How I Learned to Stop Worrying and Love the AI — Integrating LLMs into a DMS
summary
A CTO describes integrating large language models into a document management system using Retrieval-Augmented Generation (RAG). The talk covers practical issues: where generic LLMs fall short for enterprises, how search must respect existing access controls, keeping results up to date, and maintaining data protection.
AI-written summary · about
chapters (9)
- 0:00Introduction
- 1:04Future vision
- 2:52AI as new interaction
- 5:39Devs obsolete?
- 7:47AI in DMS
- 10:15Live AI demo
- 12:47AI integration challenges
- 15:33AI risks or chances
- 17:00Q&A
related talks
53mFrom RAG to Riches: Secrets of Data-Augmented LLMs
57mLLMs gone wild
18mLLMs and GenAI: A Guide to Building Your Own RAG Model for Document Interaction
49mA Practical Approach to Using LLMs: Peculiarities and Pitfalls
47mA Step-by-Step Guide to Securing Large Language Models (LLMs)
36mTechniques to avoid common LLM pitfalls
56mSmart search over internal knowledge base with LLMs: from architecture to deployment
44mRAG for a Medical Company: Technical and Product Challenges AI & Data