• Version
• Download 5
• File Size 550.83 KB
• File Count 1
• Create Date 5 March 2025
• Last Updated 5 March 2025

RAG -CLONE A Generic Framework

RAG -CLONE

A Generic Framework

Dr. T. Syam Sundara Rao1, P. Venkata Snehalatha2, R. Lakshmi Naga Chaitanya3, M. Aparna4,

Sk. Haleema Kusum5

Associate Professor of CSE-Data Science, KKR & KSR Institute of Technology and Sciences1, Guntur, AndhraPradesh, India.B. Tech CSE-Data Science, KKR & KSR Institute of Technology and Sciences, Guntur, Andhra Pradesh, India2-5.

ABSTRACT

This paper presents a RAG system (Retrieval Augmented Generation)that aims to improve how AI processes, accesses ,and generates information. Our approach uses Vector embedding to improve data absorption and  provide more accurate and contextual answers using FAISS-based on the similarity and the mistral searches.

The system is created to process unstructured, unstructured data from a variety of sources, including PDFs and Excel files. Users can interact with text-based queries as well as  voice commands. To make this simple, we integrate Whisper AI for speech recognition, allowing users to ask  questions verbally, but Google's text speech (GTTS) gives  the answer generated by AI to speak the spoken language.  Convert to feedback.

An important feature of our system is the ability to store and show information at a granular level. Instead of dealing with the entire document, organize and retrieve relevant sections to ensure more detailed answers. FAISS-based similarity search helps you efficiently find the most  relevant information in large data records, but Mistral AI  produces documents to improve the quality and consistency of answers will be improved.

User can perform a profound search process, extract  meaningful knowledge, and interact in a seamless, intuitive way using AI-controlled knowledge .Ultimately,ourrag system bridges the gap between data calls andAI-controlled  content generation, making information accessible and easy implementable in a variety of applications.

Keywords:

Large Language Models (LLMs), Data Pipelines, Data Retrieval