What we’re about
At DFW Data Science, we strive to be a catalyst for a Data Driven culture for Enterprises in DFW Area. We commit to learn and help others learn how to deliver solutions with a data-first approach.
Our topics range from core Data Science concepts to applying these concepts at Enterprise scale for various industry verticals. So, whether you are looking to get into the Data Science field, or want to keep in touch with the latest developments in the rapidly evolving pace, this meetup is right for you.
Our goal is to meet once a month, come rain or shine. For now, it is the first Monday of the month. Regardless if the event is actually stated on the calendar.
With our Enterprise outreach program, we have taken our meetup crowd into companies local to DFW including USAA, Capital One, Toyota Connected. If you are an enterprise and want to host the event, please feel free to reach out to us.
Howdy Experimenters!
It's been a while since our last event, and DFW Data Science is excited to resume its talks with a "double feature." We will host two sessions: the first led by Jon Handler (Senior Principal Solutions Architect at AWS / OpenSearch), followed by a second session with Trey Grainger (Founder at Searchkernel, author of the brand new AI-Powered Search book). If you like open source search and analytics or ever search and visualize your logs on AWS, you may already be familiar with Jon's work on the OpenSearch project. Some of you may remember Trey from his previous visit, where he discussed The Apache Solr Smart Data Ecosystem. As moderators, we are thrilled to restart our speaker series with these two accomplished individuals and hope you find their talks as engaging as we anticipate.
Some Items To Consider:
- Seating is limited to 80 (hard limit)
- Food and Drink will be provided.
- All Attendees MUST provide first name, last name, and email a week prior to the event. Send your email to scottccote@gmail.com with subject line "AI-Powered Search + OpenSearch"
- All visitors will be required to present a current government issued picture ID before entering the Amazon office.
As stated earlier, seating is limited. Therefore, if you do not provide the required attendance information, then we will give your slot to the next person on the list with complete identification. We will send a confirmation message on May 10th.
Make sure you are ready to have a great time....
Session 1:
Title: OpenSearch - open-source search engine, log analytics, and vector database
Presenter: Jon Handler, Senior Principal Solutions Architect, AWS
Abstract: OpenSearch is a search, analytics, and vectors suite that lives in the databases world. You send your search documents to OpenSearch, and OpenSearch indexes your content. Its rich query APIs give you the search tools you need to find the right information. Its aggregations make it easy to analyze log data to provide real-time monitoring for your application, infrastructure, and business. Its vector capabilities bring you sparse and dense vector search for hybrid search, and as a knowledge base for retrieval-augmented generation. In this session, you’ll learn the basics of OpenSearch, and how to employ it to monitor your infrastructure, power your website search, and use the latest AIML technologies.
Bio: Jon Handler is Director of Solutions Architecture at AWS, working with the OpenSearch Project and providing help and guidance to a broad range of OpenSearch users. Prior to joining AWS, he worked on a large-scale e-commerce search engine. Jon holds a Master of Science and PhD in computer science and artificial intelligence from Northwestern University.
https://opensearch.org/community/members/jon-handler.html
Session 2:
Title: AI-Powered Search: A survey of modern retrieval and ranking algorithms
Presenter: Trey Grainger, Author of AI-Powered Search, Founder @ Searchkernel
Abstract: Search engines (including vector databases) are critical components of modern AI systems. Retrieval Augmented Generation (RAG) is the key design pattern used to provide generative AI systems with the relevant context needed to prevent hallucination, but the “R” in RAG is both the hardest to implement and least-well-understood aspect of these systems. For example, doing retrieval (aka “search”) well requires a solid understanding of knowledge representations (knowledge graphs, sparse vector representations, dense vector embeddings, etc.), relevance and ranking algorithms, and how to interpret query and click streams to power reflected intelligence approaches for personalization, signals boosting of most relevant items, and training machine-learned ranking models.
Leveraging code examples from his latest book, Trey will walk through key concepts and AI-powered search algorithms you’ll want to understand to implement relevant, data-driven retrieval well. We’ll cover different approaches for semantic search (query expansion vs. embeddings), quantization methods for optimizing recall versus performance, multimodal search, matrix factorization, and both hybrid and multimodal search. Whether you’re implementing a user-facing search application, trying to improve the quality of your generative AI outputs, or just interested in learning more about this fascinating area of data science, you’ll walk away from this talk with a broader understanding of modern retrieval and ranking techniques and how you can plug them into your own applications.
Bio: Trey Grainger is lead author of the book AI-Powered Search (Manning 2025) and the Founder of Searchkernel, a software consultancy building the next generation of AI-powered search. He previously served as CTO of Presearch, a decentralized web search engine, and as Chief Algorithms Officer and SVP of Engineering at Lucidworks, an AI-powered search company whose search technology powers hundreds of the world’s leading organizations. Trey is also co-author of the book Solr in Action (Manning 2014), as well as over a dozen other publications including books, journals, and research papers. Trey has 18 years of experience in search and data science, including significant work developing semantic search, personalization and recommendation systems, and building self-learning search platforms leveraging content and behavior-based reflected intelligence.
