A toolkit for end-to-end neural ad hoc retrieval
Capreolus is a toolkit for conducting end-to-end ad hoc retrieval experiments. Capreolus provides fine control over the entire experimental pipeline through the use of interchangeable and configurable modules.
- Prerequisites: Python 3.6+ and Java 11
- Install the pip package:
pip install capreolus
- Train a model:
capreolus train with reranker=KNRM niters=2 expid=myquickstart
- If the
traincommand completed successfully, you've trained your first Capreolus reranker on robust04! This command created several outputs, such as run files, a loss plot, and a ranking metric plot on the dev set queries. To learn about these files and about how to evaluate your model, read about running experiments with Capreolus.
Capreolus uses environment variables to indicate where outputs should be stored and where document inputs can be found. Consult the table below to determine which variables should be set. Set them either on the fly before running Capreolus (
export CAPREOLUS_RESULTS=...) or by editing your shell's initialization files (e.g.,
|Environment Variable||Default Value||Purpose|
||~/.capreolus/results/||Directory where results will be stored|
||~/.capreolus/cache/||Directory used for cache files|
||(unset)||Indicates GPUs available to PyTorch, starting from 0. For example, set to '1' the system's 2nd GPU (as numbered by
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
|Filename, size||File type||Python version||Upload date||Hashes|
|Filename, size capreolus-0.1.4-py3-none-any.whl (4.0 MB)||File type Wheel||Python version py3||Upload date||Hashes View hashes|
|Filename, size capreolus-0.1.4.tar.gz (3.8 MB)||File type Source||Python version None||Upload date||Hashes View hashes|
Hashes for capreolus-0.1.4-py3-none-any.whl