Weaviate Podcast

Weaviate Podcast #18. Thank you for watching the 18th Weaviate Podcast with Vincent D. Warmerdam! Vincent is an engineer at Spacy working on exciting tools such as Prodigy! Vincent describes how nearest neighbor search can aid in tasks such as Data De-Duplication and Data Labeling! Vincent shared many interesting ideas from representations of text, challenges with annotator disagreement, lessons from hosting data labeling workshops to train data scientists, and many more!

Weaviate Podcast #17. Thank you for watching the 17th Weaviate Podcast with Kyle Lo! Vector Search enables us to find semantically similar items in large collections. Scientific Literature Mining is an extremely interesting case of this where we search through enormous collections of scientific papers to find evidence and ideas. Kyle has an extremely impressive resume in this application domain, tackling tasks such as Question Answering, Summarization, Fact Verification, and more! We really hope you enjoy the lessons Kyle describes from building these systems. Further, we hope that this inspires excitement in your own Vector Search applications!

Weaviate Podcast #16. ANN Benchmarks are a tool for evaluating the performance of in-memory approximate nearest neighbor algorithms. Etienne Dilocker, the CTO of SeMI Technologies, the company behind Weaviate shares some insight knowledge about this interesting topic.

Weaviate Podcast #15. Weaviate is used as a database for Jina AI's Neural Search Framework. In this podcast, Maximilian Werk, Engineering Director at Jina AI, will talk about all things related to this neural search framework together with Connor Shorten. Also, Maximilian will give a Jina Example Walkthrough... Enjoy!!

Weaviate Podcast #14. Thanks for watching the Weaviate podcast! Our 14th episode welcomes Yi-Lin Sung, Jaemin Cho, and Professor Mohit Bansal, a research team from UNC! Our guests present their work on VL Adapter, a technique to achieve full fine-tuning performance while only updating 4% of original parameters!! This is an incredibly interesting finding for the sake of cost-effective tuning of Vision and Language models based on CLIP. We additionally discussed topics around compression bottlenecks in neural architectures, V&L datasets, and the tricky question of compositional generalization. If you are curious about using CLIP in Weaviate, please check out this text-to-image search example with Unsplash images and a React frontend!

Weaviate Podcast #13. Rick Lamers, CEO, and Founder of Orchest.io. Orchest is a tool targeted at data scientists and this software simplifies building data pipelines.

Weaviate Podcast #12. Please check out Composer from MosaicML! https://github.com/mosaicml/composer Jonathan Frankle is the Chief Scientist at MosaicML and a PhD student in Machine Learning at MIT. Jonathan is the first author of “The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks” which won an ICLR best paper award. You can learn more about Jonathan Frankle here: http://www.jfrankle.com/.  Here is an explanation of how to use the Python library of Composer: https://www.youtube.com/watch?v=Xi_5w...

Weaviate Podcast #11. You can now use Weaviate as the document store for DocumentArray in Jina AI. We had the pleasure to talk with their CEO Han Xiao. See the timestamps below what it is all about, or check out the recap from Henry AI!

Weaviate Podcast #10. A guided conversation about HNSW by Connor Shorten between Yury Malkov, Staff ML Engineer at Twitter and the co-inventor of HNSW, and Etienne Dilocker, the co-founder of Weaviate. Check the timestamps below!

Weaviate Podcast #9. Karen Beckers, Data Scientist from Squadra Machine Learning Company, gives insightful information about how to use vector search in eCommerce in this podcast with Connor Shorten. Some topics are image-based datasets, vector search for data scientists, the future of eCommerce, and many more! See the timestamps below for more information.