LlamaIndex Sessions: Practical Tips and Tricks for Productionizing RAG (feat. Sisil @ Jasper)

Поділитися
Вставка
  • Опубліковано 12 гру 2024

КОМЕНТАРІ • 15

  • @seanbergman8927
    @seanbergman8927 9 місяців тому +4

    This was an excellent talk. Thanks so much for sharing your experience and this RAG framework. If there could be a follow up sometime with a sample notebook that uses these techniques, and a code walkthrough video , I’m sure many people would greatly benefit from it.

  • @infraia
    @infraia 3 місяці тому

    Very helpful guys! Thanks !

  • @philipagenmonmen
    @philipagenmonmen 6 місяців тому

    Super comprehensive. Thanks for this.

  • @memsSudar
    @memsSudar 9 місяців тому +1

    Sisil's presentation was exemplary, addressing key pain points with innovation.
    Congratulations on your work!. We as a company also trying to solve all pain points you have mentioned in the pdf docs area.
    Thanks to Jerry for spotlighting talent like Sisil. Excited for more content!

  • @bszhang2115
    @bszhang2115 9 місяців тому +1

    a showcase sample notebook would be deeply appreciated!

  • @jeevan999able
    @jeevan999able 9 місяців тому +1

    this was fantastic, can you provide a tutorial notebook?

  • @falven
    @falven 8 місяців тому

    Would have loved if you shared the slides in the description. :)

  • @karthikmukundakrishnan7853
    @karthikmukundakrishnan7853 9 місяців тому +1

    Is there a sample code you can post a link to, specifically for indexing the subdocs, then the chunks and retrieving them?

  • @chenrannight2272
    @chenrannight2272 9 місяців тому

    amazing!!! Sisil really explained the difference between benchmarks and real world openended questions!
    btw, could you include the datasets name Sisil talked about regarding "retrieval" and "reranking" on evaluation?

  • @jeevan999able
    @jeevan999able 9 місяців тому +1

    how does lexical indexing work for subdocs

  • @qingsongyao4974
    @qingsongyao4974 9 місяців тому +2

    I wonder what is the PDF parse Sisil 's team is using?

    • @bram1223
      @bram1223 9 місяців тому +1

      Adobe Extract PDF API or something. I haven't tested it but it works pretty well from what I've heard.

    • @UdayVakalapudi
      @UdayVakalapudi 8 місяців тому

      There is an opensource version as well (Works in Linux Distro) called unstructured. You just need to do pip install unstructured[all].

  • @DanielHernandez-n1o
    @DanielHernandez-n1o 9 місяців тому +2

    I didn't catch what was the pdf parser used? Can you name it please?

    • @jochenade
      @jochenade 9 місяців тому

      I think it was adobe api