--- title: How PDI built an enterprise-grade RAG system for AI... description: PDI Technologies built PDIQ, an enterprise AI assistant powered by a custom RAG system on AWS serverless infrastructure. The solution crawls diverse data... canonical: https://daily.dev/posts/how-pdi-built-an-enterprise-grade-rag-system-for-ai-applications-with-aws-osvzeervg twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: How PDI built an enterprise-grade RAG system for AI applications with AWS | daily.dev og:description: PDI Technologies built PDIQ, an enterprise AI assistant powered by a custom RAG system on AWS serverless infrastructure. The solution crawls diverse data... og:url: https://daily.dev/posts/how-pdi-built-an-enterprise-grade-rag-system-for-ai-applications-with-aws-osvzeervg og:image: https://api.daily.dev/og/posts/oSVzEErvg.png og:image:alt: How PDI built an enterprise-grade RAG system for AI applications with AWS og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # How PDI built an enterprise-grade RAG system for AI applications with AWS **[AWS](https://daily.dev/sources/aws)** · 13 min read · 1 upvotes · 0 comments ## Summary PDI Technologies built PDIQ, an enterprise AI assistant powered by a custom RAG system on AWS serverless infrastructure. The solution crawls diverse data sources (websites, Confluence, SharePoint, Azure DevOps), processes documents with image captioning using Amazon Nova, implements intelligent chunking with document summaries, and stores vector embeddings in Aurora PostgreSQL. Key innovations include dynamic token management (70% content, 10% overlap, 20% summary), image caption injection for searchable context, and role-based access control. The system improved query accuracy from 60% to 79%, reduced support resolution times, and provides scalable knowledge access across business units using Amazon Bedrock foundation models. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [AWS aims to take the pain out of RAG with Bedrock Managed Knowledge Base](https://daily.dev/posts/aws-aims-to-take-the-pain-out-of-rag-with-bedrock-managed-knowledge-base-5adnuuplz) · InfoWorld · 2 upvotes · 0 comments - [Democratizing institutional knowledge: Building an AI-powered knowledge management system with AWS](https://daily.dev/posts/democratizing-institutional-knowledge-building-an-ai-powered-knowledge-management-system-with-aws-kmqgw0qtc) · AWS · 0 upvotes · 0 comments - [How Ricoh built a scalable intelligent document processing solution on AWS](https://daily.dev/posts/how-ricoh-built-a-scalable-intelligent-document-processing-solution-on-aws-48ujfcjyy) · AWS · 0 upvotes · 0 comments --- Tags: [#aws](https://daily.dev/tags/aws), [#llm](https://daily.dev/tags/llm), [#genai](https://daily.dev/tags/genai), [#rag](https://daily.dev/tags/rag), [#vector-search](https://daily.dev/tags/vector-search) [View this post on daily.dev](https://daily.dev/posts/how-pdi-built-an-enterprise-grade-rag-system-for-ai-applications-with-aws-osvzeervg) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"How PDI built an enterprise-grade RAG system for AI applications with AWS","url":"https://daily.dev/posts/how-pdi-built-an-enterprise-grade-rag-system-for-ai-applications-with-aws-osvzeervg","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/how-pdi-built-an-enterprise-grade-rag-system-for-ai-applications-with-aws-osvzeervg"},"datePublished":"2026-01-22T17:20:50.301Z","dateModified":"2026-01-22T17:21:14.240Z","description":"PDI Technologies built PDIQ, an enterprise AI assistant powered by a custom RAG system on AWS serverless infrastructure. The solution crawls diverse data...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/a43c27e999f819936faf8f1326220095?_a=AQAEulh","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/a43c27e999f819936faf8f1326220095?_a=AQAEulh","isAccessibleForFree":true,"articleSection":"AWS","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"AWS","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/aws","url":"https://daily.dev/sources/aws"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/how-pdi-built-an-enterprise-grade-rag-system-for-ai-applications-with-aws-osvzeervg","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"aws,llm,genai,rag,vector-search","timeRequired":"PT13M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"AWS","item":"https://daily.dev/sources/aws"},{"@type":"ListItem","position":3,"name":"How PDI built an enterprise-grade RAG system for AI applications with AWS"}]} ```