Retrieval-Augmented Generation (RAG)

Retrieval-augmented generation (RAG) is a hybrid approach in AI that combines two key techniques: document retrieval and generative modeling. RAG first retrieves relevant information or documents from a large database and then uses a generative model (such as ChatGPT) to process the available data and generate a response based on both the retrieved data and the input query. This technique enhances the accuracy and relevance of generated content, especially when dealing with domain-specific knowledge or large datasets.

‍

Related terms: generative AI; vector embeddings

‍

On the Onehouse website:

• Managing AI Vector Embeddings with Onehouse
• Announcing: AI Vector Embeddings Generator for the Lakehouse