An elegant hybrid search engine that significantly enhances search precision by seamlessly querying semantically related results using embedding AI models.
- Semantic Search Engine
- Tech Stack
- Installation
- Important
- Environment Variables
- Starting the Development Server
- Contributing
- Live Preview
- TypeScript
- Next.js
- Tailwind CSS
- Drizzle
- PostgreSQL
- VectorDB
- Hugging Face
Make sure you have Node.js installed on your machine.
Clone the repository:
git clone https://github.com/nyintosh/semantic-search.git
Navigate to the project directory:
cd semantic-search
Install dependencies: Run one of the following commands based on your preferred package manager:
- Using npm:
npm install
- Using yarn:
yarn install
- Using pnpm:
pnpm install
To run this locally, make sure you've set up a PostgreSQL database and obtained API keys for both Upstash Vector and Hugging Face. Alternatively, you can utilize similar technologies and update the configuration accordingly.
This project requires the following environment variables:
DATABASE_URL
UPSTASH_VECTOR_REST_URL
UPSTASH_VECTOR_REST_TOKEN
HF_TOKEN
Make sure to set these environment variables in your development environment.
To start the development server: Run one of the following commands based on your preferred package manager:
- Using npm:
npm run dev
- Using yarn:
yarn dev
- Using pnpm:
pnpm dev
Open your browser and navigate to http://localhost:3000 to see the app live.
If you want to add additional features and improvements, we welcome contributions! Please follow these guidelines:
- Fork the repository
- Create a new branch
- Make your changes
- Submit a pull request
You can preview the live version of the project at https://nk-semantic-search.vercel.app.