RAGViz: Diagnose and Visualize Retrieval-Augmented Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Tevin, He, Jingyuan, Xiong, Chenyan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916466192809984
author Wang, Tevin
He, Jingyuan
Xiong, Chenyan
author_facet Wang, Tevin
He, Jingyuan
Xiong, Chenyan
contents Retrieval-augmented generation (RAG) combines knowledge from domain-specific sources into large language models to ground answer generation. Current RAG systems lack customizable visibility on the context documents and the model's attentiveness towards such documents. We propose RAGViz, a RAG diagnosis tool that visualizes the attentiveness of the generated tokens in retrieved documents. With a built-in user interface, retrieval index, and Large Language Model (LLM) backbone, RAGViz provides two main functionalities: (1) token and document-level attention visualization, and (2) generation comparison upon context document addition and removal. As an open-source toolkit, RAGViz can be easily hosted with a custom embedding model and HuggingFace-supported LLM backbone. Using a hybrid ANN (Approximate Nearest Neighbor) index, memory-efficient LLM inference tool, and custom context snippet method, RAGViz operates efficiently with a median query time of about 5 seconds on a moderate GPU node. Our code is available at https://github.com/cxcscmu/RAGViz. A demo video of RAGViz can be found at https://youtu.be/cTAbuTu6ur4.
format Preprint
id arxiv_https___arxiv_org_abs_2411_01751
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle RAGViz: Diagnose and Visualize Retrieval-Augmented Generation
Wang, Tevin
He, Jingyuan
Xiong, Chenyan
Computation and Language
Artificial Intelligence
Retrieval-augmented generation (RAG) combines knowledge from domain-specific sources into large language models to ground answer generation. Current RAG systems lack customizable visibility on the context documents and the model's attentiveness towards such documents. We propose RAGViz, a RAG diagnosis tool that visualizes the attentiveness of the generated tokens in retrieved documents. With a built-in user interface, retrieval index, and Large Language Model (LLM) backbone, RAGViz provides two main functionalities: (1) token and document-level attention visualization, and (2) generation comparison upon context document addition and removal. As an open-source toolkit, RAGViz can be easily hosted with a custom embedding model and HuggingFace-supported LLM backbone. Using a hybrid ANN (Approximate Nearest Neighbor) index, memory-efficient LLM inference tool, and custom context snippet method, RAGViz operates efficiently with a median query time of about 5 seconds on a moderate GPU node. Our code is available at https://github.com/cxcscmu/RAGViz. A demo video of RAGViz can be found at https://youtu.be/cTAbuTu6ur4.
title RAGViz: Diagnose and Visualize Retrieval-Augmented Generation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2411.01751