Kristian Aune

Head of Customer Success, Vespa

17 Jun 2022

Lester Solbakken presenting at Berlin Buzzwords 2022

Berlin Buzzwords 2022 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.

AI-powered Semantic Search; A story of broken promises?

Jo Kristian Bergum from the Vespa team gave a talk on AI-powered Semantic Search; A story of broken promises?.

Semantic search using AI-powered vector embeddings of text, where relevancy is measured using a vector similarity function, has been a hot topic for the last few years. As a result, platforms and solutions for vector search have been springing up like mushrooms. Even traditional search engines like Elasticsearch and Apache Solr ride the semantic vector search wave and now support fast but approximative vector search, a building block for supporting AI-powered semantic search at scale.

Without doubt, sizeable pre-trained language models like BERT have revolutionized the state-of-the-art on data-rich text search relevancy datasets. However, the question search practitioners are asking themself is, do these models deliver on their promise of an improved search experience when applied to their domain? Furthermore, is semantic search the silver bullet which outcompetes traditional keyword-based search across many search use cases? This talk delves into these questions and demonstrates how these semantic models can dramatically fail to deliver their promise when used on unseen data in new domains.

If you were interested in this talk, why don’t you check out some of our previous work on state-of-the-art text ranking:

Also check out the Vespa MS Marco sample application
which demonstrates how to represent state-of-the-art ranking methods with Vespa.

See also our blog posts on Vector search:

Hybrid search > sum of its parts?

Lester Solbakken from the Vespa team gave a talk on Hybrid search > sum of its parts?.

Over the decades, information retrieval has been dominated by classical methods such as BM25. These lexical models are simple and effective yet vulnerable to vocabulary mismatch. With the introduction of pre-trained language models such as BERT and its relatives, deep retrieval models have achieved superior performance with their strong ability to capture semantic relationships. The downside is that training these deep models is computationally expensive, and suitable datasets are not always available for fine-tuning toward the target domain.

While deep retrieval models work best on domains close to what they have been trained on, lexical models are comparatively robust across datasets and domains. This suggests that lexical and deep models can complement each other, retrieving different sets of relevant results. But how can these results effectively be combined? And can we learn something from language models to learn new indexing methods? This talk will delve into both these approaches and exemplify when they work well and not so well. We will take a closer look at different strategies to combine them to get the best of both, even in zero-shot cases where we don’t have enough data to fine-tune the deep model.

Understanding Vespa with a Lucene mindset

Atita Arora from OpenSource connections gave a great talk on
Understanding Vespa with a Lucene mindset. Fantastic overview
of Vespa, Vespa’s strengths and how Vespa compares to Apache Lucene based search engines.

Vespa is no more a ‘new kid on the block’ in the domain of search and big data. Everyone is wooed over reading about its capabilities in search, recommendation, and machine-learned aspects augmenting search especially for large data-sets. With so many great features to offer and so less documentation to how to get started on Vespa , we want to take an opportunity to introduce it to the lucene based search users.
We will cover about Vespa architecture , getting started , leveraging advance features , important aspects all in the analogies easier for someone with a fresh or lucene based search engines mindset.

Matscholar: The search engine for materials science researchers

John Dagdelen from the department of materials science and engineering at UC Berkeley,
gave a insightful talk on Matscholar: The search engine for materials science researchers. This talk demonstrates how Vespa can be used to power advanced search use cases, including entity recognition,
embedding, grouping and aggregation.

Matscholar (Matscholar.com) is a scientific knowledge search engine for materials science researchers. We have indexed information about materials, their properties, and the applications they are used in for millions of materials by text mining the abstracts of more than 5 million materials science research papers. Using a combination of traditional and AI-based search technologies, our system extracts the key pieces of information and makes it possible for researchers to do queries that were previously impossible. Matscholar, which utilizes Vespa.ai and our own bespoke language models, greatly accelerates the speed at which energy and climate tech researchers can make breakthroughs and can even help them discover insights about materials and their properties that have gone unnoticed.

Summary

Berlin Buzzwords is a great industry conference, and the 2022 edition was no exception. Lots of interesting discussions, talks
and new friends and connections were made.

If you were inspired by the Vespa talks you can get started by the following Vespa sample applications:

• State-of-the-art text ranking:
  Vector search with AI-powered representations built on NLP Transformer models for candidate retrieval.
  The application has multi-vector representations for re-ranking, using Vespa’s phased retrieval and ranking
  pipelines. Furthermore, the application shows how embedding models, which map the text data to vector representation, can be
  deployed to Vespa for run-time inference during document and query processing.

• State-of-the-art image search: AI-powered multi-modal vector representations
  to retrieve images for a text query.

• State-of-the-art open-domain question answering: AI-powered vector representations
  to retrieve passages from Wikipedia, which are fed into an NLP reader model which extracts the answer. End-to-end represented using Vespa.

These are examples of applications built using AI-powered vector representations and where real-world deployments
need query-time constrained nearest neighbor search.

Vespa is available as a cloud service; see Vespa Cloud – getting started,
or self-serve Vespa – getting started.

Kristian Aune

Head of Customer Success, Vespa

23 Jun 2023

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:

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

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:

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 performs 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.