Some helpful updates from across Google this week, lots more to come! 🧵
@NotebookLM is introducing Cinematic Video Overviews for Ultra users in English.
Distill complex information into amazing visual deep dives - take a look 👇
@amazonIN I received garbage, broken , damaged totally different camera lens when ordered new Sony lens. Raised complaint with Amazon Support however I have been asked follow up instead of resolving issue.
Totally unexpected. @AmazonHelp
Companies like Microsoft are already hiring with 'vibe coding' as a requirement.
You can now add Lovable as a certification on LinkedIn, and it's ranked by how much you've used Lovable.
Build more great apps and get a higher certification!
🇮🇳 Good morning India! A lot of you asked for full-length mock JEE Main tests in @GeminiApp at no cost - done! Good luck on your prep!
Last week, SAT. This week, JEE.
What other global exams would be most helpful?
Helpful update for students, you can now take full practice SATs for free in the @GeminiApp.
It uses vetted content from @ThePrincetonRev and gives you feedback straight away. Starting with the SAT today, but more tests are on the way!
@SUBWAY@SubwayIndia Hiked prices, reduced size and portion , degraded hygiene and substandard quality . Anything else left behind … ? kind of subs get delivered now days is totally surprise, no veggies and no sauces just piece of bread and patty
RAG vs. Graph RAG, explained visually!
RAG has many issues.
For instance, imagine you want to summarize a biography, and each chapter of the document covers a specific accomplishment of a person (P).
This is difficult with naive RAG since it only retrieves the top-k relevant chunks, but this task needs the full context.
Graph RAG solves this.
The following visual depicts how it differs from naive RAG.
The core idea is to:
- Create a graph (entities & relationships) from documents.
- Traverse the graph during retrieval to fetch context.
- Pass the context to the LLM to get a response.
Let's see how Graph RAG solves the above problem.
First, a system (typically an LLM) will create a graph from documents.
This graph will have a subgraph for the person (P) where each accomplishment is one hop away from the entity node of P.
During summarization, the system can do a graph traversal to fetch all the relevant context related to P's accomplishments.
The entire context will help the LLM produce a complete answer, while naive RAG won't.
Graph RAG systems are also better than naive RAG systems because LLMs are inherently adept at reasoning with structured data.
👉 Over to you: Have you used Graph RAG in production?
People used make fun of Microsoft browser that it is only being used for downloading Google Chrome.
Today I am using Google Chrome to download Microsoft Edge.
#microsoftedge
@MyntraSupport@myntra complaint IN23053118064114933501 is pending since two weeks. Only response I get from support that I will get update in 24 hours.
#worst#service and no one has any idea.