Advanced RAG with Self-Correction | LangGraph | No Hallucination | Agents | LangChain | GROQ | AI

Поделиться
HTML-код
  • Опубликовано: 3 дек 2024

Комментарии •

  • @icecubeinsights8349
    @icecubeinsights8349 4 месяца назад

    Hi Eduardo, this is a really nice video, thank you. Do you think you could add a citation functionality, such that the user get's reaffirmed, where the information was taken from? Thanks

  • @vasudevanvijayaragavan3186
    @vasudevanvijayaragavan3186 5 месяцев назад +1

    Very nice, the only challenge with this approach is the total cost of answering each query, and it could run forever in some cases till both llms agree or till you get thr eight relevant information from the search. I think of customers want 100% gurantee and are not worried about latency, this will work really well.

    • @eduardov01
      @eduardov01  5 месяцев назад +1

      Indeed, it'll depend on the usecase that you have because for some cases you wouldn't sacrifice the quality of the responses for the speed.

    • @jayden_finaughty
      @jayden_finaughty 5 месяцев назад

      Surely this approach becomes more and more viable as the cost of newly released models keep on decreasing by 5x, 10x est as we are currently seeing?
      So the cost of this multi-shot RAG approach with a new model 5x cheaper is still less expensive than a single-shot of its more expensive predecessor?

    • @eduardov01
      @eduardov01  5 месяцев назад +1

      Exactly!

  • @marcoaerlic2576
    @marcoaerlic2576 5 месяцев назад +1

    Awesome video. Thank you.

    • @eduardov01
      @eduardov01  5 месяцев назад

      Glad you liked it!

  • @VLM234
    @VLM234 4 месяца назад

    Great video! But how to break a loop after a few trials if the model gets stuck into an infinite loop during Hallucinations grading or answer relevance?

  • @SonGoku-pc7jl
    @SonGoku-pc7jl 5 месяцев назад +1

    thanks, good flow between rag and web search, thanks!!1 :)

    • @eduardov01
      @eduardov01  5 месяцев назад

      Thank you. I'm glad you found it interesting!

  • @chikosan99
    @chikosan99 5 месяцев назад +1

    Great video, very nice

    • @eduardov01
      @eduardov01  5 месяцев назад

      Thank you very much!

  • @keilavasquez728
    @keilavasquez728 6 месяцев назад +1

    I've been searching for a self-correcting system because sometimes the responses I receive from LLMs aren't precise. Thank you so much for your help.

    • @eduardov01
      @eduardov01  6 месяцев назад

      I'm glad it was helpful!

  • @ramakanaveen
    @ramakanaveen 5 месяцев назад +1

    Nice one. Question : what if all the docs are marked as irrelevant chunks by the model , do you need to query the vector db again ? I guess an improvement may be to include a Hyde model in between to improve the questions and keep trying to get a different chunks from DB ?

    • @eduardov01
      @eduardov01  5 месяцев назад +1

      It'll perform a web search to find the relevant information (node that has the Agent). Yes, that could be an option too.

  • @pavanpraneeth4659
    @pavanpraneeth4659 5 месяцев назад +1

    Awesome

  • @amacegamer
    @amacegamer 6 месяцев назад +1

    Great video! But I have a question I hope you can answer and help me.
    Why is so slowly answering? that's normal for the architecture or there is other reason, and can we do something to fix that?

    • @eduardov01
      @eduardov01  6 месяцев назад

      The fact that we have 5 LLMs to generate answers + retriever + a websearch is performed when the question is not in the vector store database + we also store the web search results in the database and all these steps can take some time. To make it faster, you can use fewer LLMs and maybe skip the web search, depending on your usecase.

  • @eucharisticadoration
    @eucharisticadoration 5 месяцев назад +1

    Can you make an example using only Local LLMs and Local Agents, so no API Keys (and no costs) are created? That would be amazing!

  • @eyalfrish
    @eyalfrish 6 месяцев назад +1

    Nice video!
    Any chance to get access to the excalidraw version of the diagram?

    • @eduardov01
      @eduardov01  6 месяцев назад

      Thanks!
      I have a free account in Excalidraw and just have 1 session with all my diagrams. But you can get access to the flowchart using this link: github.com/Eduardovasquezn/advanced-rag-app/blob/main/images/rag.png

  • @keila9874
    @keila9874 6 месяцев назад +2

    Is the Tavily API for free? Can I use the Google Search Engine instead?

    • @eduardov01
      @eduardov01  6 месяцев назад +1

      Yes, you can make 1,000 API calls for free every month.
      It's also possible to use Google Search as an agent for this. I have a video explaining step-by-step how to use it: ruclips.net/video/ppGRPWpv9Wc/видео.html