Semantic Query Engines with Matthew Russo - Weaviate Podcast #131!

Matthew Russo is a Ph.D. student at MIT where he is researching the intersection of AI and Database Systems. AI is transforming Database Systems. Perhaps the biggest impact so far has been natural language to query language translations, or Text-to-SQL. However, another massive innovation is brewing. AI presents new Semantic Operators for our query languages. For example, we are all familiar with the WHERE filter. Now we have AI_WHERE, in which an LLM or another AI model computes the filter value without needing it to be already available in the database! `SELECT * FROM podcasts AI_WHERE “Text-to-SQL” in topics` Semantic Filters are just the tip of iceberg, the roster of Semantic Operators further includes Semantic Joins, Map, Rank, Classify, Groupby, and Aggregation! And it doesn’t stop there! One of the core ideas for Relational Algebra and how its influenced Database Systems is query planning and finding the optimal order to apply filters. For example, let’s say you have two filters, the car is red and the car is a BMW. Now let’s say the dataset only contains 100 BMW, but 50,000 red cars!! Applying the BMW filter first will limit the size of the set for the next filter! So many interesting nuggets in this podcast, loved discussing these things with Matthew, and I hope you find it interesting! Links: Palmipzest (GitHub): https://github.com/mitdbg/palimpzest A Declarative System for Optimizing AI Workloads: https://arxiv.org/abs/2405.14696 Abacus: A Cost-Based Optimizer for Semantic Operator Systems: https://arxiv.org/abs/2505.14661 Semantic Operators: A Declarative Model for Rich, AI-based Data Processing: https://arxiv.org/abs/2407.11418 SemBench: A Benchmark for Semantic Query Processing Engines: https://arxiv.org/abs/2511.01716 Chapters: 0:00 Welcome Matthew! 0:47 Semantic Query Processing Engines 7:07 Semantic Operators 13:57 Relational Algebra and Query Planning 18:19 Internal vs. External Query Engines 23:33 Semantic Joins 33:22 SemBench 42:07 Latency,