Jo Kristian Bergum presenting on using LLMs for training ranking models at Berlin Buzzwords 2023

Berlin Buzzwords 2023 has just finished and we thought it would be great to summarize the event. Berlin Buzzwords is Germany’s most exciting conference on storing, processing, streaming and searching large amounts of digital data, with a focus on open source software projects. This year, the conference was filled with exciting talks about Large Language Models (LLMs) and neural search techniques.

Boosting Ranking Performance with Minimal Supervision

Jo Kristian Bergum from the Vespa team gave a talk on Boosting Ranking Performance with Minimal Supervision.

Using generative Large Language Models (LLMs) to generate synthetic labeled data to train in-domain ranking models. Distilling the knowledge and power of generative LLMs into effective ranking models.

If you were interested in this talk, why don’t you check out some of our previous work on zero-shot ranking and adapting ranking models to new domains using LLMs:

• Improving Search Ranking with Few-Shot Prompting of LLMs
• Improving Zero-Shot Ranking with Vespa Hybrid Search
• Improving Zero-Shot Ranking with Vespa Hybrid Search - part two

In the context of ranking and retrieving context for LLMs we can also recommend:

• Minimizing LLM Distraction with Cross-Encoder Re-Ranking
• Vespa support in langchain

The Debate Returns (with more vectors): Which Search Engine?

Jo Kristian Bergum from the Vespa team joined a panel of search engine and vector search experts to discuss and contrast search technologies.

Privacy-Preserving Web Search

Lara Perinetti from Qwant.com gave a talk about building privacy preserving web search. Qwant uses Vespa for indexing and ranking 5B web documents.

Bar Camp at Berlin Buzzwords 2023

Berlin Buzzword’s Barcamp is an informal session with a schedule decided on the day. This session was not recorded.

Tom Gilke from otto.de (see their Tech Blog), Germany’s second largest e-commerce site, presented on using Vespa for search suggestions.

Tom Gilke from Otto.de presenting at Berlin Buzzwords 2023.

Tom Gilke presented on introducing semantic search suggestions using Vespa nearest neighbor search combined with Vespa’s embedding inference capabilities.

We also recommend a talk on how the otto.de team migrated their infrastructure for powering search suggestions. They present their iterations moving from Elasticsearch to a simple python solution and in the end to Vespa in How we built the autosuggest infrastructure for otto.de.

Learning to hybrid search

Roman Grebennikov and Vsevolod Goloviznin presented on hybrid search ranking alternatives, all evaluated on the Amazon’s ESCI product ranking dataset.

We at the Vespa team have also worked with this large e-commerce ranking dataset in our blog series on Improving Product Search with Learning to Rank:

• Part one: introduction to ESCI product ranking dataset
• Part two: neural methods
• Part three: GBDT methods (hybrid)

Vectorize Your Open Source Search Engine

In this talk, Atita Arora gave a talk on vector search using bi-encoders that maps queries and documents into a latent embedding vector space and perform similarity search using nearest neighbor search.

Atita Arora from Open Source Connections presenting at Berlin Buzzwords 2023.

One key takeaway from the talk was a relevance evaluation breakdown by query type intent, where we clearly can see that vector search alone does not solve all search use cases.

The state of Neural Search and LLMs, interview with Jo Kristian Bergum - Berlin Buzzwords 2023

Jo Kristian Bergum from the Vespa team joined Founder and CEO Jakub Zavrel at Zeta Alpha to talk about the state of Neural Search and LLMs.

Hybrid search is buzzing

This year, the conference was filled with talks on hybrid search and we think it’s worthwile mentioning Lester Solbakken’s great talk from Berlin Buzzwords 2022 where he presented Hybrid search > sum of its parts?

Summary

Berlin Buzzwords is a highly regarded industry conference that brings together experts and professionals from various fields to discuss the latest trends and advancements in storage, processing, streaming, and search. One noticeable aspect of the 2023 edition was the significant emphasis on search-related topics, LLMs role in search, and neural hybrid search.

If you are interested to learn more about Vespa; See Vespa Cloud - getting started, or self-serve Vespa - getting started. Got questions? Join the Vespa community in Vespa Slack.