LangGraph: Multi-Agent Workflows

Поділитися
Вставка
  • Опубліковано 3 гру 2024

КОМЕНТАРІ •

  • @bqmac43
    @bqmac43 8 місяців тому

    These videos never cease to impress me. Straight-forward and effective. Thank you, LangChain team!

  • @christopherscheidel5431
    @christopherscheidel5431 10 місяців тому +9

    Fantastic work as always. Thanks to the LangChain team.

  • @raphael39
    @raphael39 8 місяців тому +1

    Super helpful series. I delved a lot in langchain source code, docs to customize already well-established examples and started these series for LangGraph it's a great format thanks a lot.

    • @tonyppe
      @tonyppe 6 місяців тому

      are you using ai to write youtube comments?

    • @ilianos
      @ilianos 4 місяці тому

      @@tonyppe just because you read the word "delve" ;-) ? look at the last words of his comment: missing punctuation marks :)

  • @akashlives
    @akashlives 10 місяців тому +1

    Thank you for constantly posting such videos.
    So easy to use and adopt.

  • @paraconscious790
    @paraconscious790 10 місяців тому

    This is a super helpful series, a quick starter, easy to follow along with practical examples, thanks so many Harrison! Starting to experiment right away!

  • @Orcrambo
    @Orcrambo 10 місяців тому +1

    Excited to get my hands dirty with langgraph. Hopping on now!

  • @ManiSaintVictor
    @ManiSaintVictor 10 місяців тому

    Thank you! Very helpful. I did the first 2 exercises. I'll be back for the 3rd.

  • @Mullheimer
    @Mullheimer 10 місяців тому

    Great way of explaning. Thank you. Will dive into it sometime soon.

  • @ramzirebai3661
    @ramzirebai3661 4 місяці тому

    This is incredibly beautiful

  • @dvirbenor2690
    @dvirbenor2690 10 місяців тому

    Very interesting and well explained! Thanks 👌

  • @lucascresci509
    @lucascresci509 9 місяців тому +1

    Bro is just a beast!

  • @ZhambylYermagambet
    @ZhambylYermagambet 10 місяців тому

    Awesome! Thank you guys for great work

  • @Sandheip
    @Sandheip 3 місяці тому

    LangGraph makes creating multi-agent processes easier. SymthOS is an essential viewing for anyone interested in cutting-edge AI frameworks. #AI #MultiAgentWorkflows #SymthOS

  • @johnvicente796
    @johnvicente796 6 місяців тому +2

    Great video. Can you PLS create an example in langgraph on how to use an SQL database tool and call the tool with an agent. More importantly do a RAG search with it. That would be helpful

  • @kevinkawchak
    @kevinkawchak 6 місяців тому

    Thank you for the discussion.

  • @glowstorm334
    @glowstorm334 7 місяців тому +1

    For anyone facing any error , there are the two error I have faced :
    1: Make sure Matplotib is installed in your environment
    2: Change the name of Chart Generator to Chart_Genenrator , this fixes an error which the regex does not recognize the name of Chart Generator.

  • @free_thinker4958
    @free_thinker4958 4 місяці тому +1

    That would be great if you add a disclaimer at the beginning of the video mentionning that it's for intermediate and advanced levels because beginners will feel lost and sometimes more confused just like me

  • @rahulvb5044
    @rahulvb5044 8 місяців тому +1

    In the supervisor example , the model returns ,
    {
    "function_call" : {
    "arguments" : "{"next","Coder"}",
    "name" : "route"
    }
    How is this used to determine the next agent.
    Or how is Agentstate populated with next : Coder after getting the above out put from model. I can see a JsonOutputFunctionsParser. But i cant understand, how next value is determined from that

    • @HiKami-f5o
      @HiKami-f5o 4 місяці тому

      In conditional edges setup. You parse it to dict and then make a conditional navigation depending on 'next' value

  • @adandrea
    @adandrea 7 місяців тому

    Great video. One bit things I'm trying to figure out: how can the tools access the graph state? I mean custom tools. I really need them to have context of the conversation, user session metadata, etc, and I can't past them that info if the tools are called just with the parameters filled with syntetic data generated by the llm. I'm sure there is a way to do it but can't seem to fiture it out. Thanks!

  • @drtristanbehrens
    @drtristanbehrens 9 місяців тому

    Such a cool video!

  • @waneyvin
    @waneyvin 10 місяців тому

    great job! please advise how if I wanna add reward or policy into the state for further decision making sake.

  • @ragsAI
    @ragsAI 10 місяців тому

    Hi! Is Langchain integratable/compatible with redshift/databricks? (especially the text-to-sql framework)? Thank you.

  • @estebanmunoz1637
    @estebanmunoz1637 10 місяців тому

    I can't make this example work using AzureOpenAI, I am receiving the error: 'create() got an unexpected keyword argument 'functions''
    after executing:
    result = agent.invoke({"input": "what's the weather in SF?", "intermediate_steps": []})
    Are Agents supported using AzureOpenAI? I have been trying different formulas but I cannot make my agents work using AzureOpenAI

  • @aryangautam7161
    @aryangautam7161 10 місяців тому

    Are there examples on how you can use multi agent workflow that doesn’t involve openAI function calling?

