This project is an answer-based search engine that fetches and answers user questions based on content from the No Man's Sky Wiki fandom page. The search engine is designed to provide quick and accurate answers to questions related to the game, such as information on planets, star systems, resources, creatures, and more.
A streamlit integration was added to enable easy and shareable web app.
My application crawls the https://nomanssky.fandom.com/ website, extracting numerous pages that are subsequently stored in an SQL database. The project employs the Whoosh search application to enable users to search through these stored documents using queries. The retrieved documents are then processed by one of three language models: DeepPavlov, GPT-3.5 (4k tokens), or GPT-3.5 (16k tokens) to generate responses for users.
(generated by instagraph)
To run this project, you will need:
- Python (version 3.8.0 or higher)
- Django (version 3.0 or highter)
- The text stored in the No Man's Sky Wiki fandom website
- Clone this repository to your local machine.
git clone https://github.com/Scylidose/AtlasFind.git
- Create and activate a new virtual environment:
python3 -m venv venv
source venv/bin/activate # on Linux or macOS
.\venv\Scripts\activate # on Windows
- Install the required Python packages:
pip3 install -r requirements.txt
This will install all the necessary dependencies.
- Run project:
python manage.py runserver
4.5 Run Stramlit:
streamlit run main.py
Contributions to this project are welcome. If you find a bug, have a feature request, or want to contribute code, please open an issue or pull request on the project's GitHub page.
This project is licensed under the MIT License. See the LICENSE file for details.