AI Image Similarity Search
This video shows Python code for image similarity search - using Qdrant as the Vector Database and a free vision transformer model : ViT Model 'facebook/dino-vits16'
This is all free. No need for a paid AI service such as OpenAI. Unlike many tutorials and videos, this uses a custom dataset, rather than the usual ready made one. I have used some Real Estate Property images from a Kaggle collection, but you could just as easily add your own and modify the metadata accordingly. I introduce the project at the start, and then the second half is a sequence of me demonstrating it.
🟢 The process of finding similar images
🔗 https://huggingface.co/blog/image-similarity#the-process-of-finding-similar-images
- chapters -
00:00 intro - Real Estate Image Similarity Search
02:32 making a dataset
03:27 metadata
10:21 import dataset
12:22 source image
14:12 run code
16:33 qdrant actix vector database (Docker)
18:48 hugging face usage tips
Links:
---------
Vision Transformer (ViT)
🔗 https://huggingface.co/docs/transformers/v4.36.1/en/model_doc/vit#overview
🔗 https://huggingface.co/docs/datasets/v1.11.0/loading_datasets.html
Qdrant
🔗 https://qdrant.tech/
🔗 https://qdrant.tech/documentation/concepts/search/
🔗 https://colab.research.google.com/github/qdrant/examples/blob/master/qdrant_101_image_data/04_qdrant_101_cv.ipynb
Pytorch
🔗 https://pytorch.org/get-started/locally/
If you want a fast VPS server with Python installed check out :
🟢 https://webdock.io/en?maff=wdaff--170
Nostr
---------
@RngWeb
findthatbit@iris.to
https://findthatbit.info/
https://redandgreen.co.uk/
#computervision #ai #qdrant
10
views
Learning Rust | Neovim Setup
This video covers me discussing neovim, spaced repetition, keybindings, and Rust specific remaps including saving, compiling, and a custom escape with "kj" rather than "esc" .
📌 This is a not a "best practice" video, rather "tips that you may find useful"
- chapters -
00:00 intro
04:20 Andy Olsen
05:45 init.vim
11:16 plugins
🔗 https://redandgreen.co.uk/category/rust-programming/
If you're an experienced developer then this may not be suitable for you, but I've tried to make this a video that I would have found useful when starting or switching to learning Rust.
📌 My init.vim file :
https://gist.github.com/RGGH/9bf10b5c3ad8df37eb0076814a68a4db
You're welcome to copy it, but would recommend making your own from scratch after!
📌 The course I mentioned was by Andy Olsen.
Not a promotion, just happened to find his course really good:
https://github.com/andyolsen
#neovim #rustlang
39
views
Unit Tests in Rust | RustLang
Demo of using Unit tests in Rust with a Builder pattern.
Unit tests are essential for software development because they ensure that individual components of code work correctly. They help identify and fix bugs early, provide documentation for code behaviour, and enable safe code changes by preventing regressions. Ultimately, unit tests enhance code reliability, maintainability, and overall software quality
Read about The “Builder” pattern in Rust and Unit tests :
https://redandgreen.co.uk/unit-tests-in-rust/rust-programming/
Try the code in Rust Playground :
https://play.rust-lang.org/?version=stable&mode=debug&edition=2021&gist=b34543fc23ade0c0e7068adcb1a25acb
#rustlang #rustforbeginners
21
views
LangChain Course | Beginners
Full 1 hour course explaining all of the key features of LangChain.
Why use LangChain? This LangChain course looks at how LangChain can simplify and enhance working with a Large Language Model. This also includes a project to use Qdrant vector database search and a Strreamlit app with chat history. I used OpenAI ChatGPT as it's currently the most widely used and easy to use when you only have a regular laptop computer. See below for link to all of the LangChain code used on GitHub.
🟢 This video is split into the same chapters as the official LangChain documentation. It demonstrates the Python code to use LangChain Models, Prompts, Chains, Memory, Indexes, Agents and Tools.
🟢 The video also demonstrates using Qdrant as a vector database to enable retrieval of embedded vectors along with tips on how to debug LangChain and how to set up a project from scratch.
🟢 As well as the regular examples you my find on the LangChain documentation pages I also show how to create a video suggestion chatbot and in the 'indexes' chapter I show you how to create a full project to query your documents, 'upserting' data from a text document and then querying it.
-Chapters -
00:58 why we need LangChain
02:37 register with openai
04:13 models
10:37 prompts
24:58 chains
28:35 memory
32:53 indexes
52:01 tools and agents
⛓️🦜 LangChain 🦜⛓️
• OpenAI & LangChain & chatGPT
🟢 Become a patron : 🌏 https://www.patreon.com/drpi
🟢 Buy me a coffee (or Tea) ☕ https://www.buymeacoffee.com/DrPi
If you want a fast VPS server with Python installed check out :
🟢 https://webdock.io/en?maff=wdaff--170
Get the code used in the video:
GitHub : 🌏 https://github.com/RGGH/LangChain-Course
LangChain with Python article : 🌏 https://redandgreen.co.uk/langchain-w...
To use serpapi you'll need to sign up: https://serpapi.com/ ~ "Scrape Google and other search engines from our fast, easy, and complete API"
Thumbs up yeah? (cos Algos..)
🟢 https://findthatbit.com
contact : https://redandgreen.co.uk/contact/
🟢 LangChain Beginner's Guide - Step-by-Step Tutorial | How to use LangChain
65
views