From the course: Complete Guide to Data Lakes and Lakehouses

Unlock the full course today

Join today to access over 25,200 courses taught by industry experts.

Introduction to RAG (retrieval-augmented generation)

Introduction to RAG (retrieval-augmented generation)

From the course: Complete Guide to Data Lakes and Lakehouses

Start my 1-month free trial Buy for my team

Introduction to RAG (retrieval-augmented generation)

“

- [Instructor] Now that I've clarified the topic of LLMs and how they relate to our project, let's quickly talk about retrieval-augmented generation, or RAG. Retrieval-augmented generation combines the strengths of retrieval based and generation based models. By retrieving relevant information from our dynamic document database during the text generation process, ragging enhances the quality and relevance of responses generated by the system. The modern retrieved relevant documents or passages from an external knowledge base based on the user's context or query. The retrieved information is then fed into a generative model, which uses it to generate a coherent and contextually accurate response. For our project, we use RAG to enhance the accuracy and relevance of the Cisco pilot's responses. By retrieving information from our document base and feeding it into the Mistral model, we ensure the answers are contextually accurate. These are some of the benefits of applications of…

Contents