Building a Generative Ai App on Private Enterprise Data With Retrieval Augmented Generation (Rag)

16:40 - 17:10 | AI & MLOPS THEATRE
BUILDING A GENERATIVE AI APP ON PRIVATE ENTERPRISE DATA WITH RETRIEVAL AUGMENTED GENERATION (RAG)
WEDNESDAY 20 SEPTEMBER 2023
SPEAKER: MADHUKAR KUMAR

Large Language Models (LLMs) are typically trained on a large collection of publicly available data with an expiration date. Unfortunately this means LLMs are unable to recall any data outside their repository, making them overall less effective for domain-specific tasks.

Retrieval Augmented Generation (RAG) is a technique designed to recall data from outside a foundational LLM, enhancing queries by introducing relevant, semantic data into the context of the original query.

In this session led by SingleStore CMO Madhukar Kumar, you’ll get an immersive, hands-on look at how to build a generative AI application on your private enterprise data with RAG using SingleStoreDB.

The session will cover:

• How to introduce RAG into your foundational LLM
• Real-world use cases where RAG can be incorporated into generative AI applications
• How SingleStoreDB leverages RAG as a more cost-effective option to pre-training and fine-tuning LLMs, reducing hallucinations