Kristian Aune

@abhi1thakur Looking forward to the deep tech sessions !

Let's make search great again 🚀 I'm joining Vespa ai and my role is to help you build a world class search, RAG and recommendation systems. In addition, I will be: 👨🏽‍💻 Taking part in open-source communities and contributions 👀 Creating tutorials to learn how to build search for real world problems 📈 Working with cross-functional teams to bring search from "good" to "great" for real users 👨🏽‍🎓 Learning and evolving: as always If you’re passionate about search, rag, embeddings, hybrid architectures, or you’re using (or exploring) Vespa ai and want to collaborate or chat, please reach out! Always happy to connect.

This is critical for applications with high-volume text content, both for text search and in hybrid / RAG applications

My talk in Atlanta is an intro to integrating Large Language Models (LLMs) to improve the quality of completing specific tasks without problems like hallucinations. Important tradeoffs are cost, latency, and quality - experiments based on the paper “In-Context Learning” or: How I learned to stop worrying and love “Applied Information Retrieval" from @UofGlasgow. Bonus: A sneak peek into using the same techniques with Visual Language Models - this is much more exciting than the LLMs, if possible! Using @vespaengine, it does not take much to get you going. I hope to see you today at @DataSciConnect! datasciconnect.com/events/collide…

@DmitryKan @UofGlasgow Sure! arxiv.org/pdf/2405.01116

@kraune @UofGlasgow Cool, can you share the link to the paper?

I am excited to hold a talk about In-Context Learning, with inspiration from the “In-Context Learning” or: How I learned to stop worrying and love “Applied Information Retrieval" paper from the @UofGlasgow! This is a promising way to integrate large language models to improve the quality of completing specific tasks without hallucinations. Also, getting started does not take much, particularly when using @vespaengine! Today, at @mlconference in Brooklyn, New York: mlconference.ai/machine-learni…

@BatAndrew314 @UofGlasgow Yes that is the plan :-)

@DanswerAI has been using @vespaengine as our search engine for a long time. In this blog, I outline the key benefits of using Vespa. Thanks @jonbratseth, @kraune and @jobergum for keeping Vespa open source and helping our users with Vespa questions! blog.vespa.ai/why-danswer-us…

@dtaivpp Your Vespa sticker is outdated! Let us send you one with the new logo

I may need help…

@jobergum @vespaengine Excited and looking forward to meeting with the French tech scene - hoping for many good questions and discussions!

If you are in Paris tonight, you should check out this meetup with @kraune from @vespaengine aicamp.ai/event/eventdet…

@minoru_osuka @vespaengine @jobergum @takatorisatoshi Thanks! Thanks to Stanby team too for a very thorough post!

Vespa Blogに弊社の検索エンジンをVespa (@vespaengine ) にマイグレーションした記事を寄稿しましたー。 @kraune @jobergum @takatorisatoshi Thank you for your cooperation! blog.vespa.ai/migrating-to-t…

It is so cool that @Stanby_inc , a leading job search service in Japan, has migrated to using @vespaengine : "Vespa was chosen as the unified search engine because it aligns well with the characteristics of Stanby’s search requirements": blog.vespa.ai/migrating-to-t…. Thanks to @takatorisatoshi and @minoru_osuka for writing this!

@srchvrs @lateinteraction @jobergum @vespaengine @Stanford @hackwithtrees @andreer 😂

@lateinteraction @jobergum @vespaengine @Stanford @hackwithtrees @andreer @kraune Are they joining a PhD, MS or just BS?

We are sending our most lovely @vespaengine people to the @Stanford @hackwithtrees this weekend, and as a bonus, they'll be in the Bay Area for the full week. Grab them and ask about representing the ColBERT model with Vespa @andreer @kraune treehacks.com

検索技術勉強会での弊社 (@Stanby_inc) 検索エンジニア @takatorisatoshi からの Vespa (@vespaengine) 移行の発表資料の元ネタ、Tech Blogの記事が公開されましたので、こちらも読んでいただけたらと思います。 techblog.stanby.co.jp/entry/vespa_mi… #searchtechjp

@vespaengine is hosting "AI in production systems + Embedding Recycling to Accelerate ML Inferencing" Nov 21, Trondheim Norway - see you there! meetup.com/trondheim-big-… #Meetup

The coolest feature in @vespaengine blog.vespa.ai/vespa-newslett… is the DFA used for way faster fuzzy queries! select * from music where myArtistAttribute contains ({maxEditDistance: 1}fuzzy("the weekend"))"

Super excited to be at 2023.trondheimdc.no to talk about "Using modern AI in production systems"! Great to have the conference back, with so many people - hope to be back next year!

@shinsuke_sugaya @johtani Would love to learn more about your experiences, so we can improve! Once upon a time we even started on github.com/vespa-engine/d… but we need someone to build it :-)

@johtani 学習コストが高い気もしますし、私もしばらくよくわからんなぁ…という状態でした。

Vespaもちょっとわかってきたので、何か作って、いろいろと試してみたい感じではある。

3/ Thanks to @dainius_jocas and his team for creating this, and try out some the examples added to the @vespaengine sample applications library at github.com/vespa-engine/s…

2/ As part of the Vespa migration work, the Vinted team contributed blog.vespa.ai/lucene-linguis… too! A strong example of the power of using open-source platforms and how teams can benefit from each other's work!

1/ vinted.com is an online marketplace for buying, selling and exchanging new or secondhand items, also named "The largest pre-loved fashion marketplace in the world". As a Vespa Team member, I was happy to read vinted.engineering/2023/10/09/ado…, but not only that!