Apache Pig

**Agenda :** * 4.30 to 4.45 PM ET: Food and Networking * 4.45 to 5.30 PM ET: "Practical Applications of Model Context Protocol (MCP) (Feb 2026 Edition)" Hello Everyone! Please join us for our Feb 10th edition of the AI-ML MeetUp. **Please note this is an in-person meeting and light refreshments/food will be provided.** **Title:** Practical Applications of Model Context Protocol (MCP) (Feb 2026 Edition) **Description:** This session explores how the Model Context Protocol (MCP) can be used to connect AI models with real-world tools and data. Attendees will learn practical patterns for implementing MCP in production workflows and applications. Through examples and use cases, the session highlights how MCP enables more capable, context-aware AI systems. **Location:** The meeting will be hosted in the Applied Information Sciences ( AIS ) office in Reston, at 11440 Commerce Park Dr # 600 · Reston, VA. The location is also right off the Silver Line metro's Wiehle-Reston Metro Station. **Parking:** Parking is paid and can be validated at the AIS office reception. We will meet in Room Lake Anne. We hope to see you all there!!!!

IMPORTANT PLEASE RSVP @ https://www.meetup.com/washington-dc-elastic-fantastics/events/312487028/?eventOrigin=group_upcoming_events \*\*\* **Date and Time:** Tuesday, February, 10th from 5:30-7:30 pm EDT **Location:** Elastic Arlington Office - 4100 Fairfax Drive, Ste 500, Arlington, VA 22203 **Agenda:** * 5:30 pm: Doors open; say hi, grab a seat, and eat some food. * 6:00 pm: "Streaming Context: Powering Semantic Search with Kafka and Elasticsearch", by Sandon Jacobs, Developer Advocate at Confluent * 6:30 pm: Q&A * 6:40 pm: "Agent Builder: Providing Relevant Context for Data Driven Agents", by Joe Gentsch, Senior Solutions Architect at Elastic * 7:10 pm: Q&A * 7:20-7:30 pm: Networking & refreshments **Talk Abstracts:** **"Streaming Context: Powering Semantic Search with Kafka and Elasticsearch"** As the de facto platform for event streaming, we’ve seen how data from Apache Kafka can easily empower basic keyword search. But let's be real, modern semantic search applications need *context* to interpret the real meaning and intent of a user's query. We could wait around for the next batch job to kick off and provide that context... *or* we could serve it up in near real-time right from our data streams. In this talk, we'll discuss how to leverage data streams from Kafka to power much smarter semantic search with Elasticsearch. We’ll follow a simple event from a Kafka topic and see how it transforms into a powerful vector embedding. Then, we’ll see this whole flow in action using a k-Nearest Neighbor search to instantly find similar items in milliseconds. While my code examples will be in Java or Kotlin using the Spring Boot and Spring AI ecosystem, FEAR NOT! The core concepts—getting data into a vector format via a stream—are totally language agnostic. Join us to grab a few practical ideas you can take and use in your next project! **"Agent Builder: Providing Relevant Context for Data Driven Agents"** What are agents? What is context engineering? Join us as we dive into the importance of context engineering for providing relevant information to agents, and how to build grounded agents using Elastic Agent Builder. **Parking:** * The building’s parking garage is operated by Colonial Parking and is located off N. Randolph Street * Book a spot on[ SpotHero](https://spothero.com/search?kind=address&latitude=38.8818514&longitude=-77.1095268&search_string=4100+Fairfax+Dr+%23500%2C+Arlington%2C+VA+22203%2C+USA) * A Metro Station is located across the street

**Title**: Powering AI Through Data Modernization: Modernizing ETL with Databricks & Unity Catalog In this session, we will discuss how enterprises are modernizing their data platforms by migrating from legacy ETL tools (such as Informatica and traditional data warehouses) to Databricks Lakehouse architecture, and how Unity Catalog enables enterprise-grade governance, security, and discoverability across data and AI assets. We will start with food and drinks at 6pm and then move into the presentation at 6:30pm. The session will cover: * Why traditional ETL platforms are becoming a bottleneck for scale, cost, and AI adoption * How Databricks changes the data engineering and analytics operating mode * The role of Unity Catalog in centralized governance * How this foundation enables AI and Gene.AI use cases on trusted data * Q&A Our speaker for this event is **Hirenkumar Dholariya**. Hirenkumar Dholariya is a Senior Data Engineering Architect with 18+ years of experience modernizing enterprise data platforms for global Fortune 500 organizations, delivering up to 40% system performance improvement and 20–35% infrastructure cost reduction through large-scale migration from legacy ETL platforms to cloud-native Lakehouse architectures. He specializes in Databricks-based data engineering, Unity Catalog–driven governance, and building scalable, secure, and real-time analytics platforms. He has led multiple enterprise-wide transformations from tools such as Informatica and traditional data warehouses to Databricks, establishing governed data foundations using Unity Catalog and enabling advanced analytics and AI use cases on top of trusted data platforms. His leadership focuses on architecting durable data platforms, enabling teams to move faster with confidence, and translating data and AI investments into measurable business outcomes. *

