%20Verion%202.0.png?width=153&height=80&name=Stormatics%20Logo%20(Transparent)%20Verion%202.0.png "Stormatics Logo (Transparent) Verion 2.0")
Watch the Webinar
Do you work with large datasets and complex queries involving similarity searches for your PostgreSQL database? pgvector might be the missing link required for enhancing your application’s capabilities with AI.
Our in-house PostgreSQL Consultant, Semab Tariq, delivered an information-packed session on “pgvector: How to transform your search capabilities with AI”. Semab shared everything you need to maximize the performance of your queries using AI.
The webinar covered:
- Introduction of pgvector and different embedding models
- Perform searches based on the meaning of the words, not just the words themselves.
- Internal structure of indexes in pgvector
- Parallel index support for Hierarchical Navigable Small World (HNSW)
- Query execution time difference between non-indexed VS IVFFLAT VS HNSW Indexed queries
- Retrieval-Augmented Generation (RAG) to improve contextual understanding and enhance response quality
- pgvector real world use cases
About the Speaker
Semab Tariq
Semab is a PostgreSQL Consultant at Stormatics with a versatile background encompassing DevOps, Packaging, and ML models. He has a strong track record of driving innovation and optimizing PostgreSQL performance across diverse platforms.
Planning on optimizing your PostgreSQL database performance with AI? Book a call with us today for a free consultation!