In this video, we take a deep dive into how to create RAG apps using only JavaScript, leveraging LangChain and Pinecone as the vector database. You'll learn how to use these tools, perform embeddings, and connect everything together. We'll also cover how to fetch text from URLs, split it, handle PDFs, and break them into chunks. Finally, we'll demonstrate how to run RAG locally with Ollama
Support Me on Petron ⚡: / codewello
00:00 - Intro & Vote
00:30 - Topics in this Video
01:20 - Env Setup
04:10 - API Keys
04:34 - Project Structure & First RAG
09:27 - What is RAG ?
12:13 - Vector Database Setup
13:45 - Embeddings
18:30 - Save To Vector Database
21:36 - Q&A RAG
25:47 - PDFs
29:06 - Ollama
32:00 - Links & Code
Code 👉 https://github.com/HossamEldinx/ai-ag...
Vote for next video 👉 / @codewello
My Pc Parts 🖥️
My Pc Parts 🖥️
RTX 3070: https://amzn.to/4cNpMjp
CPU :https://amzn.to/4dL12K1
SSD : https://amzn.to/4g2dUgt
_______________________________________________________________
🤖 Open AI Template Alima : https://codewello.gumroad.com/l/kjlzw
💷 50% Discount Code : A2LH6LZ
👉 Linkedin : / hossam-eldin
_______________________________________________________________
#langchain #ollama #rag