What is Retrieval Augmented Generation (RAG) - Augmenting LLMs with a memory

Поділитися
Вставка
  • Опубліковано 26 гру 2024

КОМЕНТАРІ • 35

  • @WhatsAI
    @WhatsAI  2 місяці тому

    Get your copy of "Building LLMs for Production": amzn.to/4bqYU9b

  • @letseat3553
    @letseat3553 8 місяців тому +9

    RAG is just 'full text indexing' on the local data with the ranked results fed into the context window and sent to the LLM along with the question.
    Every time I see it described as something of a database guy for the last 30 years all I see are new words describing long solved problems.

    • @rajeshbasnet4454
      @rajeshbasnet4454 8 місяців тому +2

      You mean like how elastic search does indexing ?

    • @ahmedzouaoui8177
      @ahmedzouaoui8177 7 місяців тому

      Well new cars have wheels which is a technology that has thousands of years of existence. It does not mean that new cars are 'obsolete' but using an old tech to improve a new one is a great way of doing engineering !

  • @KEMBL
    @KEMBL 5 місяців тому

    What happens to the information received from the RAG if the original request already occupies the entire context window?

    • @WhatsAI
      @WhatsAI  5 місяців тому +1

      It depends on the code implementation of the system! Most will put in place a system to detect it and summarize or extract key points to make it shorter.

  • @finn_the_dog
    @finn_the_dog 11 місяців тому +4

    Great video. Would you make a video the different types of RAGs? Or how to prepare data for a RAG, for example when your document has tables, math formulas, references to images, I haven't seen much content about how to handle diverse data inside a document with RAGs.
    Cheers

    • @WhatsAI
      @WhatsAI  11 місяців тому +2

      Great idea, thank you! Will definitely look into multi modal RAG! :)

  • @MK-ce7im
    @MK-ce7im 9 місяців тому +2

    I think this is the best video I have seen on this topic. Wanted to ask if we can use RAG offline maybe with Mistral model ?

    • @WhatsAI
      @WhatsAI  9 місяців тому

      Of course you can host everything locally if you have the capacity! :)

  • @nealdriscoll22237
    @nealdriscoll22237 9 місяців тому

    by any chance do you know which RAG system/framework is giving out the best performance?

    • @WhatsAI
      @WhatsAI  9 місяців тому +1

      From our work we like to use llamaindex for many parts and adapt on our own code for more personalized settings!

  • @prattipatimanojsai
    @prattipatimanojsai 11 місяців тому +1

    Very Informative and useful!! Thanks

  • @rhans6598
    @rhans6598 10 місяців тому

    Thanks but what's the point of sound effects?

  • @Parsley1965
    @Parsley1965 11 місяців тому +4

    Truly excellent video!

  • @smritisrinivas7885
    @smritisrinivas7885 6 місяців тому +1

    Wow. Thanks a lot for this amazing explanation

  • @bhanujinaidu
    @bhanujinaidu 8 місяців тому +2

    Thanks , very clear excellent explanation

    • @WhatsAI
      @WhatsAI  8 місяців тому

      Thank you! :)

  • @PriM-z2k
    @PriM-z2k 11 місяців тому +1

    Now I understood, What is RAG - Retrieval Augmented Generation ,Very Informative Video, Liked your Video 👍

  • @sabriboubaker
    @sabriboubaker 10 місяців тому +1

    Great video, straight to the point. Thanks again

    • @WhatsAI
      @WhatsAI  10 місяців тому

      Thank you Sabri! :)

  • @JavierTorres-st7gt
    @JavierTorres-st7gt 6 місяців тому

    How to protect a company's information with this technology?

    • @the_hasnat
      @the_hasnat 2 місяці тому +1

      You'd only provide placeholders for the company's information within these prompts and make sure that they are in a specific format.

  • @Plink2120
    @Plink2120 11 місяців тому +1

    Vraiment clair et précis merci

  • @Kama45
    @Kama45 7 місяців тому +2

    Subbed

  • @helainz7198
    @helainz7198 7 місяців тому +1

    Et cetera bien sur mon poto

  • @chairwood
    @chairwood 11 місяців тому +2

    thx. i enjoyed this video

    • @WhatsAI
      @WhatsAI  11 місяців тому +1

      Glad to hear so my friend! 😊

  • @mahiaravaarava
    @mahiaravaarava 4 місяці тому +1

    AI algorithms facilitate better decision-making in business by providing actionable insights from data analysis.This enhances strategic planning and operational efficiency.

  • @Mr_Arun_Raj
    @Mr_Arun_Raj 11 місяців тому

    After integrating with RAG. latency increased....

    • @WhatsAI
      @WhatsAI  11 місяців тому

      That is for sure! There is some downsides but the latency if very little.

  • @paulwillisorg
    @paulwillisorg 8 місяців тому

    The accent of the speaker is pretty heavy.

    • @WhatsAI
      @WhatsAI  8 місяців тому +1

      Hope it’s still easy to understand!

  • @kunjs
    @kunjs 10 місяців тому

    google launched gemini advanced 1.5, a RAG killer 💀

    • @WhatsAI
      @WhatsAI  10 місяців тому +4

      A database can be much larger than this context window and much more efficient I believe. It’s unsure how good the models are vs gpt4 yet. Plus, sending millions of tokens for every prompt will be extremely expensive for each request, haha! It’s good for some use cases like sending a full repo once and asking questions but not for working with customers and handling many requests I believe.