Pune Developer's Community

Link to Live Stream:
TBD

Description: Vector similarity search allows developers to infuse AI into their applications using just a few lines of code, by leveraging vector embeddings generated thanks to state-of-the-art open source pre-trained neural networks such as SBERT, YOLO or CLIP.
These applications can be used with any type of data modality and can include use cases such as product recommendation engines, semantic search, sentiment analysis, and chatbots. In this talk, we'll discuss the opportunities provided by vector similarity search and share our experience and insights on the key considerations and tools
needed for successful deployment. We'll demonstrate how to apply these techniques through real-world examples and cover how to choose the right pre-trained deep learning model, generate vector embeddings, select the appropriate distance metric and nearest neighbor algorithm, define complex queries and scale vector databases for real-time applications.

Speaker: Nava Levy
About Her: Nava is a Developer Advocate for Data Science and MLOps at Redis. She started her career in tech with an R&D Unit in the IDF and later had the good fortune to work with and champion Cloud, Big Data, and DL/ML/AI technologies just as the wave of each of these was starting. Nava is also a mentor at the MassChallenge accelerator and the founder of LerGO—a cloud-based EdTech venture. In her free time she enjoys cycling, 4-ball juggling, and reading fantasy and sci-fi books.