Oh Sam, thank you so so much. This solution is crazy simple. The agent never enters in loops unlike the solution I develop with pure langchain. The agent used to get stuck in loops when asking simple questions like hi or hello Thanks again
HI sam , we hope to work more closely with open source models such llama3, command R some of this technique not working with such this models and need some of customisations we need to reuse this concepts with open source models and thanks a lot ❣️
Hi Sam, please provide a video about the SQL agent that manages fields with high cardinality to generate the correct query in Langgraph, improving even the ones uploaded in the oficial documentation
Great video! I've been following your channel to learn LangGraph. I've watched your previous videos on LangGraph and have learned a lot. Could you please revisit one of your older projects using this new method? It would help us understand it better.
Thanks Sam, great video! One doubt I still have about ReAct agents in langgraph is the "component" that makes the LLM to think in the ReAct style. In the ReAct paper, the prompt instructs the LLM to think, act and observe. However in this example I don't see any of these instructions. Where are they "hidden" in this version with Langgraph?
yeah I pointed this out in the video that they aren't using the standard prompts. You could put that in in there if you wanted. With Function Calling / Tool use and much better models we have today you don't need it as much, but for anything serious I would massively tune that prompt in the reasoner
I tried this with groq free api mixtral model... and i faced issues as the search tool didnt get the age sometimes.. so I have to change the prompt..."You are a helpful assistant tasked with using search and performing arithmetic on a set of inputs. you are only allowed to use the tools add, multiply, divide and search. repeat the tool until you think you got the expected output"
At a low level, CrewAI is using a lot of things like this from LangGraph and LangChain and other agent frameworks. The big difference is that CrewAI is not on a guided flow as strictly as something like LangGraph is.
Nice tutorial as always Sam! Some months ago I tried to use this approach of one node for reasoning and one for tool calling but the LLM always went nuts. It iterates over and over with the same tool. Is there a way to control how many times the agent can call a tool or how many times it can iterate the tool node before saying “I don’t know”?
How to use it as a subgraph? Do I need a router? For example if I want to isolate heavy function calls from the main agent history? Is making it a tool an option? Can it have its own messages and state and be reset when it finishes processing like a subgraph?
This is a really good idea. A number of people have asked for this, so I'll make something with showing off subgraphs and how you could use this kind of style for a subgraph.
Hey Sam , very good video ! I was wondering if I can help you with more Quality Editing in your videos and make Highly Engaging Thumbnails which will help your videos to get more views and engagement . Please let me know what do you think ?
I have been trying too many frameworks some of them looks over engineered including Langraph, you don't really have control on what's under the hood specially when you are using less capable models, I'm trying Phidata as a small library that just work yet flexible enough for most basic tasks. Can you make a video on how to use it to make an autonomous agents ?
Oh Sam, thank you so so much. This solution is crazy simple. The agent never enters in loops unlike the solution I develop with pure langchain. The agent used to get stuck in loops when asking simple questions like hi or hello
Thanks again
HI sam , we hope to work more closely with open source models such llama3, command R some of this technique not working with such this models and need some of customisations we need to reuse this concepts with open source models and thanks a lot ❣️
Hi Sam, please provide a video about the SQL agent that manages fields with high cardinality to generate the correct query in Langgraph, improving even the ones uploaded in the oficial documentation
do you have a dataset, I can't use client data for tutorials etc
@@samwitteveenai yes i do, want it to practice?
Great video! I've been following your channel to learn LangGraph. I've watched your previous videos on LangGraph and have learned a lot. Could you please revisit one of your older projects using this new method? It would help us understand it better.
Great Content! This was super helpful!
Great stuff! Well done on the presentation.
Great ! , i was able to swap the prompt and test it , great learning ...
Thanks Sam, great video!
One doubt I still have about ReAct agents in langgraph is the "component" that makes the LLM to think in the ReAct style. In the ReAct paper, the prompt instructs the LLM to think, act and observe. However in this example I don't see any of these instructions. Where are they "hidden" in this version with Langgraph?
yeah I pointed this out in the video that they aren't using the standard prompts. You could put that in in there if you wanted. With Function Calling / Tool use and much better models we have today you don't need it as much, but for anything serious I would massively tune that prompt in the reasoner
thanks man ...keep on the great work
I tried this with groq free api mixtral model... and i faced issues as the search tool didnt get the age sometimes.. so I have to change the prompt..."You are a helpful assistant tasked with using search and performing arithmetic on a set of inputs. you are only allowed to use the tools add, multiply, divide and search. repeat the tool until you think you got the expected output"
yes certainly different models will respond to differently prompts. thanks for sharing that one
What a great explanation, thank you
Very nice work, as always, thank you.
This is very helpful!
Thanks Sam! Can you do a comparison of this model to a multi-agent framework like crewAI?
At a low level, CrewAI is using a lot of things like this from LangGraph and LangChain and other agent frameworks. The big difference is that CrewAI is not on a guided flow as strictly as something like LangGraph is.
Very interesting and thanks for the code. I tried modifying your code to build code assistant agent. How to add human in the loop ?
what if you have math node with math tools and search tool separate as a node? you cant bind llm. how to approach this?
Thanks Sam.
It is a better alternative than o1 model of openAI!
thanks man, what about using this reasoner to supervise agents instead of tools?
Good idea, I think I'll make something about controlling subgraphs with Reasoner.
Nice tutorial as always Sam! Some months ago I tried to use this approach of one node for reasoning and one for tool calling but the LLM always went nuts. It iterates over and over with the same tool. Is there a way to control how many times the agent can call a tool or how many times it can iterate the tool node before saying “I don’t know”?
How to use it as a subgraph? Do I need a router? For example if I want to isolate heavy function calls from the main agent history? Is making it a tool an option? Can it have its own messages and state and be reset when it finishes processing like a subgraph?
This is a really good idea. A number of people have asked for this, so I'll make something with showing off subgraphs and how you could use this kind of style for a subgraph.
great content! thanks!!
thanks
Hey Sam , very good video ! I was wondering if I can help you with more Quality Editing in your videos and make Highly Engaging Thumbnails which will help your videos to get more views and engagement . Please let me know what do you think ?
I have been trying too many frameworks some of them looks over engineered including Langraph, you don't really have control on what's under the hood specially when you are using less capable models, I'm trying Phidata as a small library that just work yet flexible enough for most basic tasks. Can you make a video on how to use it to make an autonomous agents ?
Can anyone share some langgraph projects which can help me land some job or freelance work?
What happens if the history becomes so large that it falls outside the models context window?
We can trim the history pretty easily, maybe I'll do a video about that soon.
@@samwitteveenai yes but then you’d lose valuable context and the model would “forget” stuff.
i might try to implement this without langraph... langchain shitty library and langraph is just a state transition library with some weird abstraction
I don't totally disagree with you. I do have some agents vids coming with no frameworks used