My name is Jason Zhou, a product designer who share interesting AI experiments & products. Email me if you need help building AI apps!
- Follow me on twitter: twitter.com/jasonzhou1993
- Join my AI email list: www.ai-jason.com/
- Email me for any question: [email protected]
Пікірлер
The corrective RAG schema explains why AI often tries to bring results from the web even when you tell them not to in prompt. If it doesn't understand the source properly it will look elsewhere. This was insightful, thank you.
Wait, where did the .flac information come from?
Hey as a complete freshers,not able to understand what is happening in this video but i like to create same.can you provide simple roadmap for this
thanks Jason, can i use llama on API and train PDf files in a specify directory train to respond
kzread.info/dash/bejne/X4aDtZiglryvpNY.html
🎯 Key Takeaways for quick navigation: 00:00 *🤖 Hugging Face Overview* - Hugging Face is a platform for discovering and sharing AI models. - Three main parts: models, datasets, and spaces. - Models: Various AI models for tasks like image to text, text to speech, etc., hosted for immediate testing. 01:52 *📊 Datasets on Hugging Face* - Hugging Face provides datasets for training your own models. - Allows filtering and previewing datasets, useful for training custom models. 02:20 *🚀 Hugging Face Spaces* - Spaces allow users to deploy and share their AI apps. - Users can explore and interact with apps built by others, offering learning opportunities. 03:15 *🔍 Building an AI App: Step by Step* - Components: Image to text model, language model for story generation, text to speech model. - Process: Select relevant models from Hugging Face, implement in code. 04:23 *🖼️ Image to Text Model Implementation* - Utilize Hugging Face's Transformers library to access predefined tasks. - Code implementation example for converting an image to text using Hugging Face models. 05:32 *📝 Language Model for Story Generation* - Using a language model (GPT) for generating a story based on the text description. - Integration of GPT model from Hugging Face into the app. 06:42 *🔊 Text to Speech Model Integration* - Using Hugging Face's text to speech model for generating audio from the generated story text. - Implementation of the text to speech model and handling audio output. 07:53 *🎛️ App UI Development* - Building the user interface using Streamlit library. - Integrating image upload, model processing, story generation, and audio output into the UI. 08:44 *💡 Recap and Recommendation* - Recap of using Hugging Face models for various AI tasks. - Recommendation to explore Hugging Face's tasks and models for further learning. - Mention of another platform, Relevance AI, for quick AI app development. Made with HARPA AI
Your example is a perfect illustrations of the limitations of RAG, if you store 'I don't like fish' in a vector DB... this will be _absolutely useless_ for a future prompt where the user asks 'make a grocery list' or 'make a recipe for...'. RAG will NEVER associate 'grocery list' with a correct retrieval of 'I don't like fish' from your huge document vector DB. Solve this problem... and well...
You'd be a moron to trust facebook
Thanks man, also showing how the transformers get it a bit wrong, like the lady is laughing hard, not smiling in love: 2:54.
Hey Jason, why not create a SAAS for this use case? Would sell damn well
unlucky there's no free resources :(
Hello - I am following your tutorial. However at 17:00, the node "Prepare Image for InsightFace" is not available. I have installed all the custom nodes as shown by you. Can you please guide me where I am going wrong.
Mostly are false followers just ...
Loved this Jason!!! Thank you
Thanks... Awesome video
There is empirical evidence that automation will cause displacement in the work place. Anyone who caricatures or argues against it have been caught in the widespread net of corporate deceit. Large corporations that stand to benefit the most out of AI and robotics invest large sums to keep research going in the opposite direction. Why? because the more regular people know and understand about the detrimental effects that AI will have in their lives the more they want to change laws to govern the usage of that resource. This of course doesn't fit well with the corporate world where any amouunt of capital expense reduction is welcomed. AI and Robotics may not be at the point where they can completely replace a human (though in some areas it has already happened) but it won't be long. People can mock, dismiss, or patronize all they want it does no change the facts. Corporate world frames it as a replacement of old jobs with new ones... but the cost to reskill a whole genertion will be a challenge of massive proportions.
Great Video. Can you please upload the code for this? there's no code in your GitHub repository for this.
Thank you for covering this, we are building AI Applications using groq. Fast, cheap, and reliable.
How I can use this ? Just uploading clothes and model only , not entire process???
Let's phone scammers agencies know about this trick... Very good, very nice...
I don't have the technical capacity to follow a tutorial, even though I have access to the same Linksm tool, I teach courses on the subject for non-technical people, teach me how to create my own model for Ecommerce, this is gold, for the adult niche there are several ways to monetize this.
Keep this up. This answered to loads of questions I have had previously, and were not answered in any of the HuggingFace tutorials!
I also worked on a similar project right after they announced rabbit r1, it was using ocr+yolo+ llm to control the computer. I was able to get it to click wherever I wanted, but failed to build the backend for the llm to orchestrate the high level tasks. It was simply too much work for me. 😅😅
Great content! Thanks for putting in the effort. Will use this.
Thanks!
Source code please
Pretty good thanks!
Hey, Jason. This video is 🔥🔥! Congrats, I was wondering if there is a chance to reach out to you? I might have an interesting offer for you.
Wow! I wonder if there are built-in solutions for Hungarian input&output. :)
MAKE SOME NOISE FOR THIS MAN
Excellent job, thank you. This is just what I needed.
very cool, does it have french?
Thank you. Can you say a little about your hardware setup for this work? This information is missing from a lot of online sources.
I am literally using this technique now in my internship for a project. I went through so many approaches and ended up on my version of this one. Wish you released this video about 2 months ago lol
why no one has built an online tool with API for this process? @aijason
Very usefull, thank you! Is it posible for the model to retrieve images or graphs from a PDF, or it's only text?
Please use internal Ollama embedding creation, much faster
I watch lots of AI videos and 99% of them are just a waste of time. As an AI engineer, this channel is hands down the BEST yet KEEP UP👏🏼
Is it possible to have an AI copilot real time in game ,steamvr rec room ?
Thanks! It's so fascinating how these programs 'think.' Even if I don't install one, concepts like chunking seem to translate to humans as well.
Great thanks. Can we get the repo and link to the colab notebook?
hello jason. love the video. i am facing an error, whenevr i try to run the code in kaggle, i get this error - 'FileNotFoundError: Unable to find '/kaggle/working/midjourney_prompt_dataset.csv' at /kaggle/working '. i choose kaggle since the resources are free. the error occurs on executing - 'data = load_dataset("csv", data_files="midjourney_prompt_dataset.csv")', how do i solve this? thanks a lot
12:39 if im that AI, i would be very angry with that woman interrupting me
Fantastic presentation, but the chart at 5:47 is total garbage. The tools should be by color and there should be vertical bars with the largest on top inside of colored silos to show the breakout of tool market share. This would be a much more glance-ready chart showing what the market looks like with cleaner differences while showing clear leaders.
PLS HELP ME • PS C: \Users\dania\AI GF> python app. py C: \Program Files\Python311\python.exe: can't open file 'C:\\Users\\dania\\AI GF\\app-py': [Errno 2] No such file or directory UTF-8 CRLF HTML
where is the code file ??
Great content as usual! I wonder if you could make a centralized inbox with Instagram dm, Facebook messenger, WhatsApp and email, and then have something like a custom gpt connected into the flow.
Thanks Jason, great video, this explains RAG pretty well. Subscribed!
Thanks!
thx