Contextual Retrieval: Next Level-RAG

Поділитися
Вставка
  • Опубліковано 26 лис 2024

КОМЕНТАРІ • 16

  • @AI-Makerspace
    @AI-Makerspace  Місяць тому

    Contextual Retrieval: colab.research.google.com/drive/1KGVxiwc2zoY9v6f3IQfs8qJIZeGeMKAq?usp=sharing
    Event Slides: www.canva.com/design/DAGTv5ofV8g/-wFTZpoCu8yYzseTb_kx2g/view?DAGTv5ofV8g&

    • @weiwennie40
      @weiwennie40 12 днів тому

      The Ragas part of code in the notebook is not working. Could you fix it?

  • @hoopNscoops
    @hoopNscoops 26 днів тому +1

    Great information here! Thanks for making it public. I think you're going to get a sizeable community around you because of these live streams.
    Q: where in the code is prompt caching evoked?

    • @AI-Makerspace
      @AI-Makerspace  21 день тому

      Caching is offered by Anthropic's endpoint by default - and is being taken advantage of under the hood here.

  • @seanbergman8927
    @seanbergman8927 Місяць тому

    Great video and demo as always! I learn much from your content. The contextual retrieval paper said if your corpus is less than 200k tokens, just skip rag and dump the entire corpus into the prompt for every question, and they will cache it (but only for a short time) and just use long context Q&A. I didn’t see them publish any metrics comparing long context to rag, so I take it with a grain of salt. They do want customers to spend as many tokens as possible... But I’m very intrigued at the same time. Maybe you could do a video comparing the two methods? That would be amazing research.

    • @AI-Makerspace
      @AI-Makerspace  Місяць тому

      Great insights and instincts @Sean! We'll keep the content recommendation in mind for sure! This is farthest we've gotten on Long-Context and Evaluation for the big window LLMs: ua-cam.com/users/liveBrwhbjh3boU?si=V24z6pagQ0EQ8Ms1

  • @danielusvyat
    @danielusvyat Місяць тому +1

    Great video! I’m excited to dive into contextual retrieval next week.
    When it comes to productionizing hybrid retrieval with BM25, I’m considering using Elasticsearch, any other recommendations?
    My main concern with hybrid retrieval is the added complexity it brings to the production.

    • @AI-Makerspace
      @AI-Makerspace  Місяць тому

      Elasticsearch is a great tool for this!

  • @AmanBansil
    @AmanBansil Місяць тому +1

    RAG-ception 0:55 - Context of the contextually generated chunks. Got it...got..it.......got it....ok wait what? Need to watch the whole thing.

  • @aryansaurabhbhardwaj
    @aryansaurabhbhardwaj 22 дні тому

    Hi Greg and Wiz. Great tutorial. I am actually applying it to my own application. I was wondering what would you sugges to do if the whole document size is large more than 700 pages. It want be passed in the contextual chunking function. If I take the 500 pages around the chhunk, the chaching wont work. Please can you advice? Thanks Saurabh

    • @AI-Makerspace
      @AI-Makerspace  21 день тому

      I would build some metadata, in this case, like a summary/outline and use that to generate contextual augments.

  • @micbab-vg2mu
    @micbab-vg2mu Місяць тому +1

    thanks :)

  • @MegaClockworkDoc
    @MegaClockworkDoc Місяць тому +1

    Great video, but using text that the model was already trained on is a bad test case

    • @AI-Makerspace
      @AI-Makerspace  Місяць тому

      Agreed! We typically stick with easy to consume toy-examples, however!