https://github.com/theoddysey/image-search-engine
A Weaviate Search Engine using Vector database and Docker 🔎
https://github.com/theoddysey/image-search-engine
docker json search-engine vector-database weaviate
Last synced: 8 months ago
JSON representation
A Weaviate Search Engine using Vector database and Docker 🔎
- Host: GitHub
- URL: https://github.com/theoddysey/image-search-engine
- Owner: TheODDYSEY
- Created: 2023-05-30T15:45:01.000Z (over 2 years ago)
- Default Branch: master
- Last Pushed: 2024-12-15T18:17:05.000Z (10 months ago)
- Last Synced: 2024-12-15T19:26:06.037Z (10 months ago)
- Topics: docker, json, search-engine, vector-database, weaviate
- Language: JavaScript
- Homepage:
- Size: 684 KB
- Stars: 2
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: Readme.md
Awesome Lists containing this project
README
# Weaviate Meme Search Project
**Note: This is an ongoing project and is not yet finished.**
This project demonstrates how to use the Weaviate knowledge graph to store and search for memes based on images. It utilizes the Weaviate JavaScript client library (`weaviate-ts-client`) for interacting with the Weaviate instance.
## Prerequisites
- Weaviate instance running on `localhost:8080`. You can install Weaviate from [here](https://www.semi.technology/developers/weaviate/current/get-started/installation.html).
- Node.js and npm installed on your machine.
## Getting Started
1. Clone the repository:
```bash
git clone https://github.com/TheODDYSEY/Image-Search-Engine.git
2.Install the dependencies:
``` bash
cd Image-Search-Engine
npm install
```
3.Update the Weaviate instance details in index.js:
```
const client = weaviate.client({
scheme: 'http',
host: 'localhost:8080',
});
```
4.Create the "Meme" schema and store an image:
Make sure you have the image file matrix.jpg in the ./img directory.
5.Query an image:
Make sure you have the image file matrix.jpg in the project directory.
Run the following command:
```
node index.js
```
# CONTRIBUTING
Contributions are welcome! If you find any issues or have suggestions, please open an issue or submit a pull request.