{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Beyond the CMS - A Content Management Podcast","title":"Search Is the Interface: Semantic Search and RAG with Olivier Dobberkau","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/6b48deb6\"></iframe>","width":"100%","height":180,"duration":2483,"description":"What happens when website search evolves from a keyword box into an intelligent interface?\nIn Episode 50 of Beyond the CMS, Chris Bryce speaks with Olivier Dobberkau, CEO and founder of dkd Internet Service GmbH and president of the TYPO3 Association, about how enterprise search is moving from keyword matching toward semantic search, retrieval-augmented generation (RAG), conversational experiences and agent-readable interfaces.\nOlivier explains why AI search begins with content quality, metadata and retrieval. They discuss Apache Solr for TYPO3, embeddings, document chunking, grounding, hallucination risks, search feedback and the difference between a generic chatbot and specialized search capabilities routed by user intent.\nIn this episode:\nWhy search is becoming an interface rather than only a search box\nHow keyword search differs from semantic search and RAG\nHow Apache Solr supports TYPO3 search\nWhy poor content creates poor AI-search results\nHow chunking can remove important context\nWhy specialized search capabilities can outperform generic chatbots\nHow real questions, zero-result searches and user feedback improve retrieval\nWhy organizations should repair content before adding generated answers\nChapters\n0:00 Welcome to Beyond the CMS Episode 50\n2:06 Olivier Dobberkau, dkd and the TYPO3 ecosystem\n5:32 Apache Solr search for TYPO3\n7:23 Why search is becoming the interface\n11:21 From keywords to conversational and agentic search\n13:47 Content quality, grounding and search quality\n19:46 Why chatbots are not always the right experience\n22:37 Specialized search capabilities and intent routing\n24:02 Question-based website search in practice\n26:19 Repairing content before adding RAG\n28:33 Retrieval, metadata, feedback and supervision\n31:25 RAG explained: indexing, embeddings and retrieval\n34:16 Chunking, context and grounded answers\n36:39 Open source, access and the TYPO3 community\nAbout Olivier Dobberkau\nOlivier Dobberkau is CEO and founder of dkd Internet Service...","thumbnail_url":"https://img.transistorcdn.com/FO-MfURcPdfZAybU3p1Sq0_mV2DxhS0owOU508deeIY/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS9lNjcx/M2I0M2FjODk0Yjg4/ODdjZDJkMDM1NWE3/ZGE0ZS5wbmc.webp","thumbnail_width":300,"thumbnail_height":300}