Exploring Retrieval-Augmented Generation (RAG) and Vector Databases Enhancing AI with Advanced Information Retrieval
June 5 @ 7:00 pm - 8:30 pm
About the panelist:
Devang Parekh is a Software Engineer at FIYGE Research in Toronto, with expertise in Backend Development and Applied Machine Learning. He has driven innovative projects at FIYGE, leveraging his technical skills to build robust solutions. Previously, Devang mentored students as a CS Club Mentor at the University of Waterloo, enhancing a passion for technology. As a proud Waterloonian, he is dedicated to mentoring aspiring engineers and advancing the tech community through knowledge-sharing and <a href="http://collaboration.
[event” target=”_blank” title=”collaboration.
[event”>collaboration.
[event details]
This event will introduce participants to Retrieval-Augmented Generation (RAG) and Vector Databases, emphasizing their roles in enhancing AI-driven applications such as agentic applications, text generation, and search, as well as enabling autonomous systems. The session will blend theoretical explanations with live demonstrations, ensuring attendees gain both a conceptual understanding and practical <a href="http://exposure.
By” target=”_blank” title=”exposure.
By”>exposure.
By the end of this session, participants will:
– Understand the fundamentals of RAG and its importance in AI <a href="http://applications.
-” target=”_blank” title=”applications.
-“>applications.
– Learn about vector databases and how they enhance search and retrieval <a href="http://efficiency.
-” target=”_blank” title=”efficiency.
-“>efficiency.
– See real-world applications of RAG and vector search in NLP and AI <a href="http://systems.
-” target=”_blank” title=”systems.
-“>systems.
– Explore visualization tools such as TensorFlow Embedding Projector to understand <a href="http://vectorization.
-” target=”_blank” title=”vectorization.
-“>vectorization.
– Gain hands-on insights into implementing RAG with vector databases like Chroma or <a href="http://Pinecone.
Session” target=”_blank” title=”Pinecone.
Session”>Pinecone.
Session Breakdown:
– Introduction to RAG
– What is Retrieval-Augmented Generation (RAG)?
– How does it improve AI models?
– Use cases in Targeted Text Generation, Agentic Applications, Deep <a href="http://Search.
-” target=”_blank” title=”Search.
-“>Search.
– Fundamentals of Vector Databases
– What are vector databases?
– How do they differ from traditional databases?
– Brief on Langchain
– Key vector database technologies (ChromaDB).
– How Vectorization Works
– Explanation of embeddings and <a href="http://vectorization.
-” target=”_blank” title=”vectorization.
-“>vectorization.
– Demonstration using TensorFlow Embedding <a href="http://Projector.
-” target=”_blank” title=”Projector.
-“>Projector.
– Understanding cosine similarity and nearest neighbor <a href="http://search.
-” target=”_blank” title=”search.
-“>search.
– Implementing RAG with Vector Databases
– Overview of integration: LLMs + Vector <a href="http://Databases.
-” target=”_blank” title=”Databases.
-“>Databases.
– Simple implementation walkthrough (Python, OpenAI API + ChromaDB).
– Performance considerations and best <a href="http://practices.
-” target=”_blank” title=”practices.
-“>practices.
– Q&A and Closing Remarks
Co-sponsored by: Angelina Ziesemer