LangGraph: Building a Dangerously Smart AI Agent - Dynamic Code Generation & Execution!

แชร์
ฝัง
  • เผยแพร่เมื่อ 24 ต.ค. 2024
  • Get ready to witness the power of a dangerously smart AI! In this thrilling tutorial, we dive into LangGraph, a revolutionary framework that orchestrates dynamic agents capable of generating, reviewing, and executing Python code in real-time. Watch as this AI autonomously transforms your natural language requests into executable code, reviews it for errors, and safely runs it inside a Docker container. 🚀
    This isn’t just any AI-it's an agent that learns, adapts, and even retries until perfection, all while ensuring the safety of your system. You’ll see how we build this agent step-by-step, leveraging LangGraph's StateGraph and advanced workflows. Whether you're new to LangGraph or an enthusiast, this video will show you how to push the boundaries of AI development!
    📂 GitHub Repository: github.com/Tea...
    📺 Watch the full playlist here: • AI Workflows: LangGrap...
    Make sure to like and subscribe for more mind-blowing tutorials on advanced AI workflows, dynamic agents, and LangGraph magic! Let’s explore the future of AI together!

ความคิดเห็น • 13

  • @smehra
    @smehra 9 วันที่ผ่านมา +2

    This is seriously good, so much superior to other Langgraph tutorials.

  • @tharunbhaskar6795
    @tharunbhaskar6795 9 วันที่ผ่านมา +2

    Very simple to follow. This clearly explains how we can make agents interact with each other and the importance of State in LangGraph. I really liked the code execution part, where we run it in isolation to protect from running potential harmful code

    • @MukulTripathi
      @MukulTripathi  9 วันที่ผ่านมา +1

      Safety with AI generated code is needed. I'd be extending this into my voice assistant with more safety integrated into it.
      We can also have a human in the loop if we want to run shell scripts on host machine.

    • @tharunbhaskar6795
      @tharunbhaskar6795 9 วันที่ผ่านมา

      @@MukulTripathi Yah, we can even use RegEx, to initially screen if the code generated contains any malious imports (like subprocess)

  • @ronwiltgen2698
    @ronwiltgen2698 9 วันที่ผ่านมา +1

    Would it be possible to add this as a prefect flow? And then dynamically invoke it?

    • @MukulTripathi
      @MukulTripathi  9 วันที่ผ่านมา

      Of course! In fact my voice assistant is going to be doing exactly this.

    • @tharunbhaskar6795
      @tharunbhaskar6795 9 วันที่ผ่านมา +1

      @@MukulTripathi Can we have a video on this

    • @MukulTripathi
      @MukulTripathi  9 วันที่ผ่านมา +1

      For sure, I'm on an international trip for about a month, but I might find time for this. Otherwise, it'll be around end of November.

    • @tharunbhaskar6795
      @tharunbhaskar6795 9 วันที่ผ่านมา

      @@MukulTripathi Sure, will be waiting

  • @techchanx
    @techchanx 8 วันที่ผ่านมา

    tried everything to get langraph and langchain installed and it failed repeatedly with various build errors. gave up.

    • @MukulTripathi
      @MukulTripathi  8 วันที่ผ่านมา

      Did you do a pip install for requirements? I just set it up on a new machine and it works.
      Would you like to paste the error?

    • @techchanx
      @techchanx 7 วันที่ผ่านมา

      @@MukulTripathi got it working, tried it next day and it worked :)

    • @MukulTripathi
      @MukulTripathi  7 วันที่ผ่านมา

      I'm glad it worked for you :)