Upcoming events (1)
See all- AI-Powered Search + OpenSearchDFW11, Dallas, TX
Howdy Experimenters!
It's been a while since our last event, and DFW Data Science is excited to resume its talks with a "double feature." We will host two sessions: the first led by Jon Handler (Senior Principal Solutions Architect at AWS / OpenSearch), followed by a second session with Trey Grainger (Founder at Searchkernel, author of the brand new AI-Powered Search book). If you like open source search and analytics or ever search and visualize your logs on AWS, you may already be familiar with Jon's work on the OpenSearch project. Some of you may remember Trey from his previous visit, where he discussed The Apache Solr Smart Data Ecosystem. As moderators, we are thrilled to restart our speaker series with these two accomplished individuals and hope you find their talks as engaging as we anticipate.
Some Items To Consider:
- Seating is limited to 80 (hard limit)
- Food and Drink will be provided.
- All Attendees MUST provide first name, last name, and email a week prior to the event. Send your email to scottccote@gmail.com with subject line "AI-Powered Search + OpenSearch"
- All visitors will be required to present a current government issued picture ID before entering the Amazon office.
As stated earlier, seating is limited. Therefore, if you do not provide the required attendance information, then we will give your slot to the next person on the list with complete identification. We will send a confirmation message on May 10th.
Make sure you are ready to have a great time....
Session 1:
Title: OpenSearch - open-source search engine, log analytics, and vector database
Presenter: Jon Handler, Senior Principal Solutions Architect, AWSAbstract: OpenSearch is a search, analytics, and vectors suite that lives in the databases world. You send your search documents to OpenSearch, and OpenSearch indexes your content. Its rich query APIs give you the search tools you need to find the right information. Its aggregations make it easy to analyze log data to provide real-time monitoring for your application, infrastructure, and business. Its vector capabilities bring you sparse and dense vector search for hybrid search, and as a knowledge base for retrieval-augmented generation. In this session, you’ll learn the basics of OpenSearch, and how to employ it to monitor your infrastructure, power your website search, and use the latest AIML technologies.
Bio: Jon Handler is Director of Solutions Architecture at AWS, working with the OpenSearch Project and providing help and guidance to a broad range of OpenSearch users. Prior to joining AWS, he worked on a large-scale e-commerce search engine. Jon holds a Master of Science and PhD in computer science and artificial intelligence from Northwestern University.
https://opensearch.org/community/members/jon-handler.html
Session 2:
Title: AI-Powered Search: A survey of modern retrieval and ranking algorithms
Presenter: Trey Grainger, Author of AI-Powered Search, Founder @ SearchkernelAbstract: Search engines (including vector databases) are critical components of modern AI systems. Retrieval Augmented Generation (RAG) is the key design pattern used to provide generative AI systems with the relevant context needed to prevent hallucination, but the “R” in RAG is both the hardest to implement and least-well-understood aspect of these systems. For example, doing retrieval (aka “search”) well requires a solid understanding of knowledge representations (knowledge graphs, sparse vector representations, dense vector embeddings, etc.), relevance and ranking algorithms, and how to interpret query and click streams to power reflected intelligence approaches for personalization, signals boosting of most relevant items, and training machine-learned ranking models.
Leveraging code examples from his latest book, Trey will walk through key concepts and AI-powered search algorithms you’ll want to understand to implement relevant, data-driven retrieval well. We’ll cover different approaches for semantic search (query expansion vs. embeddings), quantization methods for optimizing recall versus performance, multimodal search, matrix factorization, and both hybrid and multimodal search. Whether you’re implementing a user-facing search application, trying to improve the quality of your generative AI outputs, or just interested in learning more about this fascinating area of data science, you’ll walk away from this talk with a broader understanding of modern retrieval and ranking techniques and how you can plug them into your own applications.
Bio: Trey Grainger is lead author of the book AI-Powered Search (Manning 2025) and the Founder of Searchkernel, a software consultancy building the next generation of AI-powered search. He previously served as CTO of Presearch, a decentralized web search engine, and as Chief Algorithms Officer and SVP of Engineering at Lucidworks, an AI-powered search company whose search technology powers hundreds of the world’s leading organizations. Trey is also co-author of the book Solr in Action (Manning 2014), as well as over a dozen other publications including books, journals, and research papers. Trey has 18 years of experience in search and data science, including significant work developing semantic search, personalization and recommendation systems, and building self-learning search platforms leveraging content and behavior-based reflected intelligence.
