Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/typesense/showcase-ai-image-search
WORK IN PROGRESS | Text to image search & Image Similarity Search using @Typesense
https://github.com/typesense/showcase-ai-image-search
clip-model clip-vit image-search similarity-search text-to-image-search typesense typesense-showcase vector-search
Last synced: about 2 months ago
JSON representation
WORK IN PROGRESS | Text to image search & Image Similarity Search using @Typesense
- Host: GitHub
- URL: https://github.com/typesense/showcase-ai-image-search
- Owner: typesense
- Created: 2024-04-03T02:38:20.000Z (9 months ago)
- Default Branch: master
- Last Pushed: 2024-05-01T00:45:56.000Z (8 months ago)
- Last Synced: 2024-05-01T09:38:45.917Z (8 months ago)
- Topics: clip-model, clip-vit, image-search, similarity-search, text-to-image-search, typesense, typesense-showcase, vector-search
- Language: TypeScript
- Homepage:
- Size: 42.6 MB
- Stars: 3
- Watchers: 3
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
🤖 AI Image Search, powered by Typesense
This is a demo that showcase Typesense's Image Search feature which includes:
- Search images using text descriptions of their contents
- Image Similarity search
🌇 🔍 Live Demo: [ai-image-search.typesense.org](https://ai-image-search.typesense.org)
## Tech Stack
- Typesense
- NextJS
- Typescript
- Tailwind
The data contains 1265 best images out of the first 5000 image-prompt pairs which were taken from DiffusionDB and then filtered based on aesthetics using aesthetics-scorer.
## Project Structure
```bash
├── scripts/
│ ├── data/
│ │ └── 20-images.json
│ └── indexTypesense.ts # script that index data from 20-images.json into typesense server
└── src/
├── app/
│ ├── [slug]/
│ │ └── page.tsx # explore similar style (search similar images with image)
│ └── page.tsx # search images using text descriptions
├── components/
│ └── UI components...
├── hooks/
│ └── useImageSearch.ts
└── lib/
└── typesense.ts # typesense client config
```
## Development
To run this project locally, make sure you have docker and nodejs, install dependencies and start the dev server:
Installation
```shell
git clone https://github.com/typesense/showcase-ai-image-search.git
cd showcase-ai-image-search
npm i
```
Start typesense server
```shell
npm run start:typesense # or: docker compose up
```
Download sample data:
```shell
# From the root of the repo:
curl -o ./scripts/data/20-images.jsonl https://ai-image-search-images.typesense.org/20-images.jsonl
```
Index data into typesense
```shell
npm run index:typesense
```
Start the dev server
```shell
npm run dev
```
Open http://localhost:3000 to see the app ✌️
## Environment
Set env variables in `.env` file to point the app to the Typesense Cluster
```env
NEXT_PUBLIC_TYPESENSE_SEARCH_ONLY_API_KEY=xxx
NEXT_PUBLIC_TYPESENSE_HOST=xxx.typesense.net
NEXT_PUBLIC_TYPESENSE_PORT=443
NEXT_PUBLIC_TYPESENSE_PROTOCOL=https
NEXT_PUBLIC_IMAGE_BASE_URL=...
```
Only for indexing:
```env
DIFFUSION_DB_JSONL_FILE=...
TYPESENSE_ADMIN_API_KEY=...
INDEXING_BATCH_SIZE=100
```