From the course: Oracle Cloud Infrastructure Generative AI Professional Cert Prep

Unlock this course with a free trial

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

Q&A chatbot architecture and basic components

Q&A chatbot architecture and basic components - Oracle Cloud Infrastructure Tutorial

From the course: Oracle Cloud Infrastructure Generative AI Professional Cert Prep

Start my 1-month free trial Buy for my team

Q&A chatbot architecture and basic components

“

(bright music) - [Hemant] The workflow of a chatbot begins with a question from a user. Sometimes question alone is not sufficient to arrive at the right answer. We may like to add information or instructions or both through a prompt. We may also provide additional context by fetching relevant documents to our question and include these in our prompt. We may also consider including a set of prior questions and answers that we have stored in a memory. We provide all these to LLM as input. LLM responds back with an answer and we update memory with the last question and answer. We already have learned that OCI generative AI offers us a variety of features to generate, summarize, and embed data. We can leverage all these useful and powerful features to build very useful applications. Open source framework LangChain offers multitude of components to build LLM-based applications, including an integration with OCI Generative AI service, vector databases, document loaders, and many others…

Contents