![Loading Events](https://semiwiki.com/wp-content/plugins/the-events-calendar/src/resources/images/tribe-loading.gif)
Webinar: Optimizing Generative AI with Vector Databases: What, Why, and How
June 26 @ 10:00 AM - 11:00 AM
![Screenshot 2024 06 11 185519](https://semiwiki.com/wp-content/uploads/2024/06/Screenshot-2024-06-11-185519.png)
Vector databases have emerged as the preferred option for customizing generative AI and making it more trustworthy. Both dedicated vector DBs and vector-enabled DB suites deliver companies’ domain-specific data–most often text or imagery–to large language models. They help fine-tune models and enrich user prompts via retrieval-augmented generation (RAG). These use cases enable companies to customize their language models and better govern their inputs, reducing risks such as hallucinations, privacy breaches, and compliance issues.
Join this webinar to learn:
- What vector databases are and how they work
- Why domain-specific LLMs need vector databases
- How vector databases support model fine-tuning and RAG
- Requirements and best practices for successful implementation
Speakers
![](/wp-content/uploads/2024/06/7Ba4119bff-0e80-4936-97ec-987517ebdc557D_C-MKA-33977_T-MKA-39264-Kevin_Petrie.jpg)
Kevin Petrie
Vice President of Research at BARC
Hosts
![Ryan Carson](/wp-content/uploads/2024/06/7Bd3ca6cb4-c677-48cb-9eca-40b95156de9d7D_Ryan_Carson.png)
Ryan Carson
Senior AI Developer Community Lead, Intel Sales and Marketing Group
Intel and TSMC IDM 2024 Discussions