FREE PhiData AI Agent UI Framework Open Source!🤖 Beats CrewAI & AutoGen?? Memory Tools Vector Stores

What's going on everybody Josh pook here and in today's video we're going to be taking a look at a very cool AI agent framework called fi data and this one is definitely very unique opposed to some of the other Frameworks that we covered because this is the first framework that I've personally seen where you're able to build AI agents with memory knowledge tools and reasoning all open source and all within a beautiful UI interface a playground feature as well as a

Cookbook with pre-made agents that you you can just plug and play and get things rolling right away I'm going to show you how you can set it up by the time you're done watching this video Let's dive right into [Music] it all right so lately we've covered a lot of different AI agents and AI agent Frameworks on this channel and in today's video we're going to be covering and in today's video we're going to be covering something that's a little bit

Different so fi data is essentially a platform where you can build ship Monitor full stack agentic software every agentic system needs a database Vector database and an API bu datas full stack templates take you from zero to production in minutes and I really do believe that this is a gold mine when it comes to building AI agents with pre-made templates you know a full stack solution that can really take you from Zero to Hero when it comes to getting things up

And running quickly this will allow you to easily build domain specific agents using the most powerful AI framework according to them on the market and you can use any single llm including local models you can ship so deploy your agents using templates preconfigured with Vector databases and apis they say bring your own cloud and let us handle the devops and then you can monitor runs tokens quality evaluate optimize and improve your agents over time and the beautiful thing is that it

Is open source and the pricing right here is pretty much the free plan so free frame workor for building agents you can check it out right here I think they are coming out with a pro and Enterprise plan but at the moment you can do everything with the open source framework which is really really nice and don't get me wrong I love personally building AI agents with tools like crew AI autogen whatever the case may be but sometimes it's nice to

Just have a nice UI interface and personally this is something that I even thought of creating for myself and now I see that fi data has already done that at least for their own AI framework and I really like their cookbook which we're going to dive into in a second where you can easily just plug and play some pretty cool pre-made agents into their system and start using it right now all right so I'll leave a link to their GitHub as

Well as their website in the description down below where do we start well first things first is you're going to go ahead and click on try demo that's going to take you to the login page and you're going to want to create an account you can do so with GitHub or Google once you do that you're going to be in the FI data dashboard okay so you're going to see dashboard sessions playground settings API key a bunch of different stuff and

Dashboard is where you can view all your analytics session is where you can see your session history playground is where you can test out the different agents settings you can change some of the settings and then API key is what we're going to go to first you're going to click on that and you're going to want to copy your API key and save that for later so when you first get in here you'll see the endpoint is pointing to WS demo

Agents okay you'll see here I also have Local Host 7777 once we set things up you'll have that as well if you want to play around with the demo agents you can do so you can test out the different Agents from web search research agent Finance agent and you'll be able to see over here in the config the different tools they have the storage they may have the knowledge the description of the agent the instructions every single thing surrounding each individual

Agent will be shown here in the config as well as the history with the agent so now that you have your API key we're going to go over to the doc section right here and the docs are very extensive I would recommend checking out the docks looking at the different capabilities because there's a lot of different cool things you can do with this tool are you tired of pouring thousands of dollars into appointment CS only to watch leads slip away imagine

Having a team of elite sales agents booking qualified appointments for you around the clock no more wasted time on training no more frustration with performance and no more draining your budget on inconsistent and expensive call centers introducing stride agents AI powered appointment centers that work 24/7 never get tired and book appointments while you sleep trained on thousands of successful conversations our AI agents El performed human teams at just one tenth of the cost join the ranks of businesses that doubled their

Appointments and booking rates in just a matter of weeks don't get left behind in the AI Revolution visit stride agents.com now and transform your entire sales process with cuttingedge AI techn techology it's time to accelerate your stride with AI agents all right so here's what you're going to do you're going to go to the cookbook documentation right here which I'll leave a link in the description and then you're going to fork and clone the FI data repo so actually we're just

