Can AI explain itself? In other words, if I take an AI model and ask it questions about any other AI model, I would expect it to answer my questions. But it turns out that the model simply doesn’t know about any other models. Can a simple workaround for this problem lie with Retrieval Augmented Generation or RAG.
I developed a chat app using LangFlow and StreamLit with minimal coding and solved this very problem. It uses a RAG pipeline in the backend. I provided the retrieval system with all the papers on the Phi series of models developed by Microsoft and eventually, the system was able to answer my questions about the Phi family of models.
So in this video, I will walk you through how I went about developing the pipeline and along the way demonstrate how easy it is to develop a chat app using LangFlow.
⌚️ ⌚️ ⌚️ TIMESTAMPS ⌚️ ⌚️ ⌚️
0:00 – Intro
1:11 – Problem with existing LLMs (LLAMA2 example)
2:09 – LangFlow Installation
3:18 – LangFlow UI…