  • @octopusfinds
    @octopusfinds 8 місяців тому

    Thank you!

  • @adityagaurav2816
    @adityagaurav2816 9 місяців тому

    I tried to implement supervisor based multi agent framework for my use case but after my workers return something to supervisor , supervisor doesn't call FINISH and get into a loop of calling the same worker again and again. Has anyone faced this issue ? or know how to fix this ?

  • @zelx7567
    @zelx7567 7 місяців тому

    Thank you langchain team, this helps a lot. In the example multi-agent graph all agents share the same instance of a large language model (LLM), is it possible to use different LLMs for different agents?

  • @jimjimjimjimjim
    @jimjimjimjimjim 5 місяців тому +1

    Does anyone get issues where the supervisor agent loops over and over calling the sub agents?

    • @calebadobah641
      @calebadobah641 4 місяці тому

      Yes same. Have you managed to fix it?

  • @VijayasarathyMuthu
    @VijayasarathyMuthu 10 місяців тому

    Could you show how to bring Humans in the Loop in each architecture or any one of them?

  • @mertsengil4697
    @mertsengil4697 3 місяці тому

    Hello, thank you for the vide. I have a problem. I created my own tools instead of "tavily search" and "PythonREPL" tools. I did everything same with your code. But i cant get the end token {'supervisor' : {'next' : 'FINISH'}}. why? can anyone help me pls?

    • @mertsengil4697
      @mertsengil4697 3 місяці тому

      Continuous 1. tool... 2. tool... 1. tool. ... As the 2nd tool, it loops through my tools, but it never goes to the finish token and finishes the loop.

  • @joehenri1
    @joehenri1 10 місяців тому +3

    What is the differences between CrewAI and LangGraph ?

    • @yuripourre
      @yuripourre 7 місяців тому

      CrewAI is a thin wrapper around langgraph.

  • @陈晓耀
    @陈晓耀 4 місяці тому

    not work with the current version of langgraph/langhchain, issues never solved

  • @aryangautam7161
    @aryangautam7161 10 місяців тому +2

    I tried to implement multiagent using supervisor agent and running into issue where it couldn't parse function call.
    langchain_core.exceptions.OutputParserException: Could not parse function call: 'function_call

  • @Stormyys
    @Stormyys 10 місяців тому

    How do we get access to langsmith?

    • @LangChain
      @LangChain  10 місяців тому

      DM Harrison on twitter @hwchase17 :)

  • @carterjames199
    @carterjames199 10 місяців тому

    How can I request access to langsmith??

    • @LangChain
      @LangChain  10 місяців тому

      hey, if you drop Harrison a message on twitter @hwchase17 he'll get you access

    • @carterjames199
      @carterjames199 10 місяців тому

      @@LangChain already done he was very fast to reply

  • @manfyegoh
    @manfyegoh 10 місяців тому

    hi how do i get access to langsmith?

    • @LangChain
      @LangChain  10 місяців тому

      Drop Harrison a message on twitter @hwchase17 and he'll sort you out

    • @manfyegoh
      @manfyegoh 10 місяців тому

      @@LangChain thanks! i just gotten my access!

  • @Kenykore
    @Kenykore 10 місяців тому

    Need access to langsmith

    • @LangChain
      @LangChain  10 місяців тому

      DM Harrison on twitter @hwchase17 :)

  • @adamwilfrid3271
    @adamwilfrid3271 10 місяців тому

    requesting for Langsmith access please 😊

    • @LangChain
      @LangChain  10 місяців тому

      DM Harrison on twitter for access @hwchase17 :)

  • @googleyoutubechannel8554
    @googleyoutubechannel8554 9 місяців тому +10

    Oh no, I feel so sorry for everyone trying to use this, you don't have nearly enough basic logging functionality or debugging / investigation tooling in langchain to make using multiple prompt stages remotely tolerable, I wonder how long it will take people trying to actually implement this to solve a problem to figure it out.

    • @ste7081
      @ste7081 9 місяців тому +16

      didn’t they make langsmith exactly for this?

    • @xfldiazx
      @xfldiazx 6 місяців тому

      ​@@ste7081 but it's not private :( honestly a framework should not rely on a paid service for basic functionality, I wish I could use it though

  • @RonnyAndersson-p6z
    @RonnyAndersson-p6z 10 місяців тому

    Great video! Can you hook me up with Langsmith?

  • @IAMTHEMUSK
    @IAMTHEMUSK 2 місяці тому

    The last one is far from easy to implement. I wonder if learning langgraph is worthy instead of learning how to do the same from scratch. It feels like learning a new programming language.

  • @RonnyAndersson-l2q
    @RonnyAndersson-l2q 10 місяців тому

    Great video! Can you hook me up with langsmith? :)

    • @LangChain
      @LangChain  10 місяців тому

      Shoot Harrison a message on twitter @hwchase17 :)

  • @avi7278
    @avi7278 10 місяців тому +1

    What's your Twitter?