Jupyter Notebook agents

This Repo contains Mary ChatBot a trained Model containing a story, query and answers. Trains the story and query to output the correct answer. It uses the Softmax activation layer for multiclass classification

The idea behind this project is to develop a new generation of mental healthcare tools that are as dynamic as the people they serve. This has been achieved by deploying a bot service that helps ease the initial screening process for people who are seeking mental health related aid. BroBot is designed to be there for you, to have a tiny conversation, to vent out your feelings and to direct you to the right professionals if required.

A simple transformer chatbot that trained with cornell movie-dialogs corpus. And a Streamlit app to make it easy to use.

Python AI Chat Bot for answering questions related to my resume.

Jupyter notebooks for testing Prisma AIRS AI Runtime with your LLM

Conversational Model that recognizes food images and return nutritional facts

CureWise-AI is a modern, production-grade healthcare data platform that leverages Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and advanced AI/ML techniques to deliver intelligent analytics, medical report parsing, and conversational AI for hospitals, doctors, and patients.

OpenAI GPT-3 NLP task completion & Stable Diffusion Text2Image generator, before ChatGPT and DALL-E

How to build a chatbot to parse conditional statements

MedBot is a medical smart chatbot which uses NLG to answer user medical queries. It is made on top of a distilled version of GPT-2 by using the HuggingFace Repository. The bot is trained on medical queries gathered from websites such as WebMD and questionDoctor.

Chatbot built using Flask and the OpenAI GPT-3.5 turbo model. The chatbot allows users to interact with a language model powered by GPT-3.5 turbo and get responses based on their input.

Chatbot app for interactively conversing with PDFs

An AI-driven healthcare assistant that predicts diseases based on user-provided symptoms. This project leverages machine learning for disease prediction, provides descriptions and precautionary measures, and includes a user-friendly GUI with text-to-speech integration.

This is AI ChatBot. I make it By AI(NLP). I know sometime it's show wrong answer because i use less data to train my model because i haven't big dataset. you can read my code and you can learn many thing. This chatbot is not bad at all. You can have fun with it in your spare time if you want.

Question Answering Chatbot with DistilRoBERTa Sentence Embeddings, Dialogflow and Ngrok

Bot/Agent which will act as a guide for self assessment of probable risks from corona virus and increase awareness about the pandemic.

A simple 3-layer NN based model with predefined responses

🚀 Build and understand a Large Language Model from scratch using PyTorch through hands-on notebooks focused on core Transformer concepts.

A cybernetic physicist sent back in time to fuse techniques from quantum field theory and machine learning. April Fools' 2023.

Tagging using LLM

This demo repository demonstrates how to analyze customer reviews with Azure OpenAI Service (AOAI). I leveraged "ASOS Customer Review" from Kaggle to obtain valuable insight from the customer review content.

Demonstration of using GPT4 to answer D&D questions

A benchmark study analyzing cost and token efficiency across 14 LLMs from 5 providers — comparing price-per-token, latency, and accuracy to surface the most cost-effective models for real-world use.

ChatGPT Prompt Engineering for Developers

Building a GPT-3 powered Amazon Support Bot for precise customer query responses via fine-tuned model on Amazon QA data

Slides and resources for HT Media Group NLP Workshop, 2025

RAG framework that combines structured knowledge representation using hypergraphs with efficient response generation via semantic caching.

A RAG Application powered by Llama 3.2b and HuggingFace Embeddings

Multimodal RAG-Based Product Search Chatbot Using Amazon Bedrock and OpenSearch

Replication for SOTA "Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generation"

A lightweight, local Retrieval-Augmented Generation (RAG) system for domain-specific Q&A over financial documents. Uses pdfplumber for PDF parsing, sentence-transformers for dense retrieval, and optionally connects to local LLMs (e.g., Ollama + Mistral). Runs on FastAPI with a custom frontend.

Code for the presentation.

A meta-app, built with Streamlit—supercharged with Snowflake AI—to help Streamlit evolve, one issue at a time.

A comprehensive collection of RAG (Retrieval Augmented Generation) implementations 📚✨, from foundational concepts to advanced agentic 🤖 and knowledge graph 🌐 RAGs

Baseline replication for paper “EMERGE: Enhancing Multimodal Electronic Health Records Predictive Modeling with Retrieval-Augmented Generation.”

