From the course: Oracle Cloud Infrastructure Generative AI Professional

Unlock this course with a free trial

Join today to access over 24,900 courses taught by industry experts.

Conversational RAG

Conversational RAG - Oracle Cloud Infrastructure Tutorial

From the course: Oracle Cloud Infrastructure Generative AI Professional

Start my 1-month free trial Buy for my team

Conversational RAG

“

(soft music) (graphic whooshing) - [Hemant] So far, we discussed what RAG is, and how RAG pipeline is implemented. We now understand how RAG helps us improve the context of our query by retrieving relevant documents, and sending these to the LLM for getting more relevant and specific response to our query. RAG is used often to create chatbots. Chat is a series of question and answers. A user will ask a question, LLM will provide an answer, and then user will follow with a next question, and so on. RAG is used to answer the questions by using the relevant information from the provided ex-corpus. In case of a chat, even the prior questions and answers may act as an additional context to the next question. For example, if we ask, "Tell me about Las Vegas," and the next question is, "Rell me about its typical temperature throughout the year," it's, in the second question, is referring to Las Vegas. In order to maintain a list of questiod asked and answers given, a concept of memory is…

Contents