RAGChat: Optimal retrieval with Azure AI Search

preview_player
Показать описание

Our RAG solution uses Azure AI Search to find matching documents, using state-of-the-art retrieval mechanisms. We'll dive into the mechanics of vector embeddings, hybrid search with RRF, and semantic ranking. We'll also discuss the data ingestion process, highlighting the differences between manual ingestion and integrated vectorization



#MicrosoftReactor #learnconnectbuild #RAGDeepDive

[eventID:24572]
  1. Microsoft Reactor
Рекомендации по теме
RAGChat: Optimal retrieval 1:04:16

RAGChat: Optimal retrieval with Azure AI Search

RAGChat: The RAG 1:03:30

RAGChat: The RAG solution for Azure

Agentic RAG: build 1:04:21

Agentic RAG: build a reasoning retrieval engine with Azure AI Search | BRK142

Multimodal RAG: Chat 1:11:04

Multimodal RAG: Chat with PDFs (Images & Tables) [2025]

What is Retrieval-Augmented 0:06:36

What is Retrieval-Augmented Generation (RAG)?

What is Agentic 0:05:42

What is Agentic RAG?

RAGChat: Customizing our 1:01:57

RAGChat: Customizing our RAG solution

Evaluating your RAG 1:01:12

Evaluating your RAG Chat App

Building AI Agents 0:16:08

Building AI Agents with RAG Search (Microsoft Managed) using Azure AI Agent Service

RAG vs. Fine 0:08:57

RAG vs. Fine Tuning

RAGChat: Multimedia data 0:59:38

RAGChat: Multimedia data ingestion

Build a RAG 0:54:29

Build a RAG Agent with Azure AI Search

How to Build 0:29:35

How to Build a RAG System with Azure OpenAI & Python Step by Step Tutorial

Build a Large 0:02:53

Build a Large Language Model AI Chatbot using Retrieval Augmented Generation

Python RAG Tutorial 0:21:33

Python RAG Tutorial (with Local LLMs): AI For Your PDFs

GraphRAG vs. Traditional 0:04:17

GraphRAG vs. Traditional RAG: Higher Accuracy & Insight with LLM

RAGChat: Private deployment 0:49:15

RAGChat: Private deployment

RAGChat: Extending RAG 1:02:40

RAGChat: Extending RAG with function calling

RAGChat: User login 1:05:31

RAGChat: User login and data access control

Learn RAG From 2:33:11

Learn RAG From Scratch – Python AI Tutorial from a LangChain Engineer

RAG + Langchain 0:16:42

RAG + Langchain Python Project: Easy AI/Chat For Your Docs

Vector Search RAG 1:11:47

Vector Search RAG Tutorial – Combine Your Data with LLMs with Advanced Search

Vector search, RAG, 1:04:54

Vector search, RAG, and Azure AI search

Multimodal RAG - 0:17:39

Multimodal RAG - Chat with Text, Images and Tables

Комментарии
Автор

What would be the reason to set semantic score on scale 0-4, while 99% of AI stuff is normalized to 1?

MariuszAndrzej-iqyt
Автор

Thanks for the session!
What would be the best place to follow for integrated vectorization updates.
In particular would be interested in whether there's a plan to introduce the page number / sourcepage references out of the box.
Another potentially useful feature for indexer - define in which cases to skip auto re-indexing the doc(.e.g custom metadata assigned, no contents changed)
At this point had to create a custom solution for locating PDF page numbers for indexed document chunks.

alexeymind
Автор

I see that there is an option to manage files. Is this feature standard for all users? That is to say that each user can manage his files individually and make his own RAG (remove and add his own files to the feature)?

jordan
welcome to shbcf.ru