Hugging Face + Langchain in 5 mins | Access 200k+ FREE AI models for your AI apps
AI技術の魅力を伝える記事を書くライターとして、Hugging FaceとLangchainの組み合わせについてご紹介します。Hugging Faceは200,000以上のAIモデルにアクセスできるプラットフォームであり、Langchainは無料で利用できる開発環境です。
Hugging Faceは、画像から音声ストーリーを作成するデモを通じてその可能性を示しています。具体的なチュートリアルでは、以下のステップが紹介されています:
1. 画像からテキストモデル
2. LLM(言語モデル)
3. テキストから音声モデル
4. Streamlitを使用したUIの構築
さらに、Hugging Faceにはさまざまなチュートリアルが提供されており、コード不要の代替手段もあるため、初心者でも取り組みやすいです。
私はJason Zhouと申します。製品デザイナーとして興味深いAI実験や製品を共有しています。AIアプリを構築する際に必要なサポートがあれば、ask@ai-jason.comまでお気軽にご連絡ください。
Hugging FaceとLangchainの組み合わせは、AI技術の魅力を最大限に活かし、革新的なアプリケーション開発を可能にします。是非この素晴らしい機会を活用してください!#huggingface #langchain #autogpt #ai #nocode #tutorial #stepbystep #langflow #flowise #gpt #falcon
My screen was like: 🌚🌝🌚🌝🌚😀👀😵
Why not a dark theme on hugging face too?
I am getting the error
"ValueError: Unable to create tensor, you should probably activate padding with 'padding=True' to have batched tensors with the same length."
when using the image to text model
Shitty tutorial.
Jason, you are a walking GOAT! Keep going, please!
Legendary video.
Can u share the code please?
You got a subscriber
Awesome
This code no longer seems to work, multiple functions have been depriciated. updated code on a github would be great!
You have earned a subscriber my friend. Thanks for such an awesome tutorial.
Wait, where did the .flac information come from?
🎯 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
Thanks man, also showing how the transformers get it a bit wrong, like the lady is laughing hard, not smiling in love: 2:54.
Pretty good thanks!
Love It!!
thanks Jason , content is really good but text is very small invisible to view in laptop screen , please zoom out while you show the code.
thank you so much
Most of the questions I had about the huggingface ecosystem were answered in the video. Thank you for making this video.
Beatuful work Jason, just wondering if could share a demo of how to implement other hugging face LLM to do the text generation task, eg. mistralai/Mixtral-8x7B-Instruct-v0.1 . thx
good stuff, thanx 💯🤙
the way you describe is really outstanding
Great tutorial!
You're a legend mate.
I have created a server using node and express and i want a model which can summarize my text which comes from database now pls tell me how can use that model ???
fucking ..good keep it bro.
But OpenAI API isnt free anymore right
Thanks!
I am nauseated by pictures being turned to words! What?–have people become so stupid they can't imagine and find the right words? What we need as writers is for AI to turn words to pictures that we can tweak to match our imaginations.
Love your work Jason. You are an inspiration.
Excellent breakdown of using Hugging Face for AI apps! Your step-by-step guide is incredibly helpful for both beginners and experienced developers. Thanks for sharing your expertise!
Very good example, thanks for sharing.
FYI: I did run into a error 403 with Streamlit, possibly Windows related. I was able to resolve by creating a ./.streamlit/ folder with config.toml file, with the following details:
[server]
enableXsrfProtection=false
enableCORS = false
Thanks, Jason. this was very informative, I hope you can make more in depth videos on HF own deploy Inference API
from where you are getting the open AI key ? I know in Azure Open AI but thats paid . is there anyway to get / aceess API key for free ?
Anyon getting this error – "AttributeError: 'str' object has no attribute 'handlers'" ?
Hello . Do you know is it possible to create an own LLM for own startup?
Thank you for sharing Jason,now I have the superpower to make a model every day,well actually every 5 mins 🙂
Pretty dope.
Very clever content idea, concentrated info. Helpful for newcommers and professionals both. Thanks
You made a really superb video. Straight to topic. I felt like learning something new today. You got a new subscriber 🤗
helped a lot! thanks
idk how to download model locally omfg im so stuppid
Super useful thank you 🙂
Thanks for this walkthrough tutorial
before publishing videos, you could check whether langchain has deprecated or migrated the modules, classes… tried your exact code, and I get the following error: openai.NotFoundError: Error code: 404 – {'error': {'message': 'This is a chat model and not supported in the v1/completions endpoint. Did you mean to use v1/chat/completions?', 'type': 'invalid_request_error', 'param': 'model', 'code': None}}
bro code dene ka kya loge bc
The code for "llm" is no longer working.
You obviously need to know some basic coding language to input into the right areas, what resources do you suggest for a beginner to learn the basic inputs?
Great vids! I’m learning a lot!
What combo would you recommend using to parse and clean structured and unstructured data? For example there are 1000 real estate listings in a csv, and many do not contain a piece of data explicitly, but they may contain it in the long unstructured description…
Great. I especially liked the summary of the code at the end.
Thank you. 新年快乐。 我钦佩中国。
Great stuff⭐