Get startedGet started for free

Preparing for Multi-Modal RAG

This exercise is part of the course

End-to-End RAG with Weaviate

View Course

Exercise instructions

  • Instantiate the model and accompanying processor to compute the text and image embeddings.
  • Preprocess the image inputs and generate the image embeddings using the model and processor you defined.
  • Create and use a collection called "Pages" to store the PDF pages and their embeddings.
  • Add the image embeddings to the "Pages" collection and close the connection.


Note: If you’re running DataLab in Restricted Mode, this exercise isn’t supported yet. We’re actively working on making it available in the future.


Hands-on interactive exercise

Turn theory into action with one of our interactive exercises

Start Exercise