Learn how to build a scalable AI-powered chatbot using Wikipedia video game data in this comprehensive tutorial. Explore the implementation of semantic search and Retrieval-Augmented Generation (RAG) with SingleStore, optimize performance using vector indexes, and integrate OpenAI's GPT models to create an interactive, data-driven chat experience. Follow along as the instructor guides you through database setup, mock vector generation, data retrieval from Wikipedia, vector index construction, index testing, hybrid search implementation, and the final chatbot integration. Gain practical insights into building advanced AI applications with real-world data sources and cutting-edge technologies.
Building a Scalable AI Chatbot with Wikipedia Data - Semantic Search and RAG
Overview
Syllabus
Introduction
Database setup
Generating the mock vectors
Getting the Wikipedia video game data
Building the vector indexes
Testing our indexes
Hybrid search in SingleStore
Chatting with the video game data
Closing remarks
Taught by
Kunal Kushwaha
Related Courses
-
Vector Databases for Embeddings with Pinecone
-
Vector Search RAG Tutorial – Combine Your Data with LLMs with Advanced Search
-
Vector Databases: from Embeddings to Applications
-
LangChain Chat with Your Data
-
RAG from Scratch with Llama 3.1 - Building a Custom Data Chatbot
-
Understanding Generative AI: RAG, Semantic Search, Embeddings, and Vectors
