{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Chuck Yates Got A Job","title":"Drilling Down on Data with Bobby Neelon & John Kalfayan (Collide)","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/88e58198\"></iframe>","width":"100%","height":180,"duration":2486,"description":"Bobby Neelon and John Kalfayan from Collide break down the messy reality of getting data ready for RAG, why PDFs are dumpster fires for unstructured data, how extraction changes depending on whether you're dealing with drilling surveys or handwritten logs, and why chunking strategy matters more than people think. They walk through embeddings, vector databases, MCP servers for pulling external data without leaking internal info, and why good metadata and folder structure actually make AI deployments way easier. Plus the hard truth that AI isn't a silver bullet for bad data management and the crap-in-crap-out problem is getting worse because now it can hallucinate on top of the crap.\nClick here to watch a video of this episode.\n\n0:00 - Introductions and RAG overview\n3:15 - Document identification and classification challenges\n8:40 - Extracting data from unstructured PDFs\n13:25 - Real world examples of messy data formats\n18:50 - OCR paired with vision models for extraction\n22:10 - Chunking strategies and when to use each\n26:35 - Embeddings and vector databases explained\n30:20 - MCP servers and external data integration\n35:45 - Getting data AI-ready with metadata and structure\n40:30 - Text-to-SQL approaches and database access\n44:15 - Handling duplicates and M&A data integration\n48:50 - How AI learns context over time\n53:40 - Why traditional data management matters more than ever\nhttps://twitter.com/collide_io\nhttps://www.tiktok.com/@collide.io\nhttps://www.facebook.com/collide.io\nhttps://www.instagram.com/collide.io\nhttps://www.youtube.com/@collide_io\nhttps://bsky.app/profile/digitalwildcatters.bsky.social\nhttps://www.linkedin.com/company/collide-digital-wildcatters","thumbnail_url":"https://img.transistorcdn.com/c5WQufo5wbt5DUoayihGmjPfi-6mpIXlFv-B8NwxUXk/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS81ODIw/NmQyYjMwOTI3MTcw/NjU3ZTI2NDViYTlk/M2NkNi5qcGc.webp","thumbnail_width":300,"thumbnail_height":300}