End-to-end Smart RAG Chatbot with PineconeDB, Gemini AI | Shop Assistant Chatbot |

🛍️ In this video, we’ll build a powerful Shop Assistant Chatbot using Retrieval-Augmented Generation (RAG) with LangChain, Pinecone, and Gemini AI.

This is the first real-life use case of RAG on this channel — tailored for e-commerce and retail product catalogs! Unlike general AI models, this chatbot is trained on your shop’s own data and can respond with product-specific answers.

💡 What You’ll Learn:
- How to build a professional RAG pipeline
- Embedding product data from MySQL and syncing it to Pinecone
- Using LangChain with Google Gemini to generate context-aware responses
- Building the chatbot UI using Streamlit

📁 Tech Stack:
- MySQL (for shop data)
- Pinecone (as vector store)
- Google Gemini 1.5 Flash (LLM)
- LangChain (RAG framework)
- Streamlit (frontend deployment)

Timestamp :
00:00 - 01:29 : Intro
01:30 - 03:50 : Demo
03:51 - 07:15 : Process workflow
07:16 - 08:25 : Prerequisite
08:26 - 10:55 : Setup Environment
10:56 - 28:12 : Data Insertion to MySQL
28:13 - 56:04 : Sync with Pinecone DB
56:05 - 01:25:00 : Notebook for Retrieving Data
01:25:01 - 01:32:05 : Streamlit UI
01:32:06 - 01:35:12 : Final Result

🚀 This is Version 1 of the series, where we’ll continue upgrading this chatbot in future episodes — with admin panels, voice input, dynamic knowledge base updates, and much more.

🔔 Don’t forget to like, share, and subscribe if you want to follow this full AI build journey.

📄Kaggle Dataset Link : https://www.kaggle.com/datasets/supratimnag06/shop-product-catalog
🧠 GitHub Repo: https://github.com/snsupratim/ShopAssistantChatbot
#AI #Chatbot #LangChain #GeminiAI #Pinecone #RAG #Streamlit #Python

Видео End-to-end Smart RAG Chatbot with PineconeDB, Gemini AI | Shop Assistant Chatbot | канала sn dev