_version_ 1866909249820426240
author Akkiraju, Rama
Xu, Anbang
Bora, Deepak
Yu, Tan
An, Lu
Seth, Vishal
Shukla, Aaditya
Gundecha, Pritam
Mehta, Hridhay
Jha, Ashwin
Raj, Prithvi
Balasubramanian, Abhinav
Maram, Murali
Muthusamy, Guru
Annepally, Shivakesh Reddy
Knowles, Sidney
Du, Min
Burnett, Nick
Javiya, Sean
Marannan, Ashok
Kumari, Mamta
Jha, Surbhi
Dereszenski, Ethan
Chakraborty, Anupam
Ranjan, Subhash
Terfai, Amina
Surya, Anoop
Mercer, Tracey
Thanigachalam, Vinodh Kumar
Bar, Tamar
Krishnan, Sanjana
Kilaru, Samy
Jaksic, Jasmine
Algarici, Nave
Liberman, Jacob
Conway, Joey
Nayyar, Sonu
Boitano, Justin
author_facet Akkiraju, Rama
Xu, Anbang
Bora, Deepak
Yu, Tan
An, Lu
Seth, Vishal
Shukla, Aaditya
Gundecha, Pritam
Mehta, Hridhay
Jha, Ashwin
Raj, Prithvi
Balasubramanian, Abhinav
Maram, Murali
Muthusamy, Guru
Annepally, Shivakesh Reddy
Knowles, Sidney
Du, Min
Burnett, Nick
Javiya, Sean
Marannan, Ashok
Kumari, Mamta
Jha, Surbhi
Dereszenski, Ethan
Chakraborty, Anupam
Ranjan, Subhash
Terfai, Amina
Surya, Anoop
Mercer, Tracey
Thanigachalam, Vinodh Kumar
Bar, Tamar
Krishnan, Sanjana
Kilaru, Samy
Jaksic, Jasmine
Algarici, Nave
Liberman, Jacob
Conway, Joey
Nayyar, Sonu
Boitano, Justin
contents Enterprise chatbots, powered by generative AI, are emerging as key applications to enhance employee productivity. Retrieval Augmented Generation (RAG), Large Language Models (LLMs), and orchestration frameworks like Langchain and Llamaindex are crucial for building these chatbots. However, creating effective enterprise chatbots is challenging and requires meticulous RAG pipeline engineering. This includes fine-tuning embeddings and LLMs, extracting documents from vector databases, rephrasing queries, reranking results, designing prompts, honoring document access controls, providing concise responses, including references, safeguarding personal information, and building orchestration agents. We present a framework for building RAG-based chatbots based on our experience with three NVIDIA chatbots: for IT/HR benefits, financial earnings, and general content. Our contributions are three-fold: introducing the FACTS framework (Freshness, Architectures, Cost, Testing, Security), presenting fifteen RAG pipeline control points, and providing empirical results on accuracy-latency tradeoffs between large and small LLMs. To the best of our knowledge, this is the first paper of its kind that provides a holistic view of the factors as well as solutions for building secure enterprise-grade chatbots."
format Preprint
id arxiv_https___arxiv_org_abs_2407_07858
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FACTS About Building Retrieval Augmented Generation-based Chatbots
Akkiraju, Rama
Xu, Anbang
Bora, Deepak
Yu, Tan
An, Lu
Seth, Vishal
Shukla, Aaditya
Gundecha, Pritam
Mehta, Hridhay
Jha, Ashwin
Raj, Prithvi
Balasubramanian, Abhinav
Maram, Murali
Muthusamy, Guru
Annepally, Shivakesh Reddy
Knowles, Sidney
Du, Min
Burnett, Nick
Javiya, Sean
Marannan, Ashok
Kumari, Mamta
Jha, Surbhi
Dereszenski, Ethan
Chakraborty, Anupam
Ranjan, Subhash
Terfai, Amina
Surya, Anoop
Mercer, Tracey
Thanigachalam, Vinodh Kumar
Bar, Tamar
Krishnan, Sanjana
Kilaru, Samy
Jaksic, Jasmine
Algarici, Nave
Liberman, Jacob
Conway, Joey
Nayyar, Sonu
Boitano, Justin
Machine Learning
Computation and Language
Enterprise chatbots, powered by generative AI, are emerging as key applications to enhance employee productivity. Retrieval Augmented Generation (RAG), Large Language Models (LLMs), and orchestration frameworks like Langchain and Llamaindex are crucial for building these chatbots. However, creating effective enterprise chatbots is challenging and requires meticulous RAG pipeline engineering. This includes fine-tuning embeddings and LLMs, extracting documents from vector databases, rephrasing queries, reranking results, designing prompts, honoring document access controls, providing concise responses, including references, safeguarding personal information, and building orchestration agents. We present a framework for building RAG-based chatbots based on our experience with three NVIDIA chatbots: for IT/HR benefits, financial earnings, and general content. Our contributions are three-fold: introducing the FACTS framework (Freshness, Architectures, Cost, Testing, Security), presenting fifteen RAG pipeline control points, and providing empirical results on accuracy-latency tradeoffs between large and small LLMs. To the best of our knowledge, this is the first paper of its kind that provides a holistic view of the factors as well as solutions for building secure enterprise-grade chatbots."
title FACTS About Building Retrieval Augmented Generation-based Chatbots
topic Machine Learning
Computation and Language
url https://arxiv.org/abs/2407.07858