Sudhir Hasbe
@shasbe
Followers
1K
Following
2K
Media
68
Statuses
2K
Chief Product Officer @ Neo4j. ex-Google Sr. Director of Data Analytics Services.
Seattle, WA
Joined April 2008
Good readβ¦
Yes, we did shut down Salesforce a year ago, as we have many SaaS providersβan internal estimate is about 1,200 SaaS shut down. No, I don't think it is the end of Salesforce; might be the opposite. Here is what actually happened and how/why we originally intended to NOT share
1
0
5
It was fun talking to Sinan Ozdemir and Akshay Bhushan on why knowledge graphs are revolutionizing RAG and AI applications.
0
0
4
Our product vision: premium, trusted cloud native graph database platform. @shasbe at #GraphSummit Europe
1
2
10
What a fantastic way to end our #GraphSummit in NYC! #Neo4j on Times Square! π€©π @shasbe @emileifrem @steveonjava @chandrarangan
2
4
28
Super sad news. Huge loss to tech community. Life is too short. RIP Susan.
Unbelievably saddened by the loss of my dear friend @SusanWojcicki after two years of living with cancer. She is as core to the history of Google as anyone, and itβs hard to imagine the world without her. She was an incredible person, leader and friend who had a tremendous
0
0
2
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
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
1
12
63
Super excited to share our vision demo of ππ«ππ©π‘ ππ§ππ₯π²ππ’ππ¬ ππ¬ π ππππ offering powered by Microsoft Fabric and Neo4j. This should be ready for customers in coming months.
0
4
12
Wow. That's the power of graph + vector search compared to just vector search. Check out the screenshot below. Using relationships in your data is a RAG superpower.
2
6
19
Americas, are you ready?? Take a look at the agenda. #NODES2023 continuing livestream: @mesirii introducing Professor @FryRsquared, our keynote speaker and then, #Neo4j - Product Vision and Roadmap with @shasbe π΅ LIVE: https://t.co/ogxUf1DWhe
1
2
12
Panel discussion on Large language model training: tackling data challenges session at Google Cloud Next with Dr. Ali, Paroma Varma and Benjamin Flast.
0
1
9
Last week we announced support for Vector Search in Neo4j (including AuraDB). Here is a great article by Tomaz Bratanic on how you can use this from #langchain. https://t.co/9qu246rJJi
medium.com
Streamlining data ingestion and querying in Retrieval-Augmented Generation Applications
0
2
6
Super Excited to announce support for Vector Search in Neo4j database and available for our AuraDB customers to try for free. Now you can use Neo4j as long term memory for LLMs and leverage it for RAG based GenAI applications. https://t.co/2H7Vgaz1hi
0
4
14