Discover LlamaIndex: Joint Text to SQL and Semantic Search

Поділитися
Вставка
  • Опубліковано 29 лис 2024

КОМЕНТАРІ • 33

  • @starmorph
    @starmorph Рік тому +4

    excited for this whole channel!

  • @oaga74
    @oaga74 4 місяці тому +4

    What if the information is distributed in multiple tables within the SQL database? Would LlamaIndex be able to join the relevant tables without the user explicitly citing them? This question is essential, especially if the tables are not labeled more intuitively e.g. a table having cities labelled/named as Lctin!

  • @Jason-o5s
    @Jason-o5s 22 дні тому

    Cheer~~~add (comments or supplementary information) at the end of a speech or text.😊

  • @zeppelin2105
    @zeppelin2105 Рік тому +2

    hi~could u share more about the selector realization? whether i can use the llm itself to realize?

  • @ravigurram9884
    @ravigurram9884 8 днів тому

    is it basically a NL2SQL method?

  • @renaudgg
    @renaudgg 10 місяців тому

    why we use pinecone exactly? i know with llama_index there is alresdy some VectorStorrIndex etc is it because pinecone does it better? i dont understand that part

  • @garyjo3229
    @garyjo3229 8 місяців тому

    And ollama2 is posible language natural to sql ?

  • @deeplearning7097
    @deeplearning7097 Рік тому

    Thank you very much, very nice work. Could you please share your notebook? Thanks again.

  • @vishnuajoshy1588
    @vishnuajoshy1588 Рік тому +1

    Instead of using open AI..Can we do this using Llama or mistral model?

    • @vgtgoat
      @vgtgoat 10 місяців тому

      Yes you can run your own server with something like Oobabooga textgen webui

  • @elruinnou
    @elruinnou Рік тому

    Is there any JS version of this? At least for the structure ones, cz I think it’d still be better if the unstructred ones can just use python

  • @MrSawaiz
    @MrSawaiz Рік тому +2

    Can we implement the same thing in Langchain?

    • @vgtgoat
      @vgtgoat 10 місяців тому

      Very little reason to implement it yourself with langchain when llamaindex exists here. You could recreate all this with raw langchain if you want technically though.

    • @MrSawaiz
      @MrSawaiz 10 місяців тому

      @@vgtgoat I understand that but I am having some issues while using this query engine. I asked on their discord channel and they said that they won't be fixing the bug any time soon.
      I thought maybe I'll implement my version

    • @thestereokid6073
      @thestereokid6073 18 днів тому

      There's other examples of combining langchain and llamaindex, I'm working on figuring that out right now. glhf.

    • @ravigurram9884
      @ravigurram9884 8 днів тому

      @@vgtgoat llamaindex is not opensource and is a commercial product right?

  • @jcachat
    @jcachat Рік тому

    🔥🔥🔥

  • @DenisBougrimov
    @DenisBougrimov Рік тому

    Can something similar be done with SparQL instead of SQL?

    • @SanjayRoy-vz5ih
      @SanjayRoy-vz5ih 10 місяців тому

      Yess, if it is pretty trained with SparkQL and has a solid understanding developed over time

  • @kelvinadungosi1579
    @kelvinadungosi1579 7 місяців тому

    Hi what if I dont have ustructured data and instead of a vector store, I just want to query the llm itself or the general internet. Plus how to implement chat functionality where by I can ask follow up questions based on previous answers?

  • @CharlySUASISA
    @CharlySUASISA Рік тому

    how can we use llamaindex on nodejs ?

  • @FoxnewsFan
    @FoxnewsFan Рік тому

    So it's basically some sort of an Agent

  • @jayasreelingam5862
    @jayasreelingam5862 8 місяців тому

    Can you share the code once

  • @dota2gammingfun93
    @dota2gammingfun93 Рік тому +2

    How can i use it whithout OPEN API KEY - i dont want to use Open AI and want to use open source llm

    • @dennissdigitaldump8619
      @dennissdigitaldump8619 Рік тому

      There was a pine api key. This is Llama, which can be run locally.

    • @SanjayRoy-vz5ih
      @SanjayRoy-vz5ih 10 місяців тому

      ​@@dennissdigitaldump8619 pine is a vector database and has nothing to do with foundation model llms though...one way is to use huggingface hub api token

  • @ohmatokita5990
    @ohmatokita5990 Рік тому

    Hi , what if the SQL database has 10 million records, this code still working?

    • @SanjayRoy-vz5ih
      @SanjayRoy-vz5ih 10 місяців тому

      Unlikely without a pro version with unlimited token size limitations, you will face challenges

  • @daviteodoro1225
    @daviteodoro1225 7 місяців тому

    TORONTOTOKYO ?

  • @____2080_____
    @____2080_____ Рік тому +9

    You stated that the Jupiter Notebook was linked in the description. I don’t see it. 🫨

    • @gabrielkeith3189
      @gabrielkeith3189 6 місяців тому

      And folks... he put the QR code in the video.😅😅😅