Repo for DermAssist: Your AI Assitant for Skin Problems. Powered by a vision model and a reliable RAG system.

A self-contained Google Colab Notebook that implements RAG using Postgres pgvector, pgai, and LLMs. Supports local-Ollama/OpenAI/Anthropic

A Jupyter Notebook–powered toolkit that uses Retrieval-Augmented Generation (RAG) to help you craft a knockout resume. Feed it your raw career data (LinkedIn exports, old CVs, brag-worthy project notes), and let an AI do the heavy lifting—so you can spend your time practicing interview answers (or napping).

demo in blog how ai help understand omniclass

Retrieval Augmented Generation (RAG)

NLP + RAG technique for requirements engineering.

Using LLMs to generate custom UI elements. Currently using Mistral-7b.

Material y ejercicios del curso IMPACT#IA sobre LlamaIndex y Pydantic: desarrollo de agentes, uso de APIs, automatización y parseo de documentos con modelos estructurados.

IMDb IR System Project - MIR Course - Spring 2024

RAG system for an e-commerce support chatbot.

Practical sessions for the “Data Science for Economics” at the CEMFI Summer School 2025.

Retreival-Augmented Generation with Mixtral 8x7b powered by MILVUS vector database with semantically chunked text embeddings retreived and reranked using BGE-M3.

an approach to optimizing large language model (LLM) responses by extracting, reranking, and refining their internal chain-of-thought (CoT). By focusing on the most coherent and relevant parts of the CoT, we can minimize contradictory reasoning and potentially reduce token usage—ultimately leading to more reliable and efficient outputs.

RAG system using Hugging Face models, multiple vector stores (Chroma, Pinecone, FAISS), and CRAG, with sentence transformers and benchmarking tools for optimized retrieval and content generation.

Multimodal RAG chatbot with voice input for fashion product search 🤖🎙️👟⚡

Repository for final project submission for CS685 Advanced NLP.

Tesi della mia Laurea Triennale in Informatica L-31

Bifocal is an AI-powered platform that analyzes message history to detect emotional abuse and escalating risks in conversations. It flags harmful behaviors from both the victim and offender perspectives using DSM-5-informed NLP and machine learning.

Retrieval Augmented Generation (RAG) using FAISS and Gemma 2b instruction tuned model for answering your questions regarding movies.

Match synthetic patients to clinicaltrials.gov restAPI data with ChatGPT4. Course project for Johns Hopkins University EN.705.651.8VL : Large Language Models: Theory and Practice

In-depth demonstration of C# Semantic Kernel SQLiteVec Hybrid Search Tutorial - Audio Guide

Problem Statement-1: Multilingual NCERT Doubt-Solver using OPEA-based RAG Pipeline. A multilingual doubt-solving system for Grades 5–10 built only on NCERT textbooks, using OCR ingestion, grade-aware retrieval, conversational Q&A with citations, feedback capture, and reliable out-of-scope fallback through a web-friendly chat interface.

This repository contains a chatbot application designed to assist students and visitors of the Faculty of Sciences and Techniques in Tanger (FSTT) website. The chatbot use two approach of NLP: Retrieval-Augmented Generation (RAG) and Fine-Tuning.

Multimodal RAG

An interactive, state-of-the-art Retrieval-Augmented Generation Medical Assistant that leverages deep learning and FAISS-based retrieval to provide accurate, context-aware answers to medical queries in real time.

Multi-disease segmentation chest X-rays by YOLO and DenseNet121, CoAtNet models

Galileo is an AI assistant chatbot for University of Padova (Unipd) to answer student's questions, powered by llama 3 8B and RAG method (NLP's project 2024/25)

This is the Python backend for InsightAI, Architected a microservices-based EdTech platform combining Study Companion, Project Planner, and ShopGenie modules.

Question Answering Generative AI application with Large Language Models (LLMs) and Amazon OpenSearch Service using Haystack

Open-source SOC console. Free-text security incident in, MITRE ATT&CK triage card out. TF-IDF + sentence-transformer classifier, multi-provider LLM dispatch, IOC enrichment, and case management.

A hands-on guide to understanding Claude Code's architecture and implementation | 深入浅出学习 Claude Code 源码

Understanding and implementing RAGs using langchain on LLMs from scratch using APIs.

Agentic personal medical assistant that reasons over medical data using multi-agent orchestration, with leveraging mutiