Philip Rathle
@prathle
Followers
2K
Following
988
Media
118
Statuses
1K
CTO @ Neo4j. Helping the world to connect all-of-the dots.
San Francisco, CA
Joined June 2009
@latentspacepod @dharmesh @emileifrem @DMRadioOnline @neo4j 11/ We are all nodes in a massive, massive graph! So true!!
0
0
3
@latentspacepod @dharmesh @emileifrem @DMRadioOnline @neo4j 10/ Besides PageRank, one of my favorite graph algorithms is https://t.co/K2xbmAgN99 It’s a great way to resolve anonymous user breadcrumbs into a pseudonymous single identity.
1
0
3
@latentspacepod @dharmesh @emileifrem @DMRadioOnline 9/ @dharmesh: I’m pretty sure that NodeRank-the-company could be built with 3 lines of code atop @neo4j but we can definitely talk about that! :-) https://t.co/GyxmCb7l8s
1
0
0
@latentspacepod @dharmesh @emileifrem @DMRadioOnline 8/ It’s possible to get graph schema wrong. For sure. Getting it right becomes more important as you scale, just like RDBMS schema. https://t.co/6gETdKDnqC
graphacademy.neo4j.com
Learn how to design a Neo4j graph using best practices
1
0
1
@latentspacepod @dharmesh @emileifrem @DMRadioOnline 7/ Performance at scale as a big reason people use graph databases like Neo4j. Agree. Equally valuable for AI is being able to incrementally evolve your schema rather than have to decide on it ahead of time: https://t.co/3OF6jOZqnN
graphable.ai
While graph databases like Neo4j are schemaless by default, leverage the power of schemas in development by focusing on application driven graph schema design
1
0
0
@latentspacepod @dharmesh @emileifrem @DMRadioOnline 6/ You can try this yourself! https://t.co/7w31KA4Qhv
1
1
2
@latentspacepod @dharmesh @emileifrem @DMRadioOnline 5/ Graphs as a better representation for structured data in general. Agree. They can also bridge in unstructured data and relate the two. I mention this here in my “GraphRAG Manifesto”: https://t.co/DPT986iYfR Bonus concept: a “lexical graph” captures vector-document
1
0
7
@latentspacepod @dharmesh @emileifrem 4/ I heard from Data^2 today that one of their customers who is in production recently saved $27M thanks to GraphRAG. We’ll be drilling into this next week with @DMRadioOnline. You can register for this here: https://t.co/RKzOTaNplr Expect a tl;dr on graph databases and
us02web.zoom.us
The surge of Large Language Models continues to reshape traditional business processes, offering great promise for automating previously challenging, time-intensive creative activities. But what part...
1
0
1
1
0
2
@latentspacepod @dharmesh 2/ Real-world examples of GraphRAG: The most prominent to hit the airwaves lately is Klarna:
2
0
4
@latentspacepod @dharmesh 1/ Graphs as a better representation for LLM and AI: AI needs to represent the world, which shows up largely in networks and hierarchies. Graphs are the natural way to represent these.
1
0
6
Today’s @latentspacepod with @dharmesh is *of course* an awesome listen: https://t.co/YAZFLjIVt4 A thread expanding on the graph database portion the discussion 🧵:
latent.space
Dharmesh Shah on Intelligent Agents, Market Inefficiencies, and Building the Next AI Marketplace
2
9
50
Klarna’s AI journey is rooted in the power of graphs. I agree with Sebastian that the value of Neo4j/knowledge graphs/GraphRAG is in the top line. It’s not about replacing SaaS, but bringing data from the many silos into a graph, and using that for better AI decisions.
1
4
7
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
Dramatically improve the accuracy of your knowledge graph applications by applying agentic strategies with LlamaIndex workflows! In this comprehensive post by Tomaz Bratanic of @neo4j, he builds up slowly from a naive text2cypher implementation to an agentic approach with error
9
46
258
GraphRAG with @MistralAI, @CamelAIOrg, and @neo4j: - Use Mistral Large 2 to extract and structure knowledge graph from a given content source, and store this information in a Neo4j graph database. - A hybrid approach: combining vector retrieval and knowledge graph retrieval,
2
37
209
🔍 Exploring GraphRAG with Neo4j and LangChain 📝 Check out Tomaz Bratanic's deep dive into "From Local to Global" GraphRAG implementation Covers how to extract entities & relationships from text and summarize graph structures into natural language. https://t.co/sSYCRqSO2p
3
56
201
This weekend, we’re providing a definitive set of tutorials on how to build GraphRAG, step-by-step. First, check out this video by @fahdmirza on implementing the core components of GraphRAG using an in-memory implementation: 1. Extract entities and relationships using LLMs 2.
10
99
388
Microsoft GraphRAG Alternative and 10x Cheaper? 🚀 Introducing Sciphi/Triplex 💸 10x Cheaper 🤖 AI Knowledge Graph Extraction 🌟 Higher Accuracy 🛠️ Setup with @huggingface 🖥️ Local Run with @ollama 📊 Data Visualisation @neo4j Subscribe: https://t.co/RTY3pSVFGl
@sayshrey
3
37
154
If you’re looking for a conversation about GraphRAG to go alongside the GraphRAG Manifesto, look no further than my conversation with Ben Lorica on the Data Exchange podcast:
thedataexchange.media
Neo4j’s Philip Rathle on the Rise of GraphRAG and GQL.
0
16
52
0
0
3