LangGraph: Multi-Agent Workflows

Рет қаралды 88,358

LangChain

Күн бұрын

Пікірлер: 65

@bqmac43 9 ай бұрын

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

@christopherscheidel5431 11 ай бұрын

Fantastic work as always. Thanks to the LangChain team.

@raphael39 8 ай бұрын

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 7 ай бұрын

are you using ai to write youtube comments?

@ilianos 5 ай бұрын

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

@akashlives 11 ай бұрын

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

@paraconscious790 11 ай бұрын

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!

@johnvicente796 6 ай бұрын

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

@Orcrambo 11 ай бұрын

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

@adandrea 7 ай бұрын

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!

@free_thinker4958 5 ай бұрын

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

@Sandheip 4 ай бұрын

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

@ManiSaintVictor 11 ай бұрын

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

@rahulvb5044 9 ай бұрын

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 5 ай бұрын

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

@Mullheimer 11 ай бұрын

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

@glowstorm334 8 ай бұрын

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.

@dvirbenor2690 11 ай бұрын

Very interesting and well explained! Thanks 👌

@ZhambylYermagambet 11 ай бұрын

Awesome! Thank you guys for great work

@lucascresci509 10 ай бұрын

Bro is just a beast!

@ramzirebai3661 5 ай бұрын

This is incredibly beautiful

@waneyvin 11 ай бұрын

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

@adityagaurav2816 10 ай бұрын

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 ?

@estebanmunoz1637 10 ай бұрын

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 10 ай бұрын

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

@jimjimjimjimjim 5 ай бұрын

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

@calebadobah641 5 ай бұрын

Yes same. Have you managed to fix it?

@zelx7567 7 ай бұрын

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?

@StaraX95 6 ай бұрын

yep

@mertsengil4697 4 ай бұрын

u can use llama3.1 with groq

@kevinkawchak 7 ай бұрын

Thank you for the discussion.

@ragsAI 11 ай бұрын

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

@aryangautam7161 10 ай бұрын

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

@mertsengil4697 4 ай бұрын

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 4 ай бұрын

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.

@VijayasarathyMuthu 10 ай бұрын

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

@drtristanbehrens 10 ай бұрын

Such a cool video!

@陈晓耀 5 ай бұрын

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

@joehenri1 10 ай бұрын

What is the differences between CrewAI and LangGraph ?

@yuripourre 8 ай бұрын

CrewAI is a thin wrapper around langgraph.

@manfyegoh 11 ай бұрын

hi how do i get access to langsmith?

@LangChain 10 ай бұрын

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

@manfyegoh 10 ай бұрын

@@LangChain thanks! i just gotten my access!

@Stormyys 11 ай бұрын

How do we get access to langsmith?

@LangChain 10 ай бұрын

DM Harrison on twitter @hwchase17 :)

@carterjames199 11 ай бұрын

How can I request access to langsmith??

@LangChain 10 ай бұрын

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

@carterjames199 10 ай бұрын

@@LangChain already done he was very fast to reply

@octopusfinds 8 ай бұрын

Thank you!

@Kenykore 11 ай бұрын

Need access to langsmith

@LangChain 10 ай бұрын

DM Harrison on twitter @hwchase17 :)

@googleyoutubechannel8554 10 ай бұрын

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 10 ай бұрын

didn’t they make langsmith exactly for this?

@xfldiazx 7 ай бұрын

@@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

@adamwilfrid3271 11 ай бұрын

requesting for Langsmith access please 😊

@LangChain 10 ай бұрын

DM Harrison on twitter for access @hwchase17 :)

@IAMTHEMUSK 3 ай бұрын

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.