One of the biggest challenges in AI development is integrating multiple types of data, like video, images, and text, into a single, coherent system that can understand and interact with all of them at once. Intel® Liftoff member Prediction Guard is bringing solutions to the table in collaboration with Intel® Labs and Deeplearning.ai. Their free multimodal retrieval-augmented generation (RAG) course is ideal for AI developers, data scientists, and engineers who want to build smarter question-answering systems that go beyond just text.
This course will teach participants how to "chat with videos" through the creation of sophisticated question-answering systems that process and understand multimodal data. Participants will gain cutting-edge skills: from exploring multimodal semantic space, to learning how to integrate video, text, and visual information into a smooth interactive experience.
Key lessons include:
- Developing a multimodal RAG system that processes video frames, transcripts, and captions
- Storing multimodal data in a vector database
- Retrieving relevant video segments based on text queries
- Leveraging large vision-language models (LVLMs) to generate contextual responses
- Maintaining multi-turn conversations about video content
We’re proud of Prediction Guard’s commitment to advancing AI innovation and education. It’s inspiring to see pioneering startups “pass it forward” and help the industry as a whole to progress. If you’ve been looking for a way to sharpen your RAG skills, this free course is built for you.
Join the free course here: https://www.deeplearning.ai/short-courses/multimodal-rag-chat-with-videos
As a Software Tools Ecosystem Specialist at Intel, I’ve had the privilege of working on the dynamic GenAI initiative. My focus is on driving engagement with the software developer audience. I'm a proud team member of the Intel® Liftoff for Startups and the Developer Engagement, Relations, and Studio team.