Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/Marker-Inc-Korea/AutoRAG_ARAGOG_Paper
https://github.com/Marker-Inc-Korea/AutoRAG_ARAGOG_Paper
Last synced: 12 days ago
JSON representation
- Host: GitHub
- URL: https://github.com/Marker-Inc-Korea/AutoRAG_ARAGOG_Paper
- Owner: Marker-Inc-Korea
- Created: 2024-07-18T03:35:33.000Z (7 months ago)
- Default Branch: main
- Last Pushed: 2024-07-18T08:23:52.000Z (7 months ago)
- Last Synced: 2024-12-30T16:53:00.123Z (about 1 month ago)
- Language: Python
- Size: 18.6 MB
- Stars: 3
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesomerag_paper - https://github.com/Marker-Inc-Korea/AutoRAG_ARAGOG_Paper
- awesomerag_paper - https://github.com/Marker-Inc-Korea/AutoRAG_ARAGOG_Paper
README
# AutoRAG_ARAGOG_Paper
# Installation
```bash
pip install -r requirements.txt
```
# Running the project
1. Make `.env` file using `.env.template` file.
2. Run evaluator with the following command.
```bash
python run.py
```
3. Check the result in the result folder.
You can check the example config file at config folder.
And you can specify qa data path, corpus data path, and project dir if you want.
# ⚠️ Warning ⚠️
The use of RAGAS Context Precision to score retrievals is very expensive, so it is currently removed from AutoRAG.
The repo specifies in the requirement.txt that AutoRAG version 0.1.12 should be able to use RAGAS Context Precision.
However, it can be expensive to test, so be careful when using it.