to achieve with our project, and it is a good example of what we can do. Whilst Verba emphasizes on vectorizing and indexing whole pdf files, we only focus on vectorizing and retrieving separated text/image and also audio/video files.

• ArcGIS

  It is a cloud-based mapping and analysis solution that allows you to create and share maps and data. In ArcGIS, users can create and view maps and data, with multiple data layers and great visualization tools. It gives us good guidelines on what our map function can potentially achieve. In the end, we choose to only implement basic map functions as it is not our main focus.