{"id":73483,"date":"2023-12-14T05:00:00","date_gmt":"2023-12-14T13:00:00","guid":{"rendered":"https:\/\/www.salesforce.com\/?p=73483"},"modified":"2025-03-27T16:29:16","modified_gmt":"2025-03-27T23:29:16","slug":"retrieval-augmented-generation-explained","status":"publish","type":"post","link":"https:\/\/www.salesforce.com\/news\/stories\/retrieval-augmented-generation-explained\/","title":{"rendered":"How Einstein Copilot Search Uses Retrieval Augmented Generation to Make AI More Trusted and Relevant"},"content":{"rendered":"\n

Editor\u2019s note: Einstein 1 Platform is now the Salesforce Platform. For the latest, go <\/em>here<\/em><\/a>.<\/em><\/p>\n\n\n\n

\n\n\n\n

At World Tour NYC<\/a>, Salesforce introduced new unstructured data capabilities for Data Cloud and Einstein Copilot Search<\/a>. By bringing together data retrieval capabilities using semantic search and prompts in Einstein Copilot, responses by Large Language Models (LLMs) will be more accurate, up-to-date, and generated with more transparency \u2014 while also keeping company data safe and secure through the Einstein Trust Layer<\/a>.<\/p>\n\n\n\n

These powerful new features are underpinned by an AI framework called Retrieval Augmented Generation (RAG), which enables companies to use their structured and unstructured proprietary data to make generative AI<\/a> more trusted and relevant.  <\/p>\n\n\n\n

What is RAG?<\/strong><\/h2>\n\n\n\n

Put simply, RAG helps companies retrieve and use their data, no matter where it lives, for better AI results. The RAG pattern coordinates queries and responses between a search engine and an LLM, and importantly, can operate on unstructured data such as emails, call transcripts, knowledge articles, and other formats that don\u2019t fit cleanly into a typical relational data source. RAG can be more specifically described using its name: <\/p>\n\n\n\n