We’re excited to bring the community together for an evening of learning and connection. This time, we'll have a community member sharing a use case and, as usual, an Elastic employee sharing their expertise as well. Come support your fellow developers, learn something new, and meet others who are passionate about search, observability, and security. **Date and Time:** Tuesday, February, 10th from 5:30-7:30 pm EDT **Location:** Elastic Arlington Office - 4100 Fairfax Drive, Ste 500, Arlington, VA 22203 **Agenda:** * 5:30 pm: Doors open; say hi, grab a seat, and eat some food. * 6:00 pm: "Streaming Context: Powering Semantic Search with Kafka and Elasticsearch", by Sandon Jacobs, Developer Advocate at Confluent * 6:30 pm: Q&A * 6:40 pm: "Agent Builder: Providing Relevant Context for Data Driven Agents", by Joe Gentsch, Senior Solutions Architect at Elastic * 7:10 pm: Q&A * 7:20-7:30 pm: Networking & refreshments **Talk Abstracts:** **"Streaming Context: Powering Semantic Search with Kafka and Elasticsearch"** As the de facto platform for event streaming, we’ve seen how data from Apache Kafka can easily empower basic keyword search. But let's be real, modern semantic search applications need *context* to interpret the real meaning and intent of a user's query. We could wait around for the next batch job to kick off and provide that context... *or* we could serve it up in near real-time right from our data streams. In this talk, we'll discuss how to leverage data streams from Kafka to power much smarter semantic search with Elasticsearch. We’ll follow a simple event from a Kafka topic and see how it transforms into a powerful vector embedding. Then, we’ll see this whole flow in action using a k-Nearest Neighbor search to instantly find similar items in milliseconds. While my code examples will be in Java or Kotlin using the Spring Boot and Spring AI ecosystem, FEAR NOT! The core concepts—getting data into a vector format via a stream—are totally language agnostic. Join us to grab a few practical ideas you can take and use in your next project! **"Agent Builder: Providing Relevant Context for Data Driven Agents"** What are agents? What is context engineering? Join us as we dive into the importance of context engineering for providing relevant information to agents, and how to build grounded agents using Elastic Agent Builder. **Parking:** * The building’s parking garage is operated by Colonial Parking and is located off N. Randolph Street * Book a spot on[ SpotHero](https://spothero.com/search?kind=address&latitude=38.8818514&longitude=-77.1095268&search_string=4100+Fairfax+Dr+%23500%2C+Arlington%2C+VA+22203%2C+USA) * A Metro Station is located across the street

The next NoVABeerSec event - "Informal Gathering of Security Minds Over Beer'' will be Wednesday, February 25th, 5:30PM til 7ish at Crooked Run Fermentation (22455 Davis Drive, Sterling, VA ). **BONUS** there is a Senor Ramon Taqueria as part of the brewery; so it will be a “Taco Wednesday” for everyone ;) **Venue for February:** Crooked Run Fermentation (https://crookedrunfermentation.com/sterling-virginia-2/) - Crooked Run Fermentation is a Virginia-based producer of contemporary and traditional beers, coolship sours, natural wines, ciders, and seltzers. Started in 2013 in Leesburg, Virginia, Crooked Run has developed a following for creative and nuanced beverages across a variety of styles, from lagers to IPAs, barrel-aged stouts, sours, and beyond beer. In 2017, we opened our main production facility in Sterling, Virginia, and will open a third location in northeast DC in 2022. Opened in 2017, the Sterling location features a bustling taproom, outdoor biergarten, 10 BBL brewhouse, and best of all, TACOS! Senor Ramon Taqueria offers a full menu of tacos, quesadillas, empanadas, and more. Come relax with 12 beers on tap, weekend live music, and some great food! If you're biking, we're right off the W&OD Trail. **Additional Info:** We are an inclusive group, so if we missed anyone please let us know or if you want to bring your significant other/spouse please do. Have a great week and see you later this month! Cheers, Rinaldi Rampen & Mike McCabe of @NoVABeerSec

Join us for another session of our study group as we continue our coverage of the book Domain-Specific Small Language Models. In this session, we will Chapter 2 which is titled Tuning for a Specific Domain. This isn't just a lecture! Come ready to ask questions, share insights, and code along. Whether you're a beginner or have some experience, this is the perfect opportunity to continue to learn together. If you plan to work with the code on your own laptop during the session, try and download the code from here https://github.com/virtualramblas/Domain-Specific-Small-Language-Models/ ahead of time. We will be meeting at the University of North America in room 2215 for this event.