![Underfitted](/img/default-banner.jpg)
- 51
- 827 138
Underfitted
United States
Registrace 11. 02. 2011
I tell stories about Artificial Intelligence.
An introduction to Mojo (for Python developers)
This is an unconventional introduction to Mojo. I'll start with a Python script, port it to Mojo, and finish with an implementation that's 20 times faster than the initial code.
Mojo is incredible!
Here is the GitHub repository where you'll find the code in this video: github.com/svpino/mojo/
I teach a live, interactive program that'll help you build production-ready Machine Learning systems from the ground up. Check it out here:
www.ml.school
To keep up with my content:
• Twitter/X: svpino
• LinkedIn: www.linkedin.com/in/svpino
🔔 Subscribe for more stories: www.youtube.com/@underfitted?sub_confirmation=1
Mojo is incredible!
Here is the GitHub repository where you'll find the code in this video: github.com/svpino/mojo/
I teach a live, interactive program that'll help you build production-ready Machine Learning systems from the ground up. Check it out here:
www.ml.school
To keep up with my content:
• Twitter/X: svpino
• LinkedIn: www.linkedin.com/in/svpino
🔔 Subscribe for more stories: www.youtube.com/@underfitted?sub_confirmation=1
zhlédnutí: 1 625
Video
How to build a real-time AI assistant (with voice and vision)
zhlédnutí 6KPřed dnem
This is a new version of my AI assistant, this time using LiveKit (livekit.io.) This is the same platform OpenAI used to build their ChatGPT assistant. The source code of my example is here: github.com/svpino/livekit-assistant. I teach a live, interactive program that'll help you build production-ready Machine Learning systems from the ground up. Check it out here: www.ml.school To keep up with...
A Machine Learning roadmap (the one I recommend to my students)
zhlédnutí 4,6KPřed 14 dny
The books I shared in the video: * Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: amzn.to/4b2bMBj * Deep Learning with Python: amzn.to/3Xifh3x * Machine Learning with PyTorch and Scikit-Learn: amzn.to/3VyTXpb * Generative AI with LangChain: amzn.to/3KBQCzj I teach a live, interactive program that'll help you build production-ready Machine Learning systems from the ground up...
Why are vector databases so FAST?
zhlédnutí 11KPřed 14 dny
Vector databases are fascinating, and I'm surprised more people aren't talking about what makes them so fast. You can use a vector database to store arrays of floating-point numbers. You can then search the database using a similarity function to return any vector that's similar to another one. This video will show you how these databases work behind the scenes and how you can use serverless Pi...
Building an AI assistant that listens and sees the world (Step by step tutorial)
zhlédnutí 7KPřed 21 dnem
I built an AI assistant that listens to my commands and uses my webcam to understand the world around me. I used Python to build it, and this video will give you a step-by-step overview of how it works. Here is the link to the source code: github.com/svpino/alloy-voice-assistant I teach a live, interactive program that'll help you build production-ready Machine Learning systems from the ground ...
How to train a model to generate image embeddings from scratch
zhlédnutí 7KPřed měsícem
Embeddings are one of the fundamental building blocks behind Large Language Models. I built a simple model to generate image embeddings. This video will help you understand embeddings from first principles. I don’t use transformers or anything fancy. Instead, I build a simple Siamese Network step by step, and train it using contrastive loss. Link to the code in the video: github.com/svpino/cont...
How to run PyTorch, TensorFlow, and JAX on your Mac (Apple Silicon)
zhlédnutí 9KPřed měsícem
Link with instructions and code: github.com/svpino/apple-silicon/tree/main I teach a live, interactive program that'll help you build production-ready Machine Learning systems from the ground up. Check it out here: www.ml.school To keep up with my content: • Twitter/X: svpino • LinkedIn: www.linkedin.com/in/svpino 🔔 Subscribe for more stories: www.youtube.com/@underfitted?sub_confir...
I deployed a recommendation model. Testing Models In Production using Interleaving Experiments.
zhlédnutí 1,5KPřed měsícem
I teach a live, interactive program that'll help you build production-ready Machine Learning systems from the ground up. Check it out here: www.ml.school To keep up with my content: • Twitter/X: svpino • LinkedIn: www.linkedin.com/in/svpino 🔔 Subscribe for more stories: www.youtube.com/@underfitted?sub_confirmation=1
I used the first AI Software Engineer for a week. This is happening.
zhlédnutí 17KPřed měsícem
I teach a live, interactive program that'll help you build production-ready Machine Learning systems from the ground up. Check it out here: www.ml.school To keep up with my content: • Twitter/X: svpino • LinkedIn: www.linkedin.com/in/svpino
I built a simple game using Langchain. Here is a step by step tutorial.
zhlédnutí 4,6KPřed měsícem
I built a simple game using Langchain and a few large language models. One model plays against the other. It's a great way to learn how to use open-source models. Source code of this example: github.com/svpino/llm/blob/main/guessing/guessing.ipynb I teach a live, interactive program that'll help you build production-ready Machine Learning systems from the ground up. Check it out here: www.ml.sc...
