Overview
Learn to build a Retrieval Augmented Generation (RAG) application in this 21-minute tutorial that demonstrates how to create a chat app capable of answering questions about AI models. Walk through the process of developing a RAG pipeline using LangFlow and StreamLit with minimal coding requirements, specifically focusing on implementing a system that can retrieve and discuss information about Microsoft's Phi series of models. Master essential concepts including LangFlow installation, UI navigation, pipeline construction, JSON export procedures, and StreamLit integration. Follow along with comprehensive demonstrations of the StreamLit code implementation and see the finished application in action. Access the complete project materials through the provided GitHub repository, which includes references to relevant papers about the Phi model series.
Syllabus
- Intro
- Problem with existing LLMs LLAMA2 example
- LangFlow Installation
- LangFlow UI walkthrough
- Building a pipeline with LangFlow
- Compiling LangFlow
- Exporting LangFlow pipeline as JSON
- Getting StreamLit working with LangFlow
- StreamLit code walkthrough
- StreamLit app demo
- Extro
Taught by
AI Bites