วีดีโอ

Is there any idea to approach building a multi-modal graph rag? Where we need to retrieve the available relevant visual information along with the textual answer for creating more trust on the system from the users side?

Love her presentation, the potential of Graph RAG, and DiffBot. My project perfectly fits with this application!!

What open source project are you running on your local host? I’m digging the network graph that looks so cool.

are you a pure bred asian, there seems to be something european about your face

4:49 “When you clearly get a source which is not a hallucinated one 😂. very informative and entertaining as well

Thanks for the video . Entertaining and knowledgeable 😂

how does bm25 help with ranking the words excellent, good, decent, and numer like 50, 100, 150 or 150-100=50? I thought the video would discuss that

Hi, I liked the video and the explanations, I wouldve liked it to show more visuals about the topic instead of the presenters face tho

Can You make a search engine with this?

Waiting for the next videp. I enjoyed the format.

wait...I think I am in love...

Poland mentioned

Great explanation! I have a questions: KG requires a strict structure, such as node, link and attribute, which depends on target domain and questions. How can we alleviate it?

epic chinese video

BM25 doesn't do anything to address any of the issues you bring up at the beginning of the video. TF IDF is dumber than vector search in every aspect. It's just much cheaper to run. Not saying it doesn't have value as part of the toolkit but not sure why you spend the first half setting all thes problems with vector search up as if BM25 addresses any of them.

This is something Anthropic has shared with their contextual retrieval.

Thank you for delving into this important topic!

I believe a vector search is still better for rag applications. Bm25 is better for more literal matches. Also what does this have to do with LLMs doing math?

Wonderful explanation. Thank you.

Great overview, thank you!

Why don’t we include semantic dimensions in vectors

Otima exemplificacao de como word2vec não é a solucao definitiva.

super

This is so easy to understand, thank you!

before i thought the issue was a combo between input and output tokens, and figured llms just ommitted vital info because their output was constrained, now i know finding vital info is an issue also with rag. interpretation systems, thanks

this is an amazing explanation. im an instant follower

But vs is enough to scam dummies and create a market bubble.

Nice discussion, thanks! I wish there was more structure to the video so the “why” of the title I served as a main dish, ie let’s define the terms up front, explain how each works, then do why discussion and give a teaser for hybrid approach discussion. Instead there are some gaps and jumps around, which leaves it feeling incomplete or maybe not quite capturing the essence? I have a feeling this is partly a result of editing many clips, so don’t take this feedback too seriously. Cheers

BM25. Frequency-weighted by sponsored-definition-tag vector search. Yeah google search do that too, you know. If you ever did seo optimization for your website or some kind of smm you know that it works

What is DIffbot and how can we use it?

thanks this was great!

Oh man you are amazing!! Love channel I subscribed. Please do a video on working with such graphs using a vector database

Great explanation. Thank you so much!

Try tokenizing engendered languages 😂

Contributed 3blue1brown

i love this bot...

Golden nugget

thats insightful, thank you so much boss

Great video. This is why when building a search engine- I like to use BM25 for sparse search, and use Vector based search later, once most of the corpus has been filtered out. This allows me to stay precise and efficient. One additional thing- people often assume that you need a Vector Db for vector search, but you can do completely without. Just store the vectors in a normal DB.

would it work w/ ollama / local models?

Thanks, guys, YT recommended me this video, a very pleasant snippet of explanation. Trying to work through your website to understand what the service is.

Excellent presentation/explanation. Very useful. Thank you!

TURN YOUR VOLUME UP

Excuse me, but your volume is just too low. Just saying.

Thanks for the explanation, was super clear. We just planning to move from vector search to hybrid, and your explanation on BM25 helps a lot to understand what edge cases it can solve. Appreciate a lot! Guess we will see a surge on BM25 due to Anthropic Contextual retrieval paper .

The mathematics behind chatGPT is amazing

Oh no, this is going to make texts like I do!!! ok, drama aside, I do believe this will improve things a lot. I still see some caveats that would be left for luck, but huges amount of data might overcome that. I do believe we already have enough with GPT and a few previous ideas, still improving the language model itself is always a plus.

Nice video. I’ve been on the opposite side of the coin, but I like hearing the balanced argument to keep me educated

Great video! This is one of the most misunderstood concepts. Will def share this next time it comes up!

"diffbotgraphtransformer" to extract entities and build their relationships... then i see "diffbot-token / -api-key"... well, i just finished doing that with an "open-weights" LLM (i think... currently verifying that) 😎