Supercharge Your RAG with Contextualized Late Interactions

[@engineerprompt]

If you are interested in leanring more about Advanced RAG Course, signup here: tally.so/r/3y9bb0

[@qwertyntarantino1937]

that's definitely a hot topic

[@JosephCardwell]

by 51 seconds we have the most direct explanation of embedding on youtube.

[@hl236]

Thanks for this. There is a lot of obsession over LLMs but I RAG has huge room for innovation that will multiply the performance of ai applications.

[@engineerprompt]

I agree, I am personally really interested in RAG and see that as the main application that will assist people in their workflows before we see anything else

[@maxlgemeinderat9202]

nice! Yes another video which uses this in langchain would be cool!

[@hl236]

Yes please!

[@TeamDman]

Thank you for the great walkthroughs and insights! RAGatouille interface looks great, can't wait to mess around with it

[@engineerprompt]

thanks, have fun :)

[@yusufersayyem7242]

Go Ahead Sir..... ❤

[@engineerprompt]

thank you :)

[@henkhbit5748]

Thanks, would like to see a combination of colbert and langchain optimal chunking method.

[@nirmalthacker8566]

me too please

[@mowlanicabilla5002]

Thanks for the clear and concise explanation.! What metrics can be used to evaluate the output of these models.?

[@PoGGiE06]

Super interesting. I want to use dspy with ragatouille/colbert2 for embedding and retrieval. I’d like to use llama index with a different vectordb, e.g. chromadb, pinecone, or qdrant. I want to use ollama with llama 3 to then summarise my retrieved rag data, and combine with some basic analysis of my own dataset. How feasible is that now? I assume that i can use dspy to finetrain on my specific analysis cases if necessary.

[@youngchrisyang]

Great content, thanks! Also curious what tool did you use to come up with such beautiful graphs on the "blackboard"

[@engineerprompt]

I use excalidraw.com

[@borisrusev9474]

So what's the disadvantage of using CoBERTv2? Or are you saying it's strictly better?

[@engineerprompt]

At the moment, the number of vectors store supports are limited, I think only FAISS supports that. You will need a GPU to run this. In THEORY, it should perform better than dense retrieval but probably need better evals.

[@LoveWorldamineK]

yes please make the next video with RAG and integrate it and also please can you create for us a video tutorial demonstrating how to build a chatbot that inputs in XLS or CSV format, prompts the user for input, and provides charts as output. using OPENAI API

[@utkarshtripathi9118]

Hii have you figured out solutions for this ??

[@LoveWorldamineK]

@@utkarshtripathi9118 Still m working on it

[@sohelshaikhh]

Nicely explained! also, wanted to know about time comparision between embedding retrievers and colBERT

[@engineerprompt]

From my experience, colBERT is usually faster.

[@VenkatesanVenkat-fd4hg]

Can you discuss newly pdf handling with tables & docx files parser....

[@THE-AI_INSIDER]

Please make a video on Rag with a UI where input is a file pdf or csv + Colbert behind the scenes

[@engineerprompt]

will do!

[@shubhamvijayvargiya4119]

Please make a video on how to handle dynamic tabular data in pdf to feed in llm and query on tables data, as tables structure gets messed up when creating vectors.

[@JMai-ci9nl]

Thanks for the video and sharing, I can't seem to pass the loader.load_data("Orca_paper.pdf") line in the colab notebook. The load_data call complains about 'str' has no 'name' attribute.

[@JMai-ci9nl]

fixed, you need documents = loader.load_data(pathlib.Path("Orca_paper.pdf")), the load_data expects a Path object, not str.

[@JMai-ci9nl]

BTW, the load_data() method by default parses the pdf page by page into multiple documents, in case you are wondering like I do.

[@VenkatesanVenkat-fd4hg]

Can you discuss on tables in Pdf files for RAG & other .docx files loader as pdf parser but some os there......

[@jaysonp9426]

Wait for the second example you used GPT4 for embeddings instead of ada? Did I miss something?

[@engineerprompt]

Its the tokenizer not the LLM. Probably can replace that with tiktoken package to get tokens.

[@sanoussabarry4218]

Gread job !!

[@dheerajsai236]

Whenever I am doing Rag.search ,I am getting the name of the document in contents rather than answers for the query . how do I solve it ? Please kindly help

[@AdamTwardoch]

@engineerprompt Is there a reason why you design your videos so that they must be viewed on a large screen? The font used on the diagram slides is obviously completely unreadable on a phone.

[@shameekm2146]

Thank you so much for this... :). I deal with large number of documents. I find dense retrieval is very bad at it. Let me check this approach and comment back.

[@engineerprompt]

Please do share your experience. Would love to see what you find.

[@ShreyasVaishnav]

How can we use this with Chroma ?

[@Abdoana]

So We can try this with local gpt?

[@nicholasdudfield8610]

Nice!

[@utkarshtripathi9118]

Please bring next video fast

[@mohsenghafari7652]

hi. please help me. how to create custom model from many pdfs in Persian language? tank you.

[@aghast666]

As I dive into the world of storytelling and creative expression, VideoGPT emerged as my trusted ally, subtly enhancing the quality of my videos without stealing the spotlight.