Palakgarg155

LegalRAG-Evaluation

This repository contains evaluations of LLM-based Retrieval-Augmented Generation (RAG) pipelines tailored for the legal domain. It currently features RAG with three different LLMs: Mistral, OpenAI, and Phi3:Medium.

PubEvalAI

Developing an Evaluation Framework for Conversational AI in Public Procurement: Enhancing Decision-Making in AI Product Selection

Agentic-RAG-Implementation

This project implements a Retrieval-Augmented Generation (RAG) pipeline designed to answer questions based on the content of a knowledge base PDF. The system is enhanced with the agents that performs various intelligent actions.

LegalRAG-Eval

Making-MU-

Developed a novel metric to evaluate conversational AI solutions' effectiveness in filtering spam and irrelevant queries, addressing issues such as topical quadrails, prompt leaking, and jailbreaking.

MindAI-Evaluation

Multilingual-RAG-Evaluations

Palakgarg155

Config files for my GitHub profile.

rag-evaluator

A library for evaluating Retrieval-Augmented Generation (RAG) systems (The traditional ways).

The-Grand-Complete-Data-Science-Materials

Palakgarg155/Multilingual-RAG-Evaluations

Palakgarg155/Agentic-RAG-Implementation

This project implements a Retrieval-Augmented Generation (RAG) pipeline designed to answer questions based on the content of a knowledge base PDF. The system is enhanced with the agents that performs various intelligent actions.

Palakgarg155/LegalRAG-Eval

Palakgarg155/Making-MU-

Developed a novel metric to evaluate conversational AI solutions' effectiveness in filtering spam and irrelevant queries, addressing issues such as topical quadrails, prompt leaking, and jailbreaking.

Palakgarg155/MindAI-Evaluation

Palakgarg155/Palakgarg155

Config files for my GitHub profile.

Palakgarg155/rag-evaluator

A library for evaluating Retrieval-Augmented Generation (RAG) systems (The traditional ways).

Palakgarg155/The-Grand-Complete-Data-Science-Materials