title: RepoSnipy
emoji: 🐍🔫
colorFrom: grey
colorTo: grey
sdk: streamlit
sdk_version: 1.21.0
python_version: 3.11.3
app_file: app.py
pinned: true
license: mit
RepoSnipy 🐍🔫
Neural search engine for discovering semantically similar Python repositories on GitHub.
Demo
Searching an indexed repository:
About
RepoSnipy is a neural search engine built with streamlit and docarray. You can query a public Python repository hosted on GitHub and find popular repositories that are semantically similar to it.
It uses the RepoSim pipeline to create embeddings for Python repositories. We have created a vector dataset (stored as docarray index) of over 9700 GitHub Python repositories that has license and over 300 stars by the time of 20th May, 2023.
Running Locally
Download the repository and install the required packages:
git clone https://github.com/RepoAnalysis/RepoSnipy
cd RepoSnipy
pip install -r requirements.txt
Then run the app on your local machine using:
streamlit run app.py
License
Distributed under the MIT License. See LICENSE for more information.
Acknowledgments
The model and the fine-tuning dataset used: