LocalRQA: From Generating Data to Locally Training, Testing, and Deploying Retrieval-Augmented QA Systems

Xiao Yu, Yunan Lu, Zhou Yu
3/1/2024
cs.CL

No official code found. Best implementation: jasonyux/LocalRQA (6 stars, MIT, last commit 2024-03-18).

Abstract

Retrieval-augmented question-answering systems combine retrieval techniques with large language models to provide answers that are more accurate and informative. Many existing toolkits allow users to quickly build such systems using off-the-shelf models, but they fall short in supporting researchers and developers to customize the model training, testing, and deployment process. We propose LocalRQA, an open-source toolkit that features a wide selection of model training algorithms, evaluation methods, and deployment tools curated from the latest research. As a showcase, we build QA systems using online documentation obtained from Databricks and Faire's websites. We find 7B-models trained and deployed using LocalRQA reach a similar performance compared to using OpenAI's text-ada-002 and GPT-4-turbo.

View on arXivView PDF

Code Implementations(1)

jasonyux/LocalRQACommunity100%
MIT
61PythonNov 13, 20232 years agoMIT

Similar Papers

Aggregated Knowledge Model: Enhancing Domain-Specific QA with Fine-Tuned and Retrieval-Augmented Generation Models

83% match2024

Building Efficient and Effective OpenQA Systems for Low-Resource Languages

83% match1 repo112024

Retrieval Augmented Generation for Domain-specific Question Answering

83% match2024

Adapting Small Language Models to Low-Resource Domains: A Case Study in Hindi Tourism QA

83% match2025

REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering

82% match2 repos352024

Harnessing Multi-Role Capabilities of Large Language Models for Open-Domain Question Answering

82% match1 repo152024

Cite this paper

@article{yu2024localrqa,
  title  = {LocalRQA: From Generating Data to Locally Training, Testing, and Deploying Retrieval-Augmented QA Systems},
  author = {Xiao Yu and Yunan Lu and Zhou Yu},
  year   = {2024},
  eprint = {2403.00982},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2403.00982v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2403.00982.svg)](https://codeofpaper.com/paper/2403.00982)

Discussion