talk-data.com

In this talk, we will make the case that the success of enterprise AI depends on an investment in semantics and knowledge, not just data. Our LLM Accuracy benchmark research provided evidence that by layering semantic layers/knowledge graphs on enterprise SQL databases increases the accuracy of LLMs at least 4X for question answering. This work has been reproduced and validated by many others, including dbt labs. It's fantastic that semantics and knowledge are getting the attention it deserves. We need more.

This talk is targeted to 1) those who believe AI accuracy can be improved by simply adding more data to fine-tune/train models, and 2) the believers in semantics and knowledge who need help getting executive buy-in.

We will dive into: - the knowledge engineering work that needs to be done - who should be leading this work (hint: analytics engineers) - what companies lose by not doing this knowledge engineering work

Speaker: Juan Sequeda Principal Scientist and Head of AI Lab data.world

Read the blog to learn about the latest dbt Cloud features announced at Coalesce, designed to help organizations embrace analytics best practices at scale https://www.getdbt.com/blog/coalesce-2024-product-announcements

Juan Sequeda is a principal data scientist and head of the AI Lab at data.world, and is also the co-host of the fantastic data podcast Catalog and Cocktails.  This episode tackles semantics, semantic web, Juan's research in how raw text-to-SQL performs versus text-to-semantic layer,  and where we both believe AI will make an impact in the world of structured data analytics. For full show notes and to read 6+ years of back issues of the podcast's companion newsletter, head to https://roundup.getdbt.com. The Analytics Engineering Podcast is sponsored by dbt Labs.

Summary

The data ecosystem has seen a constant flurry of activity for the past several years, and it shows no signs of slowing down. With all of the products, techniques, and buzzwords being discussed it can be easy to be overcome by the hype. In this episode Juan Sequeda and Tim Gasper from data.world share their views on the core principles that you can use to ground your work and avoid getting caught in the hype cycles.

Announcements

Hello and welcome to the Data Engineering Podcast, the show about modern data management When you're ready to build your next pipeline, or want to test out the projects you hear about on the show, you'll need somewhere to deploy it, so check out our friends at Linode. With their new managed database service you can launch a production ready MySQL, Postgres, or MongoDB cluster in minutes, with automated backups, 40 Gbps connections from your application hosts, and high throughput SSDs. Go to dataengineeringpodcast.com/linode today and get a $100 credit to launch a database, create a Kubernetes cluster, or take advantage of all of their other services. And don't forget to thank them for their continued support of this show! Modern data teams are dealing with a lot of complexity in their data pipelines and analytical code. Monitoring data quality, tracing incidents, and testing changes can be daunting and often takes hours to days or even weeks. By the time errors have made their way into production, it’s often too late and damage is done. Datafold built automated regression testing to help data and analytics engineers deal with data quality in their pull requests. Datafold shows how a change in SQL code affects your data, both on a statistical level and down to individual rows and values before it gets merged to production. No more shipping and praying, you can now know exactly what will change in your database! Datafold integrates with all major data warehouses as well as frameworks such as Airflow & dbt and seamlessly plugs into CI workflows. Visit dataengineeringpodcast.com/datafold today to book a demo with Datafold. RudderStack helps you build a customer data platform on your warehouse or data lake. Instead of trapping data in a black box, they enable you to easily collect customer data from the entire stack and build an identity graph on your warehouse, giving you full visibility and control. Their SDKs make event streaming from any app or website easy, and their extensive library of integrations enable you to automatically send data to hundreds of downstream tools. Sign up free at dataengineeringpodcast.com/rudder Build Data Pipelines. Not DAGs. That’s the spirit behind Upsolver SQLake, a new self-service data pipeline platform that lets you build batch and streaming pipelines without falling into the black hole of DAG-based orchestration. All you do is write a query in SQL to declare your transformation, and SQLake will turn it into a continuous pipeline that scales to petabytes and delivers up to the minute fresh data. SQLake supports a broad set of transformations, including high-cardinality joins, aggregations, upserts and window operations. Output data can be streamed into a data lake for query engines like Presto, Trino or Spark SQL, a data warehouse like Snowflake or Redshift., or any other destination you choose. Pricing for SQLake is simple. You pay $99 per terabyte ingested into your data lake using SQLake, and run unlimited transformation pipelines for free. That way data engineers and data users can process to their heart’s content without worrying about their cloud bill. For data engineering podcast listeners, we’re offering a 30 day trial with unlimited data, so go to dataengineeringpodcast.com/upsolver today and see for yourself how to avoid DAG hell. Your host is Tobias Macey and today I'm interviewing Juan Sequeda and Tim Gasper about their views on the role of the data mesh paradigm for driving re-assessment of the foundational principles of data systems