Retrieve images using vector search (1)

Hi Community,

In this article, I will introduce my application iris-image-vector-search.
The image vector retrieval demo uses IRIS Embedded Python and OpenAI CLIP model to convert images into 512 dimensional vector data. Through the new feature of Vector Search, VECTOR-COSINE is used to calculate similarity and display high similarity images.

Application direction of image retrieval  

Image retrieval has important application scenarios in the medical field, and using image retrieval can greatly improve work efficiency. Image retrieval can also be applied in the following fields, such as:

• Image retrieval systems can be used to search for medical image data related to their research topic, for data analysis, pattern recognition, and research, accelerating the process of scientific research.
• The images in the medical imaging database can be used for the education and training of medical students. Through image retrieval, students can search and compare different types of cases, deepening their understanding of disease characteristics and diagnostic methods.
•  Image retrieval can be used to assist doctors in diagnosis. By comparing medical imaging data of patients (such as X-rays, CT scans, MRI, etc.) and providing reference images of similar cases through a knowledge base, doctors can quickly obtain relevant information and improve diagnostic accuracy.  

How to use it

Prerequisites

Make sure you have git and Docker desktop installed.

Installation

• Clone/git pull the repo into any local directory

git clone https://github.com/yueshan239/iris-image-vector-search.git
Bash
Bash

• Open the terminal in this directory and run

docker-compose build
Bash
Bash

    This process will take some time

• Run the IRIS container

docker-compose up -d
Bash
Bash

• Open the terminal in `vue` directory and run

docker-compose build
Bash
Bash

• Run the nginx container

docker-compose up -d
Bash
Bash

 Visit the address below

http://localhost:8080/
Bash
Bash

Accessing this page indicates that we have successfully run it.