Scribd
Upload
30 views10 pages

Rag PDF

RAG (Retrieval Augmented Generation) is a method that enhances Large Language Models by retrieving relevant external information before generating responses. It is particularly useful for providing accurate answers based on specific data, handling real-time information, and supporting complex decision-making. Applications include customer support, healthcare, legal research, education, and financial services, where it improves accuracy and reduces errors.

Uploaded by

sathyaselvaraj000
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
30 views10 pages

Rag PDF

RAG (Retrieval Augmented Generation) is a method that enhances Large Language Models by retrieving relevant external information before generating responses. It is particularly useful for providing accurate answers based on specific data, handling real-time information, and supporting complex decision-making. Applications include customer support, healthcare, legal research, education, and financial services, where it improves accuracy and reduces errors.

Uploaded by

sathyaselvaraj000
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 10

RAG (Retrieval

Augmented Generation)
What is RAG?
It is a method where a Large Language Model (LLM) gets help from external information
(like documents, PDFs, websites) before answering a question.

RAG combines two powerful steps:

Retrieval – It searches and finds the most relevant information from external sources
(like PDFs, websites, or documents).
Generation – It then uses a Large Language Model (LLM) to create a smart, human-
like response using that retrieved information.
Where to use RAG?
RAG is ideal when you need:

Accurate answers based on specific or private data


Real-time or frequently changing information
Combining AI creativity with trustworthy facts
Handling large volumes of documents or data that are too big for the AI to memorize
Supporting complex decision-making by retrieving relevant context
Enabling customized responses based on company or domain-specific knowledge
Enhancing search engines to provide more meaningful, context-aware results
Purpose of RAG
Improves Accuracy: AI gives better
answers using real, updated info.

Stays Current: Uses the latest files,


articles, or data.

Safe with Private Data: Works securely


with sensitive documents.

Fewer Mistakes: Reduces wrong or


made-up answers.

Smart & Creative: Combines facts


with natural language.
NO 3
Application of RAG

Customer Support Chatbots: Answer customer questions using company manuals,


FAQs, and policies.

Healthcare Assistants: Provide medical advice based on latest research papers


and patient records.

Legal Research Tools: Retrieve relevant laws, case studies, and legal documents to
assist lawyers.

Education Platforms: Help students by answering questions using textbooks


and course materials

Enterprise Knowledge Bases: Employees get quick, accurate answers from


internal documents and guidelines.

Financial Services: Assist in retrieving and analyzing financial reports and regulations.

Research & Development: Help scientists and engineers find relevant papers, patents,
or data quickly.

NO 3
Example of RAG
Imagine a company has hundreds of documents about their products and policies. A customer asks:

“How long do I have to return a product?”

The chatbot uses RAG to first search the company’s policy documents for relevant info.

It finds the “30-day return policy” details stored in the vector database.

Then it uses the LLM to generate a clear answer:

“You can return the product within 30 days from purchase.”

This way, the chatbot gives an accurate answer based on real company data, not just guesswork.

NO 3
Thank YOU

You might also like