An open source, production grade vector search engine

Bob van Luijt on why a growing number of organizations use vector search engines.


SubscribeApple • Spotify • Stitcher • Google • AntennaPod • Podcast Addict • RSS.

Bob van Luijt, is CEO of SeMI Technologies, the company behind the popular vector search engine Weaviate.  Weaviate has integrations for OpenAI, Huggingface Inference, and very shortly for Cohere and other tools popular with developers. While vector databases are used for recommendation, anomaly detection, and Q&A systems, they primarily target search and information retrieval applications.

#E4EEF7;">Subscribe to the Gradient Flow Newsletter.

This episode is a great introduction to the growing importance of vector databases and vector search engines. Bob describes their key features and core components, popular use cases, and he also provides an overview of Weaviate’s near-term roadmap. We also discuss how vector search engines compare with existing data management systems.

Figure: Weaviate’s search pipeline (with re-ranking). Image by SeMI Technologies, used with permission.

Highlights in the video version:

 

Related content:


If you enjoyed this episode, please support our work by encouraging your friends and colleagues to subscribe to our newsletter:



[Image: What is a vector search engine?; by SeMI Technologies, used with permission.]