This Isn't Just A Chatbot (OpenAI Should Be Scared...) 

That start with linus is makes my heart drop.

ONLY addition, it HAS to support markdown. Imagine, just setting this to your obsidian vaults folder path and boom, you can chat with your second brain 🤯

Finally one use for my 4080 that doesn't involve crying trying to play cities skylines 2

Hey Theo, just wanted to point out a few inconsistencies. RAG doesn’t train a model, it indexes the text files in a vector database and uses word similarity to look up relevant text. So the model, such as llama2 or mistral is unchanged but it is able to add context and make the retrieved text more conversational. There are loads of great AI/RAG projects other than Ollama out in the git seas too. Many not quite as simple or easy to use though. Thanks for all the great videos. Already subscribed ;)

It's not training the model just doing RAG. Retrieval is basically querying for relevant docs based on semantic similarity basically doing a sql query which a vectors in the where clause

I would consider giving a shoutout to the llamacpp project that serves as the backend engine to many of the open source programs like Ollama, and the many many talented engineers who brought support to so many different systems configurations. The open source scene has been on fire since Llama dropped and running models locally has never been easier.

Finally 🎉 I couldn't wait any longer for ray tracing support in my chat bot GUI

they are not directly using svelte, they are using a project OSS project called Gradio for the UI which uses svelte

This is huge for my wiki. I can just give it a directory of markdown files. 🤯

I never expected to see Freddie Mercury talking about AI

I have to admit, that is the MOST creative L&S I've ever seen on here. And I normally swear at the screen in response. Maybe.

Oh man, was not ready for that intro. I love LTT and your channel, that was a great little combination

While watching this I started to realise how huge usage I would have with this at work. The project I'm in has a huge documentation, but everything is just a brain dump, and there have many times happened that we've found something "new" in the docs that we completely had missed before. Imma work on making an AI on that dataset asap. I love experimenting with AI's locally, it so fun and it feels so much cooler and better then the cloud once

Feedback: Superb video, more AI stuff from you would be great. Specially with open source stuff with our own data.

If you don't want to use it because it's so large, get ollama and you can run it on your command prompt, I recommend watching a tutorial on it, and there's models as little as 1.8 gb (For example, phi 2, which is small yet very powerful)

WSL2 works surprisingly well. I've been using it on one of my machines for SD, llama, and mixtral.

This kind of stuff would be a lifesaver if it manages to work as an AI powered chatbot for documentation for proprietary frameworks and stuff. I'm working at a startup and we're building our own framework from scratch, so having RTX Chat work as an AI documentation assistant would be great

NOT DEEP ENOUGH! MOAR PLZ!

I’ll definitely be checking this out this weekend when I don’t have to work. This looks bad ass!

This is pretty cool, though I'm still waiting for the day that I can use at least GPT-4 level AI locally *(and ideally either for free or a one-time payment for one single version).* Sadly, I doubt this will ever happen outside of opensource projects, which tend to not be as good due to less funding and resources. But I still appreciate any effort put towards that future.

This will be huge when the ai will be capable of parsing a whole project and multiple docs.

The app isn't made with Svelte, but with Gradio. Gradio is a Python library for creating web UIs for ML applications. Gradio, however, uses Svelte and Tailwind internally.

Would love to see more AI content. Great look into this new release from NVIDIA

Deeper, go even deeper!!!

This is like ControlNet for LLMs. Dope.

I did something similar with Pinecone. I parsed a huge chuck of wiki data into a Pinecone DB. I then would use one model prompt which would return multiple pieces of data based on the prompt. That model would then decide which pieces of outside information were the most related to the prompt. It would then send the original prompt along with the external data to a new model prompt which then would provide the response to the user.

