README.md

search

Simple embedding based search on wikipedia.

Installation

Clone Repo

git clone [email protected]:muelletm/search.git
cd search

Environment

Conda

conda create -n search python=3.8
conda activate search

Venv

python3 -m venv $HOME/venv/search
source $HOME/venv/search/bin/activate

Requirements

pip install -r requirements.txt -r dev-requirements.txt

Data

mkdir -p data

1. Got to the drive directory.

2. Download the data as a zip archive

3. Move and unpack

mv ~/Downloads/people_pm_minilm-*.zip .
unzip -e people_pm_minilm-*.zip
mv people_pm_minilm data/
rm people_pm_minilm-*.zip

Test

dev-tools/test.sh