robinkim

Storyteller. @Neo4j VP Comms. Also on Mastodon @[email protected]

[robinkim @robinkim]

https://t.co/t6xAfL9C5t

[Tracy Lee | ladyleet @ladyleet]

Loving seeing these @neo4j ladies at @aiDotEngineer! @NyahMacklinDev

[Emil Eifrem @emileifrem]

At the day 1 ending keynote @aiDotEngineer. Clearly @neo4j is binding @swyx and @gdb together!

[Sebastian Siemiatkowski @klarnaseb]

Yes, we did shut down Salesforce a year ago, as we have many SaaS providers—an internal estimate is about 1,200 SaaS shut down.

Not the end of Salesforce; might be the opposite.

Here is what actually happened and how/why we originally intended to NOT share it publicly:

[Emil Eifrem @emileifrem]

I've re-read this tweet a couple of times today. 🚀💪😍

[Eric Ries @ericries]

In this episode of The Eric Ries Show, I’m joined by @emileifrem, Co-Founder and CEO of @neo4j, an open-source graph database. Neo4j enables organizations to unlock the business value of connections, influences, and relationships in data.

In our conversation today, we talk about the following topics:
🔵 The origin story of Neo4j and why they chose open source
🔵 Open source as a means of production vs. distribution
🔵 How open source fosters trust and transparency
🔵 The pros and cons of doing business in the US
🔵 Why Neo4j updated their values and changed their stance on military contracts
🔵 What a Leader’s Guide is and how it keeps companies tied to their mission
🔵 The challenges of implementing AI
🔵 An explanation of RAG information retrieval and how it relates to LLMs
🔵 And more!

You can listen to or watch the episode here:

🎥 YouTube: https://t.co/zjQDc63CQJ
🎙️ Spotify: https://t.co/7D9aHiFUZu
🎙️ Apple: https://t.co/0O7JnKP6FN

[Jerry Liu @jerryjliu0]

Build a knowledge graph agent from scratch 🔥

I'm super excited about this blog post by Tomaz Bratanic from @neo4j - this is probably the most thorough treatment I've seen for building a text-to-cypher powered knowledge graph agent that actually works well.

Tomaz walks through an entire list of potential strategies and evaluates them according to a standardized benchmark:

1. Naive text-to-cypher
2. Text-to-cypher with retry and evaluation
3. Iterative planning system by generating a plan of sub-queries before creating the final query.

All of these can be stitched together as an event-driven system with @llama_index workflows.

Check out the post! https://t.co/n86ikA0Uti

If you want to get your hands dirty on workflows check out our guide here: https://t.co/tNolgSm48v

[Emil Eifrem @emileifrem]

So happy and proud to work with Klarna to power their internal knowledge chatbot Kiki and to build their AI platform of the future.

We work with AI teams across the globe to build systems to marry LLMs and Knowledge Graphs, and the Klarna team is absolutely world class. There's a reason they are the canonical example of *real* ROI for AI, and they're only getting started.

Here's to a graphy, LLM-y future! 🚀

[Sebastian Siemiatkowski @klarnaseb]

Spännande @emileifrem och @neo4j

Klarna är stolta kunder till Neo4j som är fantastiska och nödvändiga i AI tider.

Också kul att få stötta varandra, 🇸🇪 bolag emellan!

Kanske dags för bättre och billigare betalningar på @Spotify?
hint hint @eldsjal 😉

https://t.co/tqJEyZaa37

[Jim Webber @jimwebber]

My collaborator @profjsg from @iSchoolSU and I are proposing a panel at @SXSW 2025 on election disinformation in social networks. It'll be a cool mix of tech and computational sociology.

Upvote us here: https://t.co/PdrYfyqszK

[Harrison Chase @hwchase17]

Plan for this weekend: dive into GraphRAG a bit more. Two new things I want to explore:

👨‍💻 Implementation of Microsoft's GraphRAG paper from @tb_tomaz: https://t.co/e4yRxzSYih

📃"The GraphRAG Manifesto" - a high detailed piece on GraphRAG from @neo4j: https://t.co/iM8j6GM5Vg

[Yohei @yoheinakajima]

@hwchase17 @tb_tomaz @neo4j GraphRAG is so hot right now

[Emil Eifrem @emileifrem]

My friend and Neo4j CTO @prathle has written an outstanding blog post that summarizes the recent buzz around GraphRAG, what we've learned from a year of helping users build systems with Knowledge Graphs + LLMs and where we believe the space is going.

Thread below. 👇🧵

[robinkim @robinkim]

GraphRAG ftw.

[Neo4j @neo4j]

"GraphRAG will subsume vector-only RAG and emerge as the default RAG architecture for most use cases."

@prathle explores the powerful impact of #GraphRAG—the combination of knowledge graphs + RAG - in "The GraphRAG Manifesto.” 👇 👇
https://t.co/dGijt3korH

[robinkim @robinkim]

@prathle @bigdata Great #graphrag convo @bigdata @prathle + secret events ftw

[Neo4j @neo4j]

Knowledge Graphs in combination with vector search:

1. Higher accuracy
2.Easier development
3.Increase Explainability and governance

Look at that beautiful #knowledgegraph at the end of @emileifrem’s presentation ❤️ at @aiDotEngineer

Come to our booth at #AIEWF to learn more about #GraphRAG or visit
https://t.co/Pkwvmz24c6

[robinkim @robinkim]

“LLMs need knowledge graphs if we’re to move from GenAI experiment to production” @prathle @neo4j @CollisionHQ #graphRAG #knowledgegraph + #RAG

[robinkim @robinkim]

Why computational journalism matters: @margarettalev @SyracuseU @axios on uncovering misinformation in deeply connected data to get to the truth w/ @Isikoff @cbcsteve @CBCNews @mobocks @TorontoStar @CollisionHQ #collisionconf

[robinkim @robinkim]

At the forefront of investigative journalism, research, data + tech & a highlight at @CollisionHQ: @profjsg @margarettalev @SyracuseU @iSchoolSU @axios @Isikoff @cbcsteve @CBCNews @mobocks @TorontoStar

[robinkim @robinkim]

Backstage at @CollisionHQ with @neo4j keynoter @prathle along with @WebSummit’s freakishly awesome Brendan Garrett who saves our bacon all the time #collisionconf #genai #graphrag ftw