Saved in:
Bibliographic Details
Main Authors: Yu, Xiao, Lu, Yunan, Yu, Zhou
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.00982
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909125857771520
author Yu, Xiao
Lu, Yunan
Yu, Zhou
author_facet Yu, Xiao
Lu, Yunan
Yu, Zhou
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2403_00982
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LocalRQA: From Generating Data to Locally Training, Testing, and Deploying Retrieval-Augmented QA Systems
Yu, Xiao
Lu, Yunan
Yu, Zhou
Computation and Language
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.
title LocalRQA: From Generating Data to Locally Training, Testing, and Deploying Retrieval-Augmented QA Systems
topic Computation and Language
url https://arxiv.org/abs/2403.00982