From 10 Terabytes to Zero Parameter: The LLM 2.0 Revolution

Description

I discuss why and how to build from scratch a RAG/LLM system for enterprise, without GPU or deep neural networks. Topics include accuracy, security, speed, scalability, no hallucination, exhaustivity in the prompt results, model evaluation issues, as well as real-time fine-tuning with intuitive parameters, self-tuning, efficient crawling to retrieve and leverage the underlying contextual elements, hierarchical chunking, token types, un-stemming, problems and workarounds when using Python libraries. The case study features the Nvidia corpus of public financial reports available as PDFs. Finally, I show how to design a great UI far more useful than a prompt box, an efficient backend database architecture, how to deal with various corpuses (Web, database, PDFs), multimodality, back-end agents that the user can select from the UI, sub-LLMs, and how to design your LLM to minimize prompt engineering.

Instructors Bio

Vincent Granville

Co-founder & AI Lead at BondingAI.io

Full-stack entrepreneur with multimillion-dollar exit. Co-Founder at BondingAI.io. Author (Wiley, Elsevier). Creator of open-source Python libraries / Web APIs such as xLLM and GenAI-Evaluation. Builder of high performance in-memory agentic multi-LLMs for professional users and enterprise, with real-time finetuning, self-tuning, no weight, no training, no latency, no hallucinations, no GPU. Made from scratch, leading to replicable results, leveraging explainable AI, adopted by Fortune 100. With a focus on delivering concise, exhaustive, relevant, and in-depth search results, references, and links. Vincent is a leading expert, mathematician, patent owner, former post-doc at Cambridge University, former VC-funded executive, with 20+ years of corporate experience including CNET, NBC, Visa, Wells Fargo, Microsoft, eBay. Vincent also founded and co-founded a few startups, including one with a successful exit (Data Science Central acquired by Tech Target). He is also a top influencer for brands such as Nvidia, SingleStore, and The Linux Foundation.