Reflection Agent From Scratch | Agentic Patterns Series

Поділитися
Вставка
  • Опубліковано 10 лис 2024

КОМЕНТАРІ • 16

  • @abhijithkadam383
    @abhijithkadam383 8 днів тому

    Great explanation, thank you

  • @franklinobasy
    @franklinobasy 21 день тому

    Great Explanation! Welldone.

  • @vq8gef32
    @vq8gef32 2 місяці тому +1

    Amazing and thanks for sharing this

    • @TheNeuralMaze
      @TheNeuralMaze  2 місяці тому +1

      Anytime! Thanks for the kind words 😍 I'm already working on the second episode! 🦾

  • @web3global
    @web3global 21 день тому

    🚀

  • @Danyal_alam
    @Danyal_alam Місяць тому +2

    Hey Miguel, can you please create a tutorial on production ready recommender system?

    • @TheNeuralMaze
      @TheNeuralMaze  Місяць тому +3

      hey! Once I finish the "Agentic patterns from scratch" series yes! that's what I had in mind - Medium Posts + UA-cam Videos about production-ready RecSys 😃

  • @paul_devos
    @paul_devos 21 день тому

    Great content, thank you!
    Question for you, what tool did you use to draw your diagrams, those are rich and love the fonts you used.

  • @nessrinetrabelsi8581
    @nessrinetrabelsi8581 Місяць тому +1

    When you loop on (generate then reflect), you basically are not taking into account the last reflection (critique) of last loop, no?

    • @TheNeuralMaze
      @TheNeuralMaze  Місяць тому +3

      Hey! So previously I was taking into account the whole history of messages. Problem? You may end up with too many tokens for the LLM window. What I did at the end was to limit the chat history to just two messages (the previous reflection and generation completions), and the results were very similar (and much faster).

  • @ThisIsChina-mu1ls
    @ThisIsChina-mu1ls 6 днів тому

    In my ReAct multiple agent system, the time it takes to obtain the final answer using tools can be quite long, leading to a poor user experience. In your system, how long does the process of calling the choose tool -> execute tool -> get final answer take in each round,, and how many times does the LLM (Large Language Model) need to be called?

    • @TheNeuralMaze
      @TheNeuralMaze  6 днів тому

      It depends on the task, if you go to the third video of the series, you'll see the ReAct agent I implemented from scratch, using three tools. The problem it has to solve is very simple, but maybe it will give you an overall idea of the time it takes.