Rivet Ai: Create Complex Ai Agents For FREE Better Than Langflow & Flowise (Installation Guide)

[Music] we have a new method of creating AI agents introducing rivet the IDE for creating complex AI agents prompt chaining and embedding it into your own application now on this channel we have covered multiple types of apps that are used to create AI agents whether it was abacus.ai Chidori or super AGI however rivet differs from all of these types of apps as its focus is primarily on creating more complex AI agents that are designed with an additional toolkit and plugins that are not found with these other apps the great part is is that rivet is fully open source they recently released this to be fully open source which is a game changer for creating AI agents now it has a really nice visual programming environment which we see over here and it also allows you for basic codes to be worked upon with creating different types of Agents now this node-based system basically simplifies the AI creation process which ensures accessibility for individuals with various different types of levels of programming knowledge now rivets ai's core strength lies in its ability to facilitate the design as well as the connection of notes to craft AI agents making it so much more of a valuable tool for both like seasoned AI developers as well as for people who are new and working with AI now rivet flow wise as well as Lang flow are all something that share a visual programming Paragon and this is something that is very powerful but also makes it visually similar in that sense you can see that there's like a drag and drop type of interface in which you can deploy different types of Agents by dragging encoding certain types of applications with another type of app to create a certain type of AI agent now this is something that is very similar with these other applications and it's something that we see with flow wise as well as with line flow but the things that make rivet different is its remote debugability ease of embedding directly in a host application as well as its typescript compatibility and this is overall something that is great to see with rivet as it has more of a functionality in those terms as well as a more customizable way to create these AI agents and this is something that will showcase throughout today's video by demonstrating how you can create a complex AI agent as well as going more in depth with installing this application locally on your desktop so with that thought let's get right into the video hey what is up guys welcome back to another YouTube video at the World by eye as you mentioned at the start we're going to talk a little bit more about what rivet is as it's a complex platform to create different types of AI agents with its IDE it's fully open source and it has a visual AI programming environment which we can see over here now Ribbit offers a unique invaluable feature that distinguishes itself from other AI development tools like Lang flow Abacus AI as well as flow wise now the combination of its node-based system its visual programming environment and the ability to create complex AI agents with additional toolkits and plugins makes it so much more of a versatile platform compared to those other applications and this is something that we're going to Showcase throughout this video in which we're going to show how to create complex AI agents now if you go down a little bit more we're going to talk a little bit more about what AI that rip it is actually about talking a little bit more about why you should use it and going more into that to the installation process as well as the demo of what you can do with this application so with that thought let's get to the next step of the video and where we actually install this locally on our desktop if you guys would like to access our private Discord in Virginia exclusive giveaways exclusive subscriptions to AI applications Partnerships collaboration and so much more definitely take a look at this in the link in the description below if you guys haven't followed world of AI I highly recommend that you do so so you can stay up to date with the latest AI Trends and lastly make sure you guys subscribe turn notification Bell like this video and check out our previous videos as we talk a little bit more about different things in the AI world so with that thought let's get right back into the video to install rivet there's a couple ways in actually doing this you're able to do this through their one-click installer or you can actually install it using the source now I highly recommend that you just stick with the basic way in which they can download it for whatever processor you have so in this case if you have Windows you can just easily go forward and click on the in Windows installation uh like application so in this case I'm going to be showcasing this method but if you are going to be building from The Source it's something uh that you might want to keep in mind is that you need to make sure that you have rust I've node 20 plus make sure that you have yarn you need to make sure that you have these prerequisites installed before you move forward and once you have that done you need to make sure that you have git which is an application that will help you call this repository so what you need to do is copy this code onto your command prompt and once you have cloned this repository go into the rivet folder build the yarn once you have built that you can start running it with yarn depth and you'll be able to open it up onto your localhost and that's basically easy as that but in this case I'm going to be showcasing how to install it with this one click installer so in this case I have windows so I'm going to go on to their actual rivet uh website and then click download for Windows and it'll get the installation I'm going to fully install it and I'll launch it I'll be right back during the installation I have installed its installer I double clicked it once I have done that it says Windows protected your PC but in this case you can just click run away it's completely safe so don't need to worry about this but do it at your own discretion now once you have done that you can click next save it to whatever location file you want to save it towards click next install it and once this is done I'll be right back and I'll launch this fully up and just like that we have fully installed rivet now this is the interface that will be used to create these complex AI agents you're able to run the test run it and as well as deploy it in different areas now we're going to get more into this little while later but we're going to first talk a little bit more about the features so with that thought let's get to the next step and talk about that so why would you actually want to use rivet now one of the main features about this is something that in which you're able to visualize and build using its UI as this amazing application provides you with this visual programming environment and you're able to create these complex AI agents with its complex chains and it's basically utilizing different plugins different types of methods to create these agents with all the different toolkits that are Incorporated with its visual programming environment and this way you're able to easily see as well as work alongside with the actual application to create these complex AI agents another feature is debugging remotely and this is something that gives you a deeper look into its inner workings of the AI application you're having the ability to observe the execution of the prompt chains in your application in real time which is something that is very crucial for identifying and resolving different types of bugs efficiently lastly you have the collaboration feature and this is where rivet promotes this collaboration within your team by representing different graphs in the yaml files so you can basically use any version in them with your team's repository and you could basically work alongside with your team which turns out the projects when creating these AI agents now