Yes, your explanation of RAG was very nice and easy to understand

00:03 and i already saw linus dropping not just something, a graphics card. Instant like! xD

I make 2 points here. 1 questioning the accuracy of this system 2 why windows 1. what's interesting about downloading youtube video transcripts and using those files at 7:40 is that nvidia's setup is MOST LIKELY using their own ASR (Automatic Speech Recognition) model, either Canary or Parakeet, which i've tested and found that theyre good but still not as accurate as open ai's Whisper ASR model. So without knowing what specific model is used to transcribe the youtube videos, we don't know how exact those transcriptions are, so that affects how well this RAG can asnwer questions using that data. I would reccommend using Whisper-Large-v3 and manually transcribing the youtube videos, or just uploading actual documents and notes and testing them rather than transcribing youtube videos. 2. you dont reccommend using WSL but you didnt elaborate. what is the best alternative? installing linux locally or using a cloud workstation? dont say mac because they dont come with nvidia gpu

Nice thing what Nvidia did there :) Do you want to share the two RU-vid Playlists in the comments or description maybe? :D

Ollama just released the Windows preview

Would this work on the codebase for a library? For example inputting a freshly downloaded wordpress directory and then also digesting the wordpresss developer docs to make it your private Q&A tutor for platform you're trying to learn?

Good stuff! Could you make a video on how well it performs as a coding assistant?

I would definitely appreciate more AI content as somebody just getting into web development. It seems pretty apparent that AI is going to unleash a new category of tools, one whose mastery will most likely be paramount to ones success

50% faster inference with nvidia gpus on tensor-rt is no joke, i hope they expand this and let you fine tune and add models

Theo just dropped a 3 min suscribe pitch.

Point it to a playlist of Jonathan Blow videos and then tell it JavaScript is the best language and ask when will Jai have LSP support? Can a LLM can get an aneurysm?

Never thought an AI would convince me to subscribe to someone

2:19 The RU-vid algorithm recommends me your videos frequently. Is there any real benefit I get from subscribing if I'm going to watch your videos and see all your community posts anyway?

Rags are cool, they can use vector databases to map to data.

1:36 "as you can see, it's pretty fast" yes, instant even it would seem

You and Prime need to get with this soon

That would be great for my hundred pages onenote files.

I keep thinking about this video.... RAG is showing up on my timeline on twitter everywhere... I would have had to spend HOURS trying to understand it... let alone realise I could download NVIDIAs demo and run it on my GPU..... Your videos are amazing to understand huge swathes of new AI tech easily... not to mention actually show working tech demos.

A comparison against privateGPT and/or localGPT would've been awesome

Lawyer: AI, find precedence to get my client off the hook for drunk in public. AI: Beep, bop... Bort - Say it was diabetes related.

I love it! I find this stuff fascinating

Good stuff..liked and subbed.

Already been using this, I have also wired up ollama to serve multiple requests and I run a business off it now.

The models you can run on chat with RTX are a bit inadequate right now. But it shows promise

Finally when someone says "when did i say that !! Huh" I can go. If this video on this date at this timestamp. Checkmate

Ok... this is really really cool!

Keep in mind that Chat with RTX bundles a 7B parameter model, which will consume GPU memory during use. Inference is going to be painfully slow if you're running a weaker gpu. Responses from this model aren't going to be at par with GPT4/Claude. If you're looking to chat with your own documents, paying for an OpenAI API key w. langchain RAG implementation is the more efficient way to go.

'Nvidia just dropped' linus clip is CRAZY

Crazy... it's hard to keep up. And now there's Groq.. which is ridiculously fast.

The main downside of this program is it only parses one file at a time, even if you have multiple files with data. Kinda meh if you need to do comparisons or use one file as a context to process the second.

If you’re impressed by these chatbots or ChatGPT than you really have low expectations. These models can’t connect specific data to each other or had the awareness to understand between the lines implied logic or data, or instruction. I’ve tried training them on a particular set and it still fails or returns incorrect data that would have massive implications to serious situations. It’s got years upon years to go before these things can really be reliable.

I wonder if you could train your language model to play a game on your behalf, such as Cyberpunk, for example of course. It seems feasible, as some local language models are equipped with vision capabilities. It would be fascinating to witness the first RU-vidr attempting this."

MOAR AI. The solution to having a job with AI is knowing how to use it

I feel like this one is kind of overhyped, like why does it show the whole conversation history when it can't even see your previous messages

I can get a little more specific on a topic with chat with rtx. Compared to chatgpt.

This is the future. There's so many AI integrations dropping. The possibilities are getting out of hand.

