From surviving to thriving with GenAI in production: Lessons to successfully scale your data layer

Join Elastic and Unstructured to learn the best practices for scaling high-quality GenAI applications fueled by your proprietary document data.

Watch this webinar

Speakers

Nina Lopatina

Developer Relations Engineer, Unstructured

Amy Ghate

Solutions Architect, Elastic

Date of recording

Tuesday, February 25th

Overview

Great GenAI apps need tons of your unstructured data delivered in clean, canonical JSON. How you choose to build and manage your data layer is massively consequential to the success of your app, the efficiency of your team, and your stress level.

Done well, your data layer isn’t something you spend a lot of time thinking about. Grab data from wherever it lives, in any format, and clean JSON goes wherever your devs need it: aggregations, filters, RBAC tools, and BM25 or vector search. Done poorly, your data layer can become a rat's nest that saps your best engineering talent and keeps you up at night.

Technical Details

Watch this hands-on tutorial from engineering leaders at Unstructured and Elastic to help you build better GenAI data systems for your users. You'll learn:

How to build streamlined ETL pipelines for your unstructured GenAI data
Parsing and chunking strategies that balance good/fast/affordable for your most complex documents
How to parse and search all your unstructured documents once data is within Elastic
Connecting your data to your downstream RAG application or training pipelines.

You'll see a code-level demo with step-by-step instructions to scale the value of your internal data. The recording includes live Q&A with our leaders.

Watch this hands-on tutorial from engineering leaders at Unstructured and Elastic to help you build better GenAI data systems for your users. You'll learn:

How to build streamlined ETL pipelines for your unstructured GenAI data
Parsing and chunking strategies that balance good/fast/affordable for your most complex documents
How to parse and search all your unstructured documents once data is within Elastic
Connecting your data to your downstream RAG application or training pipelines.

You'll see a code-level demo with step-by-step instructions to scale the value of your internal data. The recording includes live Q&A with our leaders.

Watch this hands-on tutorial from engineering leaders at Unstructured and Elastic to help you build better GenAI data systems for your users. You'll learn:

How to build streamlined ETL pipelines for your unstructured GenAI data
Parsing and chunking strategies that balance good/fast/affordable for your most complex documents
How to parse and search all your unstructured documents once data is within Elastic
Connecting your data to your downstream RAG application or training pipelines.

You'll see a code-level demo with step-by-step instructions to scale the value of your internal data. The recording includes live Q&A with our leaders.