LangGraph Functional API Overview

Поділитися
Вставка
  • Опубліковано 5 лют 2025

КОМЕНТАРІ • 28

  • @rishavranaut7651
    @rishavranaut7651 7 днів тому +4

    Just the time when i actually got used to managing these states, you brought something good 👍

    • @benjamincburns
      @benjamincburns 7 днів тому

      Glad to hear you like it! But also if you like using StateGraph, don't worry - we don't have any plans on removing it!

  • @saikrishnasunkari1822
    @saikrishnasunkari1822 День тому

    Very cool video. Please do a video on Agentic RAG😊

  • @IdPreferNot1
    @IdPreferNot1 7 днів тому +3

    Very interested in the "useful overhead" of langraph/langchain, but not for everything. Can you guys consider building/ or demonstrating some more conversions "in and out" of langchain/langraph and into or from straight python. Not knowing whjat is happening under the abstraction can be confusing. Can you build or is there a function to "bridge" that through maybe a pydantic model or something that you could apply at any point of your lanchain coding?

  • @tanyawannabe1482
    @tanyawannabe1482 7 днів тому +2

    What is the core benefits from switching from Graph API to Functional API? Wouldn't I just stick to Graph API if I prefer graph structure?

  • @angersclubbing
    @angersclubbing 6 днів тому +3

    Someone from Langchain can please tell me if we can access this fonctional api without paying for access to langgraph studio? I want to use langchain fonctional api for my agent and pay as I use it with an api Key and not spending 40$ per months for access to studio

  • @stephenthumb2912
    @stephenthumb2912 3 дні тому

    I'm assuming that the tool decorator basically adds a parameter to construct a structured input to the prompt to the LLM. is there reference for this that I can lookup? For example if I want to create types of tools or change parts of what the actual structured input looks like depending on the LLM. Using for different languages is an example or tweaking the actual structured input to optimize the LLM's peformance if it's fine tuned for a different kind of input structure.

  • @amitpanda123
    @amitpanda123 7 днів тому +2

    Nice tutorial. Is it possible to store a pandas dataframe in long term memory? Or, it supports only texts?

    • @willfu-hinthorn
      @willfu-hinthorn 7 днів тому

      We fall back to pickle in some cases for the checkpointing but I haven't specifically checked how well it works for large pandas dataframes

  • @areiner222
    @areiner222 7 днів тому +2

    Where can I find Store implementations for other databases?

  • @aifarmerokay
    @aifarmerokay 7 днів тому +1

    Please convert already existing agent tools code into this so we will get idea

  • @waneyvin
    @waneyvin 7 днів тому

    where did you store long term memory? text file? database? or just in memory?

    • @willfu-hinthorn
      @willfu-hinthorn 7 днів тому +2

      You provide the store, but usually postgres or mongo or some other db in prod.
      If it were just text file or in-memory that would be mostly useless in prod

  • @venkatareddy56
    @venkatareddy56 7 днів тому

    How would it work with copilot kit?

  • @iamBharad
    @iamBharad 7 днів тому +1

    Is there a roadmap on studio for Windows?

    • @willfu-hinthorn
      @willfu-hinthorn 7 днів тому

      It's been supported for a long time. `langgraph dev` - it's a python package.

  • @aifarmerokay
    @aifarmerokay 7 днів тому +1

    Like crewai we can’t directly or simply create agents.
    Need more tutorials on real use case to showcase

    • @willfu-hinthorn
      @willfu-hinthorn 7 днів тому

      from langgraph.prebuilt import create_react_agent
      What specifically would you like to use that would make you faster/better at building applications?

    • @aifarmerokay
      @aifarmerokay 7 днів тому +1

      @@willfu-hinthorn example shown on your how to guide for
      Multi agents is not able to relate with real use case . Also the supervisor gent shown in tutorial. Please check lots of people comments there
      (This one is not able to use in production )

  • @codingcrashcourses8533
    @codingcrashcourses8533 7 днів тому +4

    Not really sure if I see any benefit. I was already critical about Command and Interruppt. In my opinion you start to bloat the framework with edge cases and make it messy, the same what happened with LangChain.
    I would not want to work with code like that:
    attempts = 0
    @task(retry=retry_policy)
    def get_info():
    global attempts
    attempts += 1
    Putting attempts inside the state object is much cleaner in my opinion and I dont really see why we need a "quick and dirty" way to create an Agent.

    • @EugeneYurtsev
      @EugeneYurtsev 7 днів тому +3

      The attempts here is only used to simulate a network failure to illustrate that RetryPolicy works out of the box. We'll clarify it in the documentation.

  • @JohnCena12355
    @JohnCena12355 7 днів тому +1

    I certainly won't be using this. I'll stick with StateGraph.

  • @AlexanderErm
    @AlexanderErm 7 днів тому +1

    love interrupt()

  • @0730pleomax
    @0730pleomax 7 днів тому +12

    just became messier and messier