Programming Large Language Models with Azure Open AI: Conversational programming and prompt engineering with LLMs
by Francesco Esposito
Chapter 7
Chat with your data
After exploring the use of Azure OpenAI APIs for a simple example that only involved prompt engineering, it’s time for a more complex use case. In this chapter, you will learn how to build a corporate chatbot that responds based on a document database that you will construct. Initially, this database will contain unstructured or semi-structured documents, but you will see how to extend the demo to use structured data in the last section of the chapter.
To achieve this, you will use an orchestrator to apply the RAG pattern, with the final section covering some of its possible extensions. You will construct the orchestrator using LangChain and will use Streamlit—a user-friendly web framework for developing what are ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access