Build A Chat With Your Documents App Using RAG With Snowflake Cortex

Despite foundational LLMs’ requiring extensive training, their knowledge base is outdated and lacks information that is protected inside the enterprise. To address hallucinations that LLMs may have from unseen information, retrieval augmented generation (RAG) is a cost-effective strategy that teams can use to build chatbots on top of an enterprise knowledge base.

In this hands-on lab, leading Snowflake AI/ML Architect, Carlos Carrero, will show you how to easily and securely build your own AI apps. You will also learn how to:

• Deploy an automated pipeline that converts documents into vectors ready for semantic search
• Build an end to end RAG app without complex orchestration, integrations or infrastructure to manage
• Develop chat interfaces to quickly test, prototype and deploy business-facing applications