Step by step no-code RAG application using Langflow.
zhlédnutí 13KPřed 2 měsíci
Source code of this example: github.com/svpino/llm/tree/main/langflow Lanflow's GitHub Repository: bit.ly/3JcNXeC Astra Vectorstore database: dtsx.io/4aw3x17 I teach a live, interactive program that'll help you build production-ready Machine Learning systems from the ground up. Check it out here: www.ml.school To keep up with my content: • Twitter/X: svpino • LinkedIn: www.linkedin....
How to evaluate an LLM-powered RAG application automatically.
zhlédnutí 12KPřed 3 měsíci
Source code of this example: github.com/svpino/llm/tree/main/evaluation Giskard library: github.com/Giskard-AI/giskard I teach a live, interactive program that'll help you build production-ready machine learning systems from the ground up. Check it out here: www.ml.school To keep up with the content I create: • Twitter/X: svpino • LinkedIn: www.linkedin.com/in/svpino
Building a RAG application using open-source models (Asking questions from a PDF using Llama2)
zhlédnutí 51KPřed 3 měsíci
GitHub Repository: github.com/svpino/llm I teach a live, interactive program that'll help you build production-ready machine learning systems from the ground up. Check it out at www.ml.school. Twitter/X: svpino
Building a RAG application from scratch using Python, LangChain, and the OpenAI API
zhlédnutí 58KPřed 3 měsíci
GitHub Repository: github.com/svpino/youtube-rag I teach a live, interactive program that'll help you build production-ready machine learning systems from the ground up. Check it out at www.ml.school. Twitter/X: svpino
How much should you charge hourly as a Machine Learning freelancer?
zhlédnutí 3KPřed 5 měsíci
I teach a hard-core Machine Learning Engineer program. It's live. It's tough. It's different from everything else you've seen. Check it out at www.ml.school 🔔 Subscribe for more stories: www.youtube.com/@underfitted?sub_confirmation=1 Twitter: svpino
People are divided! Does GPT-4 understand what it says?
zhlédnutí 1,3KPřed rokem
People are divided! Does GPT-4 understand what it says?
The 3 most important updates to OpenAI's API.
zhlédnutí 1,6KPřed rokem
The 3 most important updates to OpenAI's API.
We just discovered faster sorting algorithms!
zhlédnutí 7KPřed rokem
We just discovered faster sorting algorithms!
5 problems when using a Large Language Model
zhlédnutí 2KPřed rokem
5 problems when using a Large Language Model
Solving complex tasks using a Large Language Model (LLM)
zhlédnutí 3KPřed rokem
Solving complex tasks using a Large Language Model (LLM)
We integrated OpenAI's Whisper with Spot
zhlédnutí 3,2KPřed rokem
We integrated OpenAI's Whisper with Spot
How to 10x your productivity with ChatGPT?
zhlédnutí 10KPřed rokem
How to 10x your productivity with ChatGPT?
Can you become a Data Scientist without a Ph.D?
zhlédnutí 3,8KPřed rokem
Can you become a Data Scientist without a Ph.D?
Superhuman AI Cracked An Impossible Game! | DeepNash, Explained
zhlédnutí 6KPřed rokem
Superhuman AI Cracked An Impossible Game! | DeepNash, Explained
The Simplest Encoding You’ve Never Heard Of
zhlédnutí 3,5KPřed rokem
The Simplest Encoding You’ve Never Heard Of
But how to center a div?
Your explanation is amazing ... Can I use 11labs voice here ?
Amazing content with solid explanation. Thanks very much 👏
Worth mentioning that the original python module could have been run in Mojo. Your mojo program should work with something like: ``` from python import Python fn main() raises: Python.add_to_path(".") # the file path to the directory with the python module you want var search = Python.import_module("search") # this is how you import a Python Module search.main() # running the python module function as you'd expect ``` TBF, you're likely going to see the most dramatic performance increases from pure Mojo.
Yes. I wanted to do the “translation” for the extra gains
Awesome Underfitted!
Hey I have a issue with key api livekit its telling me error like its invalid
Hi, great video! How to change the source code that it captures my screen, desktop. Thanks.
Thank you, It is very interesting.
Curious about the latency. I noticed that you cut the video after each question (after 19:55), so I am assuming it was a few seconds?
It wasn’t bad, but GPT-4o is not as fast as it could be, so you definitely have to wait a second or so for an answer
Hola Santiago saludos desde Cuba, acabo de ver en su perfil de Github que es un coterráneo. Su contenido es muy valioso, por aquí un ingeniero de IA tratando de salir adelante en este mundo. Me encantaría poder contactar con usted y ayudarle en algún proyecto.
