Difference between revisions of "Being-Creative-with-AI/C4/Rag-and-its-Uses/English"
Ketkinaina (Talk | contribs) (Created page with "'''Title of the Script: RAG and its Uses.''' '''Author: EduPyramids''' '''Keywords: RAG, Retrieval, Generation, Chatbot, AI, EduPyramids, video tutorial.''' {|border=1 |- |...") |
Bellatony911 (Talk | contribs) |
||
| Line 19: | Line 19: | ||
'''Learning Objectives''' | '''Learning Objectives''' | ||
|| In this tutorial, we will learn: | || In this tutorial, we will learn: | ||
| − | * How an '''AI''' model answers questions using additional information | + | * How an '''AI''' model answers questions using additional information |
| − | * What is '''Retrieval-Augmented Generation(RAG)''' | + | * What is '''Retrieval-Augmented Generation (RAG)''' |
| − | * How '''RAG''' helps improve the accuracy of answers | + | * How '''RAG''' helps improve the accuracy of answers |
|- | |- | ||
|| '''Slide 3''' | || '''Slide 3''' | ||
Revision as of 16:23, 21 May 2026
Title of the Script: RAG and its Uses.
Author: EduPyramids
Keywords: RAG, Retrieval, Generation, Chatbot, AI, EduPyramids, video tutorial.
| Visual Cue | Narration |
| Slide 1
Title Slide |
Welcome to this Spoken Tutorial on RAG and its Uses. |
| Slide 2
Learning Objectives |
In this tutorial, we will learn:
|
| Slide 3
Disclaimer Slide As AI tools constantly evolve, if you are unable to locate any icon or encounter difficulty at any step, you may use any conversational AI Chatbot for guidance. |
As AI tools constantly evolve, if you are unable to locate any icon or encounter difficulty at any step, you may use any conversational AI Chatbot for guidance. |
| Slide 4
System Requirements |
To record this tutorial, I am using:
Learners will also need a working internet connection |
| Slide 5
Prerequisites |
To follow this tutorial,
|
| Let us get started. | |
| Show grocery app order (1 kg onions) | Imagine this: you ordered one kilogram of onions from a grocery app. |
| Show wrong delivery (tomatoes) | But you receive one kilogram of tomatoes instead. |
| Show support chat opening | To resolve this, you open the support section of the app.
You ask the support chatbot: “I got the wrong item. Can I return it?” |
| Show chatbot response | The chatbot powered by AI gives you an answer. |
| Pause on screen (AI thinking?) | But how does it know what to say? |
| Show AI model trained on large data | The AI model is trained on a large amount of general text data. |
| Show How AI is helping to understand languages and generating responses as well | This helps it understand language and generate responses. |
| Highlight limitation | However, this training does not include the app’s return policy.
It is unique to each company |
| Show return policy document | The return policy exists as a separate document on the company’s server. |
| Show secure storage | This document is stored securely and is not part of the model’s training. |
| Show search inside documents | When you ask the question, the system first searches the policy document. |
| Highlight relevant lines | It finds the most relevant information related to your query. |
| Show info + question sent to AI | This information is sent along with your question to the AI model. |
| Show final response generation | The AI model then generates an answer based on this information. |
| Highlight term RAG | This process is called Retrieval-Augmented Generation, or RAG. |
| Show chatbot without policy | Let us see what happens without a policy document for the chatbot.
When a user asks “I got the wrong item in a grocery app. Can I return it?” Without specific information, the chatbot gives a general response. The response may not match the company’s actual return policy. |
| Show policy document | Now imagine the same question is asked with a policy document. |
| Display policy points | The policy states that items can be returned within 24 hours.
Perishable items cannot be returned. Refunds take 3 to 5 business days. |
| Ask same question again | We ask the same question again. |
| Show improved answer | Observe the new response. |
| Highlight improvement | The answer now clearly follows the given policy. |
| Compare both responses | The first response is general. The second response is accurate and specific. |
| Embedding / vector visual | The question is converted into a machine-readable form. |
| Search visual | The system searches for similar information in the document. |
| Highlight retrieval | The most relevant part is retrieved. |
| Send to model | This retrieved content is sent to the AI model. |
| Final answer generation. | The model generates the final answer using this information. |
| Slide 6
Key Idea behind RAG
|
This is the key idea behind RAG.
RAG lets AI fetch relevant data and generate more accurate answers. |
| With this, we come to the end of this tutorial. | |
| Slide 7
Summary In this tutorial, we learnt to:
|
In this tutorial, we learnt to:
|
| Slide 8
Assignment As an Assignment,
|
We encourage you to do this assignment. |
| Slide 9
Acknowledgement Domain Inputs: Bhavani Shankar R and Saisudha Sugavanam Script Writer: Ketki Naina Admin Reviewer: Arthi Varadarajan Quality Reviewer: Sakina Sidhwa Novice Reviewer: Misbah Samir AI Narration: Debosmita Mukherjee AI Graphics: Arvind Pillai Video Editor: Arvind Pillai Web Developer: Ankita Singhal |
Thank you for watching. |
| Slide 10
Acknowledgement This Spoken Tutorial is brought to you by EduPyramids Educational Services Private Limited at SINE, IIT Bombay. |
