Embeddings, vector databases and LLMs | Elastic & Hopsworks

Join us for a meetup on November 8th!
We are excited to host this meetup at Hopsworks' Stockholm Office for the occasion of the PyCon Sweden Conference in the same week.

Doors open at 17:30 and the presentations begin around 18.00.
Food, refreshments, and networking to follow. We wrap up around 20.30.

Address: Hopsworks - Åsögatan 119, Plan 2, 116 24 Stockholm
(Directions: 2-minute walk from Medborgarplatsen)

Agenda:
17:30 - 18:00: Doors open
18:00 - 18:10: Welcome
18:10 - 18:40: Intro to Embeddings and Vector Search
18:40 - 19:10: Pizza & Refreshments
19:10 - 19:40: Vector Databases and Beyond for RAG LLMs
19:40 - 20:30: Networking

Talks:

Intro to Embeddings and Vector Search
Iulia Feroli - Elastic

This talk will give an introduction to the foundational topics within Natural Language Processing that constitute the building blocks for LLMs and technologies like chatGPT. We will discuss word embeddings and vectorization, as well as explore practical applications for these. The talk will include a demo of vector search using Elastic (and the Harry Potter books).

Speaker Bio:
Iulia is a developer advocate at Elastic, focusing on the data science and AI side of the community. She has a background in data science and wrote her bachelor's thesis on Topic Modelling; after which she's worked in different areas of IT such as cloud architecture and technical selling.

Vector Databases and Beyond for RAG LLMs
Javier de la Rúa Martínez - Hopsworks

Retrieval-augmented generation (RAG) for large language models (LLMs) aims to improve prediction quality by using an external datastore at inference time to build a richer prompt that includes some combination of context, history, and recent/relevant knowledge.
In this talk, we will introduce how two different datastores can be used for RAG - Vector Databases that retrieve documents related to the input prompt - and Feature Stores that can retrieve enterprise data through application-supplied information, such as a user-id or booking reference number.

Speaker Bio:
Javier is a Research Engineer at Hopsworks where he actively contributes to advancing the Hopsworks Feature Store platform. He is currently pursuing his Ph.D. at KTH Royal Institute of Technology in Sweden with a primary focus on large-scale machine learning systems.

More info:

Tickets: Sign up required. Anyone who is not on the list will not get in. The event is free of charge.

Capacity: Space is limited to 100 participants. If you are signed up but unable to attend, please change your RSVP by November 7th.

Food and drinks: Pizza and drinks will be provided. If you have any food allergies please contact the meetup organizers.