Techno Pushy, sports fan, energy&relationship driven
Joined July 2012
- Tweets887
- Following230
- Followers182
- Likes316
Nicolas ROUYER retweeted
I'm so happy and proud of this new Aura Analytics offering. It's serverless and "pas as you go" (or prepaid if you want that) and it allows you to run sophisticated graph algos like pagerank, pathfinding, link predication on top of ANY enterprise data. Yes, even data outside a Neo4j database! Very cool stuff. Graph analytics for everyone!
We've got NEWS! 📣 #Neo4j Aura Graph Analytics is now LIVE!
Perform powerful graph analytics seamlessly on any cloud, any data platform, with zero ETL!
Are you ready to focus on innovation rather than implementation?
Here's how: bit.ly/4iSqAql
#GraphDatabase #GraphAnalytics
Nicolas ROUYER retweeted
🎊 The release of Neo4j 5.26 as our Long-Term Support (LTS) has arrived!
During these last years, Neo4j 5 has included:
🤩 Many features and enhancements across multiple dimensions
🤩 Performance and scalability
🤩 Operational capabilities
🤩 Security improvements
🤩 AI readiness
Take a look at these details and migrate to Neo4j 5.26 LTS! bit.ly/4hp93pk
#Neo4j #Neo4j5 #graphdatabase
Nicolas ROUYER retweeted
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 checking, retries and correction, and he has the benchmarks to prove it's a better strategy!
➡️ Implement agentic strategies for text2cypher using LlamaIndex Workflows
➡️ Explore multi-step approaches with retry and self-correction mechanisms
➡️ Understand the benefits of iterative planning for complex queries
➡️ Gain insights on benchmarking and real-world deployment considerations
Check out the full guest post on our blog here:
llamaindex.ai/blog/building-…
Nicolas ROUYER retweeted
Very cool to see this go live!
With the LangChain + @neo4j integration, you can now build GenAI apps on structured and unstructured data with their graph database. The LangChain-Neo4j partner package enables:
🔷 Unified retrieval with graph databases (vectors, docs, tables as nodes & edges)
🔷 Text-to-query generation via Cypher query language
🔷 Seamless chat memory storage to maintain context
Learn more: python.langchain.com/docs/in…
Nicolas ROUYER retweeted
📅 It's the 350th day of the year, time to celebrate the #A350!
Here are some Family Facts about the #LongRangeLeader:
✈️ Designed to fly up to 9700nm
🌍 Operated on +1250 routes
🌐 On +1.6M flights
Flying +420M passengers around the world in its beautiful #AirspaceCabin.
Nicolas ROUYER retweeted
🎊 Thrilled to announce a major milestone in #Neo4j: the general availability of Change Data Capture (CDC) in Aura Virtual Dedicated Cloud (Enterprise) and Neo4j Enterprise subscriptions and the Neo4j Connector for Confluent and Apache Kafka v5.1 with support for CDC.
Key features, uses and more:
bit.ly/3XIl9CW
Nicolas ROUYER retweeted
We are thrilled to announce a new partnership with @databricks
bit.ly/3xdewOC
Developers using the #Neo4j-#Databricks will now be allowed 👇
Nicolas ROUYER retweeted
Jerry said it really well. I think of it in two ways:
1. GraphRAG is a superset of vector-only RAG. It's not graphs INSTEAD OF vectors. It's graph AND vectors.
2. As an industry, we already converged on the best way to do Retrieval for the web. The key to a good R was graph algorithms (specifically PageRank). That innovation created a trillion dollar company.
a) Retrieve the relevant documents through keyword / vector search.
b) Rank them in the graph to get the "top ten blue links."
Vector-only RAG is Altavista. 🔍
GraphRAG is Google. 🚀
Graph RAG makes sense if you think about it as a superset of "standard" vector RAG:
1. Find an initial set of nodes via vector/keyword search
2. Augment context by traversing relationships
3. Augment context by also running other graph retrieval algorithms like text-to-cypher
4. Rerank all the context as a final pass
In this sense it's basically vector search with more context. The graph doesn't have to be complicated - just 1-2 levels deep from any text chunk. The end result is better retrieval and synthesis quality.
Building this yourself is easy in @llama_index, check out our guide here! docs.llamaindex.ai/en/stable…
Nicolas ROUYER retweeted
Ok, this is pretty crazy.
SQL has been the lingua franca of database querying since the dawn of time.
But for the first time in over three decades (!), ISO just published a NEW database query language called GQL -- the Graph Query Language!
Nicolas ROUYER retweeted
🎉 Announcing new integrations with @googlecloud and #VertexAI that solve critical challenges in #GenAI development! 🧵
bit.ly/4arOR2X
@gcloudpartners
Nicolas ROUYER retweeted
Thanks to @MGazanayi , the @Docker compose repository for the @neo4j SSO with @keycloak example is upgraded to KC20+ along with many improvements ! github.com/ikwattro/neo4j-ss…
Nicolas ROUYER retweeted
Just read this while reviewing a paper: "Allow the data model to evolve according to the needs of the domain, not the database."
This is such a pithy but incredibly important observation. This is why graph databases exist.
Nicolas ROUYER retweeted
Wow, in Jensen's keynote yesterday at #GTC24, he calls out three sources of data to integrate with LLMs: 1) vector databases, 2) ERP / CRM and 3) *knowledge graphs*!
There's this increasing realization that LLMs and Knowledge Graphs are match made in heaven. Higher accuracy, completeness of answer, explainability.
Left brain, right brain indeed.
neo4j.com/generativeai/
Nicolas ROUYER retweeted
Paris.. are you getting ready for #Kubecon??
We are so excited to meet you there!!! Come and visit us at Booth k36 to hear all about #Graphdatabases :)
#Kubernetes #cloudnative
@CloudNativeFdn #Neo4j #CloudNativeCon #KubeDay
Nicolas ROUYER retweeted
🤖JSON-based Agents With Ollama & LangChain
Learn to implement a Mixtral agent that interacts with a graph database Neo4j through a semantic layer
This work by @tb_tomaz is great for a few reasons:
- Shows how to build an agent with an OSS model
- Shows how to build and use a graph database
- Shows the power of creating a semantic layer over that graph database
Read his detailed blog here: medium.com/neo4j/json-based-…
Notebook: github.com/tomasonjo/blogs/b…
Template: github.com/langchain-ai/lang…
Nicolas ROUYER retweeted
Super excited to kickstart the Gen-AI hands-on workshop today at @Nasdaq with @neo4j and @ajeetsraina (@Docker and @collabnix ) 😀
Thanks @kitarp29 for hosting us! 🙌
Nicolas ROUYER retweeted
RDV bientôt au @KubeCon_ à Paris !
📅 19-22 Mars 2024
📍 Paris Expo Porte de Versailles
bit.ly/37JGiiT
#graphdatabases #neo4j