Linus intro is on point, Theo!

Definitely on team AI deep dive!

I would be excited about AI if people would stop at chat bots, but we won't. It will get from "cool chat bot" to "AGI existential dread" real quick.

Here's hoping more and more AI things move to have local options. Sure not everyone can run these locally, I am typing this on an iMac from 2015... BUT it is super promising.

As far as I’m aware, Meta has nothing to do with Ollama. Ollama can run Meta’s OS models though.

Maybe “trt-llm-rag-windows” implies maybe there will be a Linux or MacOS version someday. 🤔

We are beyond what you are excited about here ... This does not cut it anymore in a post ChatGPT world man ... What is the use case for this ?

I wonder how large a single text can be for this to work. Can I throw whole books at it? What about my states entire law code?

the RU-vid option isn't showing up on my rtxchat

8:17 for some reason the Dutch public news broadcaster also uses svelte sometimes lmao

This is a good video. Just wish you could run this on Linux....with a AMD card.....heh

you can so RAG with ollama when you run ollama-webui

what is vram for RAG or their version of it

Okay this is something I'm trying to learn. For the record I'm not a programmer just an enthusiast trying to learn stuff kind of a dummy Compared to you all probably. But what do you guys think of Pinocchio I've gotten llama to run through it but it doesn't always run And there's not very many good tutorials on Pinocchio . I would love it to be covered on this channel. just what you think of it? And other insights if possible. Anything I really can find on it is very basic and only gets you so far. Weird comment I know. like the channel always some great insights.

How did he get Nvidia RTX in the browser?

facebook actually making progress in the AI scene…

I will never understand how Meta's OS side can be so good, while their business side is always being so predatory.

I'm confused here, There are a ton of vector databases that you can install and run on a Mac. No external GPU needed. Like Chromadb, or Faise. Then just use something like llamaindex or langchain to chunk your documents and create embeddings using something like openai's ada2. Then insert them into chroma and starting doing rag on your documents. You certainly don't need an Nvidia GPU.

PrivateGPT is doing something similar to this.

Could you make a small RAG project :-)? Or do you have a channel who is like the theo of open source LLMs?

What’s the advantage over privateer that’s been out for months where you can choose your own model and it is tiny in comparison?

Damn, that's impressive.

This is going to give another moat to Windows devices over Mac and Linux devices

Can be good for learning, Could point it to some programming books I have so I can "chat" with them 😂

Fine fine I'll subscribe.

more Ai. definitely. as devs we need to stay on top of this stuff. the war against the machines has begun my friends and we're on the front lines.

RAG systems are table stakes now and not to hard build your own. Also, it’s pronounced “rag” not “R.A.G”

Nvidia should be freaking out over Groq

Brooo what an opening ❤❤😂

Tell me you have no idea about AI, without telling me you have no idea about AI ... There are so many great AI models, tools, libraries and projects and you choose to promote some uninspired windows release by NVIDIA 🧐OpenAI should be scared but surely not of this library! "Somewhere between traditional lookup with a GPT and training your own Models from scratch", "Its pretrained on a bunch of data", "TensorFlowRT" .... Seriously @theo I very much appreciate your content on WebDev, but please stick to what you actually know and dont fall into the hype trap of having to do AI content becaue it gnerates clicks. And you even got the svelte part kinda wrong... which falls in your alley of expertise!

So, you're gonna need an Nvidia RTX-capable card (30xx is fine) and it'll need at least 7GB vram, so maybe your laptop might struggle. Really interesting app. Super simple to install and run. It's quite the killer app for a demo 😅 some start-ups and their investors somewhere are gonna be sweating bullets. 😂

If all of the python docs were fed to an LLM model, would you use query that LLM model or still refer to the original docs?

I wanna point that folder at my current project im working on. or a massive archive or python code lol...

Good now, I can just get the point of youtube videos by putting them into Nvidea cuts out all the fluff

Woah woah woah it’s only fast because of your laptop hardware lol M1 - M4 chip?

I'm curious how good it is at code

Why would you not recommend running ollama on WSL right now

I've tried but it's a bit strange and slow and I didn't find how to start again after shutting down