Going to run get clone right here so get clone by data right here once you run that in whatever directory you want to clone it to you're going to change directory into fi data okay so you're going to run CD fi data from that point on you're going to create a virtual environment so depending on if you're on Mac you can run that command or if you're on Windows you can run this Command right here so python create your virtual environment

And then activate your virtual environment now another thing you're going to want to do is you're going to want to open up the repository in cursor or vs code or whatever IDE you want to use you're going to want to open that up all right so as you can see here I have the FI data repo I'm going to open that and then you're going to want to go to the cookbook directory and then click on the playground directory okay from

This point on you're going to want to click on the read me okay and then I'm just going to click control shift V so I can see the markdown file in this way and here you'll see basically some of the initial steps that we just did such as creating the virtual environment then you're going to want to export your API Keys all right so if you're on Mac or Linux you can run this command and if you're on Windows you can

Run it like this where it's set X open AI AP I key and then your API key right here so you can reference The cookbook if needed now you may be wondering what is EXA API key now you may already have one or maybe you don't know what EXA is well if we go to EXA right here we can see it is the search engine for AI the EXA API finds the best content on the web using embeddings so what you're

Going to want to do is go to xa. a and I'll leave a link down below and you're going to want to click on use our API now you may be wondering Josh I don't want to pay for another API well don't worry this one gives you $30 in free credits when you sign up so once you sign up for EXA there's going to be a little onboarding section down here where there's five steps you have to do just simply complete

Those five steps takes about 2 minutes and then you'll see right here I have $30 preloaded I haven't even added my credit card so you're going to want to click on API keys right here and you're going to want to copy your API key and then export it into your environment variable all right so you should have your open AI API key and your exit API key exported into your environment variables now you're going to want to install these libraries right

Here so pip install open AI EXA dock Dogo Yahoo finance and all these other ones right here so you're just going to Simply copy this command and run it after those install you're going to want to authenticate with Fi dat. apppp okay so you can simply just run this F off right here all right so I just ran the command and you'll see a browser will open at this link which is right here and I actually already authenticated with Fi but

You're just going to Simply log in and then it's going to redirect you back here and then once you authenticate you're going to want to connect open aai agents to the agent UI so make sure you're in the right directory and simply just run this command python cookbook slayground slemo dopy or you could just change directory to cookbook playground and then just run python demo. as a side note you can also see here there's fully l olama agents right here as

Well as grock agents as well as if you look in the cookbook here you'll see a bunch of different agents we have agentic rag agents with PG Vector we have basic stream agents basic rag Finance agent data analysis agent generate video generate image personalized memories SQL light storage web search there's a lot of different agents in this cookbook and a lot of cool things that can help you get going right away and you can take different ideas from different agents and

Make your own AI agent for your personal needs all right so once you run the python demo. py file you'll see that the playground has started at localhost 7777 but you're going to have to access it at this URL right here so don't go to Local Host 777 you have to go through the FI data app version of The Local Host 777 all right so now when you go to this app here you'll see that the endpoint we had our old

Demo agents but we also have Local Host right here and this is the one we're going to want to use now you can see we have all these different agents in that demo file so you can take a look at the demo file I'm not going to go through the whole thing here but you can see here we're importing different things importing dally duck ducko EXA right here and we're creating our different agents so we have our web agent we have

The different tools the rules the instructions the storage SQL agent storage we have our finance agent we have our image agent our research agent and you can see the different instruction description all the different configurations and you can definitely tweak this or make it your own or duplicate this and then run it again and we even have a YouTube agent here so the really nice thing here is if I click on any single agent you know first of all you don't

Have to write any single code if you don't want to but this cookbook gives you a really good starting point if you pair it with something like cursor you could easily get some really powerful agents that are accustomed to your use case without having to know too much about python or writing or building Agents from scratch and then you can go to this beautiful web UI and you can click on any one of these agents and then you can see the

Different tools that they have access to you can see the storage or the knowledge all the different configurations in one central location which makes it really nice all right so here I'm saying get Microsoft stock price recent news company info and analyst recommendations please we're going to send that and now we can see our agent going to work you can see it got the current stock price at $418 us the company info the symbol the sector the industry market cap the

