Introduction to AnythingLLM and the Cloud Update
There are many AI tools that let you chat with your large language models and documents. However, there are many privacy concerns with data leaks and exploits. This is where I would like to introduce AnythingLLM as a solution. It's an AI assistant that can transform documents into data for LLMs that is compatible with various vector storages and chat platforms. In short, it's an alternative to private GPT with the ultimate AI chatbot so that you can chat with any large language model, any document, with full control and with full privacy.
Now, I have already made a video about this last year. However, there is a new huge upgrade to the application where there is now a web-hosted app for AnythingLLM, and this is where you can access it through their cloud service. There are many new features like an added functionality that makes it easier to chat with the various large language models and documents. Just take a look at this example where you can add custom knowledge to your chatbot super easily so that you can have it so that the chatbot will have context when it's generating future things based off of your prompts. Now, it also showcases how you can add custom embeddings. So just take a look locally or on a server you maintained.
Demo: Teaching the Chatbot with Website Data
Let's create a workspace that we're going to publish to the world, and I'm just going to name it AnythingLLM. All right, so we're already here, we're started, and if I were to ask this chatbot, just in AnythingLLM, "what is AnythingLLM?" it'll either give me a wrong response or tell me that it doesn't know because our project is not yet big enough for GPT to have scraped it, which is sad. So I'm gonna ask it on an empty workspace, and it says that AnythingLLM is an online platform for basically people pursuing a masters of law. That is not what we are. So let's give it some information, but actually just use our website to fill in those blanks.
The way we do that is we're just going to click on the settings icon, move me out of the way, and I already have a text document embedded in here that is literally just like, "Hey, this is AnythingLLM." I said we're going to grab information from the website, so let's do that.
Embedding Data and Verifying the Context
All right, so our website was pulled in. Now all we need to do is embed it. And you're probably wondering, how am I embedding information? AnythingLLM actually ships with a built-in embedding model that runs on instance totally isolated and privately. That being said, if you want to use OpenAI next Ada embedding or the newest generation, which I believe actually has an even higher dimension output, you can. This is just what we give you for free. So let's go back to the main prompt and ask that same question: What is AnythingLLM?
So here we are asking the question again, and it says that AnythingLLM is the ultimate business intelligence tool, blah blah blah. And it got that information straight from us, anythingllm.com, which is right because it actually is in the tagline, and that is important information. So it looks like our chatbot is pretty much ready to go.
Patreon Benefits Announcement
Sorry for being repetitive, but this month we had insane partnerships with big companies giving out subscriptions to AI tools completely for free. These are tools that will streamline your business's growth and improve your efficiency.
Exclusive Patreon Access and Community
Just being a Patreon this past month, you were given access to seven paid subscriptions completely for free. Not only do you access these subscriptions, but you gain the ability for consulting, networking, collaboration with the community as well as with myself, daily AI news, AI resources and tools, giveaways, and so much more. If you're interested, take a look at the Patreon link in the description below to gain access to these benefits.
AnythingLLM Features and Cloud Service
Now isn't that amazing? This is a tool with endless possibilities as it's aiming to provide you full control and privacy while allowing you to chat with any large language model and any document. Now they've rolled out with their cloud service, and it's currently fully available with the pricing structure. Now if you were actually a Patreon, you would have gotten the chance to access that, so that's something that you should take a look at in the description below as well. But throughout today's video, we're going to be exploring some new features with revolving around AnythingLLM, showcase some of the new capabilities of it, and so much more. So with that thought, guys, stay tuned and let's get straight into the video.
Consulting Services Offer
If you would like to book a one-on-one with me where you can access my consulting services where I can help you grow your business or basically give you a lot of different types of solutions with AI, definitely take a look at the calendar link in the description below.
In-Depth Overview of AnythingLLM
Hey, what is up guys? Welcome back to another YouTube video at The World of AI. In today's video, we're going to be taking a look at AnythingLLM, which is an open-source document chatbot application. This is something that lets you chat with any document as well as any LLM with full customization, with full controllability, as well as with full privacy. Now you're able to have single and multi-user needs. It offers a really nice UI similar to Chat GPT, and there's many things that you can actually do with it, and now you're able to access it on the cloud, so it makes it a little bit easier for many users.
Now, this is a tool that's going to ensure that your document's privacy is 100% ensured. It's utilizing an embedding engine that keeps documents on the local machine or a server, and it's supporting a range of embedding models as well. Now if you are to go over to the documentation, it also gives you a good emphasis on different LLMs that you can select with, shows you the different vector databases, and so much more. This is something that we're going to take a look at as you go further into the video.
Self-Hosting and Deployment Options
So let's just get started and showcase how you can get started. Now if you are to go over to the AnythingLLM GitHub repo, you can then scroll down and once you get to the section where it states self-hosting, it showcases how you can locally install AnythingLLM where you can deploy it with Docker, AWS, GCP, digital ocean, render.com, and you're also able to download and install it for your OS system, which is your operating system, whether that's Windows, Linux or Apple or Mac OS you can say.
