Supercharge Your RAG with Contextualized Late Interactions

Поділитися
Вставка
  • Опубліковано 21 лис 2024

КОМЕНТАРІ • 48

  • @engineerprompt
    @engineerprompt  8 місяців тому +4

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

  • @JosephCardwell
    @JosephCardwell 8 місяців тому +6

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

  • @hl236
    @hl236 8 місяців тому +3

    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
      @engineerprompt  8 місяців тому +3

      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
    @maxlgemeinderat9202 8 місяців тому +2

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

    • @hl236
      @hl236 8 місяців тому

      Yes please!

  • @henkhbit5748
    @henkhbit5748 8 місяців тому +1

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

  • @LoveWorldamineK
    @LoveWorldamineK 8 місяців тому +3

    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
      @utkarshtripathi9118 8 місяців тому

      Hii have you figured out solutions for this ??

    • @LoveWorldamineK
      @LoveWorldamineK 8 місяців тому

      @@utkarshtripathi9118 Still m working on it

  • @TeamDman
    @TeamDman 8 місяців тому

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

  • @sohelshaikhh
    @sohelshaikhh 8 місяців тому

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

    • @engineerprompt
      @engineerprompt  8 місяців тому

      From my experience, colBERT is usually faster.

  • @mowlanicabilla5002
    @mowlanicabilla5002 7 місяців тому

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

  • @shameekm2146
    @shameekm2146 8 місяців тому

    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
      @engineerprompt  8 місяців тому

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

  • @THE-AI_INSIDER
    @THE-AI_INSIDER 8 місяців тому +2

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

  • @shubhamvijayvargiya4119
    @shubhamvijayvargiya4119 7 місяців тому

    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.

  • @borisrusev9474
    @borisrusev9474 8 місяців тому +2

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

    • @engineerprompt
      @engineerprompt  8 місяців тому +2

      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.

  • @PoGGiE06
    @PoGGiE06 6 місяців тому

    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.

  • @VenkatesanVenkat-fd4hg
    @VenkatesanVenkat-fd4hg 8 місяців тому

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

  • @youngchrisyang
    @youngchrisyang 5 місяців тому

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

  • @yusufersayyem7242
    @yusufersayyem7242 8 місяців тому

    Go Ahead Sir..... ❤

  • @jaysonp9426
    @jaysonp9426 8 місяців тому

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

    • @engineerprompt
      @engineerprompt  8 місяців тому +1

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

  • @aghast666
    @aghast666 8 місяців тому

    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.

  • @dheerajsai236
    @dheerajsai236 5 місяців тому

    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

  • @JMai-ci9nl
    @JMai-ci9nl 8 місяців тому

    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
      @JMai-ci9nl 8 місяців тому

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

    • @JMai-ci9nl
      @JMai-ci9nl 8 місяців тому

      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
    @VenkatesanVenkat-fd4hg 8 місяців тому

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

  • @AdamTwardoch
    @AdamTwardoch 7 місяців тому

    @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.

  • @ShreyasVaishnav
    @ShreyasVaishnav 6 місяців тому

    How can we use this with Chroma ?

  • @Abdoana
    @Abdoana 8 місяців тому

    So We can try this with local gpt?

  • @sanoussabarry4218
    @sanoussabarry4218 8 місяців тому

    Gread job !!

  • @utkarshtripathi9118
    @utkarshtripathi9118 8 місяців тому

    Please bring next video fast

  • @mohsenghafari7652
    @mohsenghafari7652 8 місяців тому

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

  • @nicholasdudfield8610
    @nicholasdudfield8610 8 місяців тому

    Nice!