Translations:FACTS About Building Retrieval Augmented Generation-based Chatbots/14/pt: Difference between revisions

Latest revision as of 07:29, 20 February 2025

Information about message (contribute)

This message has no documentation. If you know where or how this message is used, you can help other translators by adding documentation to this message.

Message definition (FACTS About Building Retrieval Augmented Generation-based Chatbots)

Our company’s content landscape includes both authoritative knowledge and unauthoritative content. Authoritative content encompasses IT help articles, HR resources in platforms like ServiceNow, and project documentation on Confluence, SharePoint, Google Drive, and engineering tools like NVBugs and GitHub. Employee-generated content complements these sources on platforms such as Slack and MS Teams. In this paper, we present three bots that we have built at NVIDIA using RAGs and LLMs. These bots are briefly introduced below. All three bots are built on our in-house built generative-AI chatbot platform called NVBot platform. Some of the queries that our bots are capable of answering are shown in Table [[#S1.T1|1]].

O cenário de conteúdo da nossa empresa inclui tanto conhecimento autoritativo quanto conteúdo não autoritativo. O conteúdo autoritativo abrange artigos de ajuda de TI, recursos de RH em plataformas como ServiceNow e documentação de projetos no Confluence, SharePoint, Google Drive e ferramentas de engenharia como NVBugs e GitHub. O conteúdo gerado por funcionários complementa essas fontes em plataformas como Slack e MS Teams. Neste artigo, apresentamos três bots que desenvolvemos na NVIDIA usando RAGs e LLMs. Esses bots são brevemente introduzidos abaixo. Todos os três bots são construídos na nossa plataforma interna de chatbot de IA generativa chamada plataforma NVBot. Algumas das consultas que nossos bots são capazes de responder estão mostradas na Tabela 1.