Introducing the AnythingLLM Cloud Feature
Now, throughout today's video, we're going to be focusing on AnythingLLM's new update, which is their Cloud feature. This is where you can access everything that we talked about previously on the cloud. And in most cases, many people don't actually know how to install certain things locally, which is why a cloud option would be really beneficial for them because it doesn't require any sort of code and it's quite easy to do so, and it's super easy and convenient.
Now, if you are to click on AnythingLLM Cloud, there's actually a pricing structure that's attached to it. I know this is an open-source project, but that's for installing it locally. To access it on the cloud, you need to pay a little bit because this is where you're going to be hosting the whole application on their server. Now, they come with three different pricing structures. You have Enterprise, you have for a plan for large teams, as well as a plan for smaller teams. Now on our Patreon, we actually gave out the plan for small teams to every Discord member, and this was something that was kind of like a treat for being a part of the Discord. You get access to these subscriptions completely for free. So if you're interested, definitely take a look at the Patreon link in the description below.
Cloud Setup: LLM and Embedding Configuration
Now, once you have registered, you can also have a 3-day trial, but once you have registered with an account or plan, you can then move forward to the dashboard. So I'm going to quickly register and I'll be right back. So once you have subscribed, you're going to be able to see your subscriptions. Now I already have two accounts, but what you want to do is click on your link which is fully hosted on your own instance. Now once you have clicked on it, you can then click Get Started. This is where you're going to be able to pick any sort of large language model that you want to work with. You can choose anyone that you want. In this case, you can even use Hugging Face models that are open source, and you can even select your own model that you have probably fine-tuned on it. You're also able to use it with LM Studio, Local AI, Together AI, as well as many others. So I'm going to quickly choose a model, and I'll be right back.
So I've now inputed my API key for OpenAI. I'm going to then move forward. And in this case, you can see that there is an embedding preference and this is where they say that AnythingLLM can work with many embedding models. This will be the model which turns documents into vectors. So you have a lot of different flexibility with choosing your embedding option.
Cloud Setup: Database, Logo, and User Configuration
This is where you can also use embedding or LLM, which is their embedder. This is the... used the built-in embedding that AnythingLLM actually provides. You can use OpenAI's Azure, OpenAI, as well as Local AI. So I'm just going to actually use AnythingLLM's embedder and then proceed forward. Now in this case, you're also able to use vector database connections where you can implement the connection with Pinecone as well as many of these other vector storages. So I'm going to quickly input my key for all of these or the one that I'm going to be using and then proceed forward. Next, you have the ability to input a custom logo for your chatbot. In this case, I'm just going to use AnythingLLM's because I really don't mind using it, but if you're an enterprise or you're a business, small business, you can use your own logo for the chatbot. So once you have then done that, you can then go over to the user setup. In this case, you need to answer some of the questions where it states that how many people will be using your instance. In this case, it's just me. Will you like to set up a password? No, and then I can continue forward.
Data Privacy and Final Setup Steps
For data handling and privacy, it's going to tell you the transparency as to what is being used as well as showcasing the control of your chatbot. So in this case, you will use OpenAI where your chats will not be used for training. Embedding engine: your document text is embedded privately on the instance of AnythingLLM. And in terms of your vector database, your vectors and document texts are stored privately on the instance of AnythingLLM. And then you can then proceed forward, input your email, specify what you're going to be using it for, and then you can get started. And there we go, we have AnythingLLM set up.
Dashboard Overview and Customization
And what I want you guys to do first is go to the settings tab. And this is where you're able to change certain things. For example, you can change the appearance, take a look at the API keys, LLM preference, you're also able to change the prompt template and prompt settings. And this is by going over to your workflow. And once you have clicked on your workflow, you can create new threads. And this is where these threads are different like chatbots, you can say, that interact with whatever files or context that you give it. So in this case, you can click on the settings tab, you can change the system prompt over there. Now, where do you actually upload your documents? And this is where you can simply just click on this button and you're going to be able to upload your custom documents. You're also able to have the embedding set up over here. You're also able to input different links like we saw previously.
Final Demo and Conclusion
So for example, I can copy my YouTube channel link, I can go back here, paste it, and I can fetch the website. This is where my website content is going to be uploaded over there. I'm going to be then going back to the chatbot. So in this case, it's not finding the URL properly. So the YouTube link wasn't actually working, so I ended up just putting my Patreon link over here and you're going to be able to start chatting with the context that is provided from this Patreon link. And that's basically about it for what you can do with AnythingLLM.
This is a great tool that lets you chat with any large language model and any document. It's super, super safe and it gives you a lot of controllability, as well as there's a huge emphasis on privacy. So I definitely recommend that you take a look at this new upgrade on their cloud service. It's a great way for you to have it hosted on the server that AnythingLLM provides, and it's super cheap to do so. So with that thought, guys, I hope you found this video to be very helpful. This is a great way for you to start chatting and working with your LLMs. I'll leave all these links in the description below. Make sure to take a look at the Patreon link in the description below as well. It's a great way for you to access subscriptions completely for free. Make sure you follow us on Twitter if you haven't already. And lastly, make sure you guys subscribe, turn on notification bell, like this video, and check out previous videos so you can stay up to date with the latest AI news. But with that thought, guys, thank you guys so much for watching, have an amazing day, spread positivity, and I'll see you guys fairly shortly. Peace out, fellas.
