Build a RAG app using LangFlow +

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 walkthrough
3:45 - Building a pipeline with LangFlow
10:30 - Compiling LangFlow
12:40 - Exporting LangFlow pipeline as JSON
14:00 - Getting StreamLit working with LangFlow
15:04 - StreamLit code walkthrough
19:08 - StreamLit app demo
20:50 - Extro

RELATED LINKS
github repo for the app: https://github.com/ai-bites/simple-ra...
Phi 1 paper: https://arxiv.org/pdf/2306.11644
Phi 1.5 paper: https://arxiv.org/pdf/2309.05463
Phi 3 report: https://arxiv.org/pdf/2404.14219
LLaVA Phi paper: https://arxiv.org/pdf/2401.02330

MY KEY LINKS
YouTube:    / @aibites  
Twitter:   / ai_bites​  
Patreon:   / ai_bites​  
Github: https://github.com/ai-bites​

WHO AM I?
I am a Machine Learning researcher/practitioner who has seen the grind of academia and start-ups. I started my career as a software engineer 15 years ago. Because of my love for Mathematics (coupled with a glimmer of luck), I graduated with a Master's in Computer Vision and Robotics in 2016 when the now happening AI revolution started. Life has changed for the better ever since.

#machinelearning #deeplearning #aibites