OpenSearch AI is an advanced search engine powered by artificial intelligence. This project aims to provide a powerful and intuitive search experience using cutting-edge AI technologies.
Live Demo: https://opensearchai.live/
The repository is organized into two main folders:
frontend/: Contains the Next.js-based user interfacebackend/: Contains the FastAPI server
The frontend of OpenSearch AI is built using Next.js, a popular React framework that enables server-side rendering and generates static websites for React-based web applications.
To set up the frontend:
-
Navigate to the
frontenddirectory:cd frontend -
Install dependencies:
npm install -
Run the development server:
npm run dev -
Open http://localhost:3000 in your browser to view the application.
The backend of OpenSearch AI is built using FastAPI, a modern Python web framework that is fast, easy to use, and based on standard Python type hints. The backend server provides an API for the frontend to interact with the search engine. It leverages an OpenAI Tool Calling Agent built using Langchain and powered by gpt-4o-mini. It uses Tavily Search Engine to search the web.
To set up the backend:
-
Navigate to the
backenddirectory:cd backend -
Create a virtual environment and install dependencies:
python3 -m venv venv source venv/bin/activate pip install -r requirements.txt -
Set the environment variables:
cp env.example .env -
Run the FastAPI server:
uvicorn server:app --reload
We welcome contributions to OpenSearch AI! Please read our Contributing Guidelines for details on how to submit pull requests, report issues, and suggest improvements.
This project is licensed under the MIT License.
For any questions or concerns, please open an issue in this repository or contact the project maintainers.
Built with ❤️ by Raihan Khan and Sayak Sarkar. Happy searching with OpenSearch AI!