Skip to content

Document ETL for RAG and Semantic Search with Elastic and Aryn DocParse

Photo of Elastic Meetup Team
Hosted By
Elastic Meetup T.
Document ETL for RAG and Semantic Search with Elastic and Aryn DocParse

Details

​​​Join us for a meetup with Elastic and Aryn at the AWS Gen AI Loft on Wednesday, December 11th. Doors open at 5:30 pm, followed by exciting presentations, refreshments, light bites, and networking.
​​
📅 Date & Time:
​Wednesday, December 11th, from 5:30-8:00pm PST

📍Location:
​​AWS Gen AI Loft - 525 Market St, San Francisco, CA 94105, USA. 2nd Floor Courtyard Entrance
​​
📝 Agenda:

  • ​​5:30 pm: Doors open
  • ​6:00 pm: Document ETL for RAG and Semantic Search with Aryn DocParse and Sycamore (Jonathan Fritz and Abhijit Pujare at Aryn)
  • ​​6:45 pm: Talk # 2 - Details coming soon! (Philipp Krenn at Elastic)
  • ​​8:00 pm: Event ends

🪧 Arrival Instructions:

  • ​When you arrive, if you reach the lobby entrance, go to the right if you’re facing the building, to the circular water fountain. You’ll see stairs lining the side of the building. Go up these stairs to enter the loft.
  • ​If a guest requires an accessible entrance (unable to use stairs), they will need to be escorted through the lobby of the building to the elevators. See any Amazon Employee or the reception desk for assistance.
  • ​A valid government-issued photo identification is required to enter the Loft. Due to the venue security policies, we are unable to make exceptions and will refuse entry to any person without a valid photo ID.​

💭 Talk Abstracts:

Document ETL for RAG and Semantic Search with Aryn DocParse and Sycamore (Jonathan Fritz – Chief Product Officer – at Aryn)
​It’s critical to properly prepare unstructured data when building RAG or semantic search applications with Elasticsearch. Creating the proper ETL pipelines with document segmentation, table and image extraction, OCR, data enrichment, data cleaning, and more is not trivial when dealing with complex data. In this session, we’ll show how to build advanced document ETL pipelines with the open source, scalable Sycamore library and use Aryn DocParse for critical processing steps.

Talk # 2 - Details coming soon!

​Are you interested in presenting at an upcoming Elastic meetup? We'd love to hear from you. Please reach out to [meetups@elastic.co](mailto:meetups@elastic.co).

Photo of Elastic San Francisco User Group group
Elastic San Francisco User Group
See more events
AWS Loft
525 Market St., 2nd Floor · San Francisco, ca