Let’s Build an AI Chatbot for Expo Docs: RAG Tutorial

In this video, learn how to build an AI chatbot using Retrieval-Augmented Generation (RAG) systems. We'll guide you through obtaining data from Expo Docs, generating vector embeddings, storing them in a vector database, and performing similarity searches. Finally, we'll integrate everything into a sleek chat UI for both mobile and web using Expo and Expo Router. Ready to get started and build your own AI Chat Bot? 🤖

⚛️ *React Native Mastery* is the *ONLY* course you need to Master mobile development with React Native & Expo 🚀

📚 This video includes a lot of tools and technologies, providing an excellent opportunity to learn about:
- RAG systems
- Gathering data from Expo Docs
- Generating vector embeddings
- Storing embeddings in a vector database
- Performing similarity searches
- Building a chat User Interface with Expo and Expo Router

📚 Enroll NOW in *The Full-Stack Mobile Developer course* and don’t miss out on your chance to become a 6-figure dev! Check out what our successful students are saying about their experience:

*💬 Join the notJust Development gang and let's build together:*

Timecodes:

Disclaimer: This build is for educational purposes only. All views, opinions, and technology choices expressed in this video are my own and do not represent the views, opinions, or technology choices of any entity I have been, am now, or will be affiliated with.
#notjustdev #aichatbot #reactnative

[SAMAmUrl]

Pure pleasure, I have to sleep early for next day Dragon Boat Competition, then Found myself surfing on the presentation Wave. It worth it. Thank you Vadim for making things simpler fro the mere mortal developper,

[tref]

Awesome project! Thanks Vadim for clarifying RAG

[UnchartedWorlds]

I'm just going through this one! Perfect tutorial!

[tref]

for getting embedding (to get vector from a text)
BadRequestError: 400 This model's maximum context length is 8192 tokens, however you requested 9193 tokens (9193 in your prompt; 0 for the completion). Please reduce your prompt; or completion length.
For example for the slug 'modules/module-api' or 'guides/authentication'

[ravilamontagne]

Why was it necessary to use the raw text from Github and not just scrap the text from the website? What if you have text stored in a database, how to pass that data to the vector database?

[birolaydin]

Great content. How can we print the answers letter by letter?

[iychlvh]

When is your ultimate react native course?