Explore the process of integrating personal data with Large Language Models (LLMs) like GPT using Azure AI Search in this comprehensive 58-minute video tutorial. Learn about the importance of using your own data, source data preparation, and the implementation of Azure AI Search for data integration. Discover techniques for importing, indexing, and chunking data, as well as handling various media types. Gain insights into hybrid search methods, including keyword search and BM25, and understand the role of the orchestrator component. Follow along as the instructor demonstrates using the Playground, adding data sources, and performing interactions backed by personal data through Retrieval-Augmented Generation (RAG). Conclude with a summary of key concepts and practical applications for leveraging your own data with LLMs.
Using Your Own Data with Large Language Models (LLMs) - Making JohnBot
John Savill's Technical Training via YouTube
Overview
Syllabus
- Introduction
- Why we need to use our own data
- Your source data
- Using Azure AI Search
- Integration and reading data
- Import and index
- What interval should be used?
- Viewing the index and indexer
- Chunking
- Other types of media beyond text
- IF YOU REMEMBER ONE THING :-
- Keyword search is still useful so we need hybrid
- BM25 searching
- Hybrid search with RRF
- Orchestrator component
- Using the Playground and key settings such as memory
- Adding my data source
- Performing an interaction backed by my data RAG
- The response and references
- Summary
- Close
Taught by
John Savill's Technical Training
Related Courses
-
Knowledge Graphs for RAG
-
Vector Search RAG Tutorial – Combine Your Data with LLMs with Advanced Search
-
Generative AI Architecture and Application Development
-
Mastering Retrieval for LLMs - BM25, Fine-tuned Embeddings, and Re-Rankers
-
Understanding Generative AI: RAG, Semantic Search, Embeddings, and Vectors
-
Building a Scalable AI Chatbot with Wikipedia Data - Semantic Search and RAG
