Qdrant Spacewalk @ AWS: What's the Best Embedding Model for Your RAG Application?
Spacewalk Event
Please note that attendees require a photo ID to enter the venue.
The Qdrant team, in cooperation with AWS, invites you to our first Spacewalk event at the AWS AI Engineering Loft where we will discuss how to choose the right embedding model for your AI application.
Qdrant is an industry-leading vector database and a semantic search engine, powering large operations such as Twitter, Discord, Firefox, Tripadvisor, Johnson & Johnson, Deloitte, and more.
Agenda:
5:00 - Doors Open
5:30-6:00 - Networking + Food
6:00-6:45 - Presentation from Thierry Damiba
6:45-7:00 - Q&A
7:00-7:30 - Networking
Learning Objectives:
Demystify the process of selecting and using embedding models for text data in RAG applications.
Teach participants how to improve the performance of their GenAI apps.
Attendees should leave with an understanding of which embedding models work best for their use case.
Key Topics:
RAG, RAG, RAG:
Understanding the basics and importance of RAG in AI applications.
Data Preparation:
Best practices for preparing data, chunking, and embedding.
Choosing the Right Embedding Models:
Identifying the challenges and common misconceptions.
Evaluating different embedding models and their suitability for RAG use cases.
Deconstructing the Black Box:
Techniques to analyze and understand how embedding models operate internally.
Methods to select the best model tailored to specific needs.
Target Audience: This event is designed for machine learning practitioners, data scientists, and AI enthusiasts who are either building AI apps or curious to learn how.
Presenter:
Thierry Damiba, Developer Advocate & Data Scientist