Welcome to Full Wiki! 🎉
Full Wiki enables seamless access to Wikipedia content in multiple languages. It translates English Wikipedia articles into German, French, Spanish, and Italian, providing a more interactive and comprehensive experience by translating section by section. It also aggregates knowledge from different language versions, ensuring no valuable insight is missed due to language barriers.
Full Wiki is a project that was created during the THE FUTURE OF AI IS OPEN by Snowflake and Streamlit to celebrate the release of the huge Arctic model.
- Translate Wikipedia articles from English to German, French, Spanish, and Italian.-
- Giving no english speaker access to the information in their native language, without even knowing the english search term.
- The english version of Wikipedia has the most articles and is the most up-to-date, so it is accessible to many more people now.
- Section-by-section translation for an interactive experience.
- Caching system for faster response times.
- Summarize and translate summaries for efficient information retrieval.
- Combine knowledge from multiple Wikipedia language versions. Since Wiki is a cornerstone of knowledge, but it is not a centralised repository. Now even english speaking people can access informations about a topic that might be hidden in a foreign language version.
-
Clone the repository:
git clone https://github.com/yourusername/full-wiki.git cd full-wiki
-
Create and activate a virtual environment:
python3 -m venv venv source venv/bin/activate
-
Install the dependencies:
pip install -r requirements.txt
-
Set up environment variables in a .env file.
-
Run the app:
streamlit run app.py
- Enter a Wikipedia search term.
- Select the desired language for translation.
- Navigate through sections to view translations.
- Use the "Combined Knowledge" feature to aggregate information from different language versions.
This project is licensed under the MIT License.
Contributions are welcome! Please fork the repository and create a pull request with your changes.