Semantic text search using AM Stemmer and BERT-based embeddings.
You'll need a pre-trained model for TF-IDF and BERT before running the web. The model can be downloaded from Azure Blob Storage.
- Clone this repo.
- Copy model blobs to a directory, default to
./data
- Create env file,
postgres.env
andweb.env
from their respective example files - Run
docker compose up
You should be able to access the web at http://localhost:8000. The database migrations will automatically run at first startup.