BERGEN: A Benchmarking Library for Retrieval-Augmented Generation

BERGEN (BEnchmarking Retrieval-augmented GENeration) is a library designed to benchmark RAG systems with a focus on question-answering (QA). It addresses the challenge of inconsistent benchmarking in comparing approaches and understanding the impact of each component in a RAG pipeline.

Key Features

• Easy reproducibility and integration of new datasets and models
• Support for various retrievers (20+), rerankers(4) and large language models (20+)
• Flexible configuration system using YAML files
• Comprehensive evaluation metrics (Match, EM, LLMEval, ... )
• Support for multilingual experiments

For more information and experimental findings, please see:

• The initial BERGEN paper: https://arxiv.org/abs/2407.01102 and our EMNLP'24 slides
• The Multilingual RAG paper: https://arxiv.org/abs/2407.01463

Quick Start

A typical RAG setup follows this pipeline:

question >> retriever >> reranker >> LLM >> answer

You can configure each component using simple YAML files. Here's an example of running an experiment:

python3 bergen.py retriever="bm25" reranker="minilm6" generator='tinyllama-chat' dataset='kilt_nq'

Installation

Check the installation guide for detailed instructions.

Usage

# simple setup for benchmarking
# run the retriever and cache results
# do the generation with VLLM
for dataset in kilt_nq kilt_hotpotqa kilt_triviaqa asqa popqa ; do

   python3 bergen.py  retriever=splade-v3 reranker=debertav3  dataset=$dataset

   python3 bergen.py  retriever=splade-v3 reranker=debertav3 dataset=$dataset  generator=vllm_SOLAR-107B
done

To fully configure BERGEN, please read our configuration guide

Evaluation

Run the evaluation script to calculate LLMEval metrics and print the results:

python3 eval.py --experiments_folder experiments/ --llm_batch_size 16 --split 'dev' --llm vllm_SOLAR-107B

#parse all the experiments files into a panda dataframe
python print_results.py --folder experiments/ --format=tiny

For more evaluation options and details, refer to the Evaluation section in the complete documentation.

RAG Baselines

Bergen provides results for several models and many datasets aiming to provide strong baselines. On the important datasets for RAG, the match metric is given by this table (see more in our paper):

Match Metric

Multilingual Experiments

Refer to our multilingual RAG guide for running experiments with multilingual user queries and/or multilingual Wikipedia as a datastore.

Training

To train a model, add a training config:

python3 bergen.py retriever="bm25" reranker="minilm6" generator='tinyllama-chat' dataset='kilt_nq' train='lora'

Extensions

To add new datasets and models, or configure prompts, see our reference guide.

Cite

If you use BERGEN for your research, please consider citing:

@misc{rau2024bergenbenchmarkinglibraryretrievalaugmented,
      title={BERGEN: A Benchmarking Library for Retrieval-Augmented Generation}, 
      author={David Rau and Hervé Déjean and Nadezhda Chirkova and Thibault Formal and
      Shuai Wang and Vassilina Nikoulina and Stéphane Clinchant},
      year={2024},
      eprint={2407.01102},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2407.01102}, 
}

@misc{chirkova2024retrievalaugmentedgenerationmultilingualsettings,
      title={Retrieval-augmented generation in multilingual settings}, 
      author={Nadezhda Chirkova and David Rau and Hervé Déjean and Thibault Formal and Stéphane Clinchant and Vassilina Nikoulina},
      year={2024},
      eprint={2407.01463},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2407.01463}, 
}

License

BERGEN is released under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 license. For more details, see the LICENSE file.