Does mojo support dynamic dictionaries? Or do you have to specify the value's type? I want a faster python but I don't want everything pydantic Thanks for the video ❤
Thanks for correcting the info there Santi! Eager to see more mojo videos, but with the 🔥 instead of .mojo 😅. Good work man 🙏
Yeah I need to start using the emoji extension
The first one was great. This one was just as great !
Thanks! I made a mistake before, so decided to fix it here.
what was wrong with the last one 🤔
I made a big mistake by not using the output of the function, so Mojo didn’t call it. That’s why is was so crazy fast.
@@underfitted at that time I was really got shocked how it can be that fast. But as everyone will agree we are still wondering because it’s still much faster than python.
sir can you help me why my assistant isnt talking back or nothings happening but its recognising in chat what im saying
Can I use newer Python version (like 3.11.3)?
I think yes, but you should try
Really cool stuff... I def plan to recreate some of these things along with you when I have a bit more time at my computer. Just a thought, adding screen capture in with this would be pretty cool too to get help with whatever applications you're in... I would imagine you could include both camera and screenshot images in the same context and it should be able to distinguish which you're asking about.. or build a different tool that it can function call for that. Can't wait until we get some slightly more expressive voices as an option like OpenAI teased us with.
What books do you recommend to get started with NLP?
obrigado, fantástico o vídeo 👏👏👏👏👏👏👏👏👏
so i cannaot code can you make toturial for using ph3 which is free and have vision and also use visper ai to convert text to speech and other free tools so minimizing the cost to completely zero I am a student trying out these stuff and don't wanna pay or don't have money to pay for the API or other things so please make a toturial using all the free and open source tools
Has anyone gotten this to work on Windows?
Hi, I am working on creating a closed lan-network, using per to per, and will input a live AI agent, locally stored, getting knowledge from LLM, and wonder if it is possible to have this kind of system then running without using internet?
Hi, does your material also covers the basic maths required for data science? If not can you make separate video on mathematical basics to learn ml and ai ?
Thanks for the video. The content and the explanation is top notch.
2:38
Hi I really liked your video I took inspiration from it and made the same thing without the camera integration I used the local llm llama3 to run it.I could not pay for openai api key so had to make use of that.If there is any new model which can do the webcam integration locally please recreate this video using that
A great explanation
Hi , i start test with all your steps and got stuck on the fact that text and audio from the openai api are not transferred to livekit, all requests pass in the terminal , tried many solutions...doesnt work
I think I may have a similar issue on Windows there is some problem with the ffmpeg library.
This is great !! thanks
Is this functionally any different than your previous video?
While they work the same for the demo, my previous code is very brittle. This one is much better because I’m using an entire existing infrastructure to support it.
How to protect a company's information with technology ?
Hi Santiago, would it be possible for you to create a project which combines a ML with a AI methods (preferably with open source tools) to solve one real word problem? In case if the other chanell members are interested on my proposal they may jump in and provide their comments and suggestions. Thank you in advance.
Have nothing to tell, than You are fantastic!
I am building a RAG application, but I am just looking for some advice on issues: 1. How to make it answer general questions like greetings, farewell, etc., directly without trying to retrieve them as there is no need to do so? I know I can use LLM to classify the question but I will need an additional API call for that (if the model is openai) 2. I implemented RBAC if a single question from a user contains two queries and the user only has access to the document that is sufficient to answer one of the two queries, I retrieve the context of whatever is close to that (here the context is sufficient to answer one of the two queries) but the response from LLM is I don't know, which means it is failing to extract the context and answer at least whatever it can, how do I address this? 3. If I ask a specific question it answers, but if I ask in an overall sense say, what is the summary of XYZ doc, it fails to answer it would be great if someone could help me with the possible approaches to fix this thanks 🙏
I hope we can we use gemini 1.5 pro? I will try to make this changes in old code
Incredible video, really like the longer content codealong.
By far you are one of the top three the best instructor I have ever seen. You remind me Richard Phillips Feynman.
Can be used with google flash? Thanks for super content!❤
Incredible video. You're taking your content to the next level. Keep up the good work and thankyou for all you do.
You turned your videos to the next level which is pretty amazing. I would like you to ask if is possible, show us how to use open source models in those apps. Thank you in advance.
Great project! I recently came across an interesting project in github that I think you might find interesting. Since I can't share a link, I share the repo title: S4mpl3r/okra
very interesting! thank you!
Great video. Keep these coming.
Nice men thanks
This is great!
i can't explain the amount of benefits i gained after watching this video ! 🖤
It's such a fantastic video, Santiago. 🎉
Can I embed this, such as with laravel, and then serve it on a host online. So I can access it anywhere?
You are fantastic in explaining complex problems in simple way. Congradulations! 😉
thanks for sharing this 🤗