https://github.com/shivamarora1/circle-and-search

Search the object inside image using gesture of finger
https://github.com/shivamarora1/circle-and-search

angular bedrock image-similarity similarity-search titan-embeddings vector-database vector-search vercel

Last synced: 2 months ago
JSON representation

Search the object inside image using gesture of finger

• Host: GitHub
• URL: https://github.com/shivamarora1/circle-and-search
• Owner: shivamarora1
• Created: 2024-10-11T11:01:33.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-11-01T05:50:47.000Z (over 1 year ago)
• Last Synced: 2025-10-04T21:48:31.932Z (9 months ago)
• Topics: angular, bedrock, image-similarity, similarity-search, titan-embeddings, vector-database, vector-search, vercel
• Language: TypeScript
• Homepage: https://frontend-shivamarora1s-projects.vercel.app/
• Size: 575 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
Circle to Search is a vector database powered feature that allows you to quickly search for information about what you see on your images, using a simple gesture with your finger or mouse pointer. 


![icon](https://github.com/user-attachments/assets/04f0a5a1-cc01-44dc-bc96-7e33d5fd162f)



 👉 Live Demo: [https://frontend-shivamarora1s-projects.vercel.app/](https://frontend-shivamarora1s-projects.vercel.app/)

 ## Architecture

![architecture](https://github.com/user-attachments/assets/6dedaa27-5b08-4579-a246-c8e8d74a0fad)

Embeddings of images along with their meta are stored inside Milvus vector database. Image embeddings are generated using titan multi embeddings generation model.

1. Image from frontend is sent to backend.

2. Backend generates embeddings of uploaded image using AWS Bedrock Titan Embedding generation model.

3. Vector Similarity search is performed using these generated embeddings and Milvus vector query.

4. Fetched results (Product image, Price, Link) are returned to frontend.

## Running in local:

1. Clone the repo.

2. Run Frontend

```

cd frontend

npm install

ng serve

```

3. Create `.env` referring to `.env.example`.

4. Run Backend

```

cd backend

npm install 

vercel dev

```