Abstract: 

Generative models have demonstrated how helpful they can be on general knowledge, helping students on their writing assignments. But as soon as you want to run it in a professional setting with prompts like ""what are the three main feature requests from our largest customers?"", they demonstrate their lack of knowledge.

In this session, I will introduce how Large Language Models (LLMs) can be connected to your data via semantic search. As I will present, there are many pitfalls and challenges. Some can be solved, when using the right technologies, others are still open problems.

Learning objectives:
- Understanding Retrieval + Generation
- Semantic Search with Embeddings
- Short comings and pitfalls with semantic search: What works, what doesn't work

Bio: 

Nils Reimers is an NLP / Deep Learning researcher with extensive experience on representing text in dense vector spaces and how to use them for various applications. During his research career, he created sentence-transformers that were the foundation for many today's semantic search applications.

In 2022, Nils joined Cohere.com to lead the team on smarter semantic search technologies and how to connect LLMs to enterprise data. Here, his teams develop new foundation models that can understand and reason over complex data.