Analyst recommendations period strong buy buy wholesale all that good stuff and then even recent news with links to the news better AI stocks Microsoft first Lumen Tech right three different top news articles we could ask for more of course and then we can see the history with this specific agent and one thing I'll also mention too is that fi data isn't tracking this data there is a way that you could enable that feature but by default it's turned off so that

Means when you're running the agent and let's say you wanted to delete all the data that's locally stored on your device you could simply just come down here to whatever agent dat database that you have and you could just simply delete this and then it wouldn't be showing your recent history here in the actual playground all right so here's the web agent I'm going to say please search for the recent AI news today on October 21st 2024 all right so it's

Pulling this straight from Duck Dogo we got perplexity AI start startup controversy we got X's new terms and service for AI training all these different ones right here of course we could ask for more but it pulled the top five all right so now we're going to try the research agent which is using search with EXA and you can see the different instructions here so for the provided topic run three different searches read the results carefully and prefare a New York

Times worthy article and then focus on facts and make sure to provide references so I'm saying Deep dive into scaling laws for AI explain in depth wow look at this we're getting a New York Times the article right here sort of like perplexity as you can see here um you got overview what are scaling laws the mechanism behind scaling laws recent Trends and AI scaling laws challenges considerations and then references down below all right now let's try the image agent so

I'm going to say generate an image of a bear eating a pink cookie all right so here we go first picture was kind of blurry I think it kind of glitched out here I said make it bigger and clearer and boom we got a nice cartoon bear right here eating a pink cookie look at that like that's pretty damn good all right so lastly we're going to try the YouTube agent so I'm going to copy one of my videos right here

And I'm going to paste it right in here and you can see the tools it has access to are getting the video captions and then getting the YouTube video data so I'm saying summarize this video and get me all the analytic data around this video all right so it's using both those tools we can see here the summary of the video which is accurate because it's getting the captions of the video and then the video metadata okay so it's the metadata

It isn't the analytics data but it got the title The author the author URL and all that good stuff so it worked pretty well and I'm definitely going to be improving upon this YouTube agent as well as some of the other agents like adding additional tools maybe adding some memory some knowledge changing some of the prompts I'm really excited to start using and customizing fi data let me know what you guys think about fi data and I'll leave fi data's YouTube

Channel down below where you can check out some of their videos around fi data and agent UI right here and I'm really excited to see where they actually take this tool I know they probably have a lot of cool things coming and I think some of the other AI Frameworks may start coming out with something similar in terms of the UI or maybe someone else will come up with a UI for some of these big Frameworks and then open source it

As well so I think it's really only a matter of time like I said I love putting together agents in Python and seeing them run and do cool things but I think something is really cool and to be said about the playground feature they have and the UI I think it's really nice as well as having data and dashboard and tracking all within one Central place that can be local on your system and can use any llm model I think this

Is definitely an extremely valuable resource like I said I would really recommend checking out their docks as well as their cookbook in the repo and seeing all the different templates and getting all different ideas from what they've already built for you but other than that guys let me know what your thoughts are down below surrounding fi data you think this is a cool tool have you used it before or do you have some issues with it let me know what your

Thoughts are down below and how do you think it compares to some of the other AI Frameworks out there other than that guys if you're new to the channel we upload videos every day on AI Marketing sales business growth Etc so if you're new here you got some value make sure to like the video comment down below and smash that subscribe button to stay up to date with the daily uploads also too guys if you haven't already joined our free community

Stric community.com I'll leave a link down below you can join our free Facebook group and Discord Channel and then also too guys if you run a business and you need help with marketing Sales Systems automations or integrating ai ai agents into your business then definitely check out the first link in the description down below and book a call with my team and we can see if there's any way we could potentially help you or not other than that guys thank you

So much for the recent 9k subscribers I'm really grateful like I said once again to everyone who watches these videos I will see you in tomorrow's video guys keep hustling keep grinding and of course accelerate your stride take care