A casual tech talk to share how I turbocharged PDF indexing (shredding and embedding) for use by LLMs (Large Language Models). I'll show off my open-source AI pipeline system, SlothAI, and explain how it uses Google Cloud Storage and Document AI to supercharge PDF text extraction for passing data to embeddings models.
Kord is a programmer and founder with a focus on AI and search technology. He started Mitta and MittaAI, specializing in document and data processing systems. Earlier in his career, he created Grub, an open-source search engine, and co-founded Loggly. His work emphasizes simplifying data interaction and processing.