these are just one of the many types of features but this is why you would want to use this compared to many of these other different types of applications I know this might look a little bit more like graphically Intense or it looks more code intense but if you have a basic knowledge on code I highly recommend that you Jesus because you will have more customer customizable like features as well as more more toolkits like basically design and create different sizes of AI agents compared to like laying floor or like floor wise for example but not saying that they're bad it's just this is gives you more range of tools to basically develop more complex AI agents now I'm going to Showcase one usability someone was actually able to create in their own chatbot in which it responds as a chemist so in this case we can see over here the prompt is that you are an expert chemist find all the mfos mentioned in this context try to make the predictions on their stability as well as have a justification for your answer your output should be in adjacent format do not make up answers and from this prompt they give a context from a Json file and from this Json fault it's exported in a Json format after the chat helped has been generating the responses and this was fully created using a rivet and we can see over here it starts off with the context that's given through a file it is then sent to the chat bot and the chatbot is then basically extracting the Json fault and it is then released in the Json file and this is from the input text you give it the context of what you are going to be responding with as well as the prompt as to what it should do when a response is given to the chatbot and in this case it then utilizes gbt4 model and then it lastly extracts it as adjacent fault and this is just one simple little like agent that was created with rivet but there's so much more you can do with this but it's just a cool way as to what you can do as well as deploy it in different environments now I'm going to be showcasing as to how you can do this with rivet in the next step of the video so what you want to do first is click on the settings tab on the top right go into settings and once you are here here you want to go on open Ai and input your open AI Avi key this will make you utilize the GPT models when executing and creating different types of AI agents now in general you can select different types of themes you have molten theme you have the grapefruit theme as well as the Taffy theme so in this case you can close it and then open it up and you'll be able to see this now let's get to the next step where I'll now showcase how to create your first AI agent now once you're on the interface you can see over here once you have set your API Keys you want to make sure that the executor is on browser you can also change it to node but in this case we're going to have it on browser at this current moment now what you can do while you're working with this AI agent is that once you have created it you can basically go on and basically host it off the debugging localhost URL in which you can work alongside as well as test how the AI agent is off your localhost so if you're basically creating this chatbot you're able to basically chat with it and test out if it's basically creating accurate Generations off the localhost and this is something in which you can run as well as host off the remote debugger and this is something that they set up within the rivet application so that you can easily host it and basically have this remote debugger start working alongside with your AI creation and your AI agents that you just basically deployed now what you want to do first in terms of creating your AI agent is clicking on new graph now you're able to create different types of folders in which you can create different uh like graphs within so in this case I I'm going to name this as a chatbot for I don't know World debate for example this is something that will be responding to World of AI in this case you can right click on your mouse or you can press space to open this up and this is where you're able to build different notes on this UI so in this case I can build a different common text node which could be output a string of text it gives you a demonstration as to what you can do with it in this case you can also do a common chat but on this case I'm going to utilize AI chat and this is a chat node that will utilize the GPC 3.5 turbo model now something that you can also keep in mind is you can tweak this and change it to different other models you're able to play around with the different types of temperatures you can split it in a different way and have different types of splits the node title is over here as well as giving this description over here now this is something I'm just gonna basically create you can have the chatbot respond in a certain type of prompt assemble a different prom so it assigns the chatbot to respond in a certain type of way so now you can have the system prompt Linked UP And this is by putting it over here or you can change it to the prompt now there's different types of configurations in which you can incorporate different nodes you can have different lists uh give you different as the numbers objects data as well as Logics inputs and outputs in which you can have it stored in a different type of storage which is Pinecone over here so you can have different types of outputs linked to over here you're also able to incorporate it and Export it in different types of files which we saw at the start you're able to export it as a Json file and so much more this is just an example guys and I'm just gonna show you a basic user interface on their Channel or on their actual documentation they give a good representation as to how it actually operates to give you a good overview of the interface working with different nodes how to set this up so if you want a more in-depth analysis so what you you can do as well as exporting your grass creating different graphs working with different projects making it collaborable so you can work alongside with different people with the same graph splitting it sub graphs executors recordings incorporating different sets of plugins that are not already there as well as creating your own plugin they have inbuilt plugins you are able to utilize different applications like anthropic and so much more guys this is just the top of what I talked about just I just basically scratched the top of this there's so much more to this so I highly recommend that you check this out but in summary these are some of the small features in which you can use to actually create very powerful and complex AI agents so I highly recommend you check this open source project out as it's something that puts it aside compared to these other AI applications that are used nowadays so with that thought guys thank you guys so much for watching I hope you enjoyed this video and you got some sort of value throughout this video about rivet I'll leave all the links in the description below make sure you check out our patreon page if you want to access our private Discord follow world of AI on Twitter to get the latest AI news and lastly make sure you guys subscribe to notification Bell like this video and check out our previous videos so you can stay up to date with the latest AI news and content but with that thought guys thank you guys so much for watching have an amazing day and I'll see you guys very shortly peace out fellas

Channel: WorldofAI

Views: 43,355

Keywords: rivet.ai, rivet ai, rivet, create complex ai agents, ai agents, auto ai, autonomous ai agents, best autonomous ai agents, Create Complex Ai Agents For FREE, Rivet AI, AI agents, Large Language Models, LLM prompt graphs, visual programming, debugging, collaboration, version control, Ironclad, practical applications, AI development, artificial intelligence, open-source AI, Autonomous ai agents, langchain tutorial, flowise, flowise ai, langflow, ai chatbot

Id: Zd5wjy4YPis

Length: 15min 5sec (905 seconds)

Published: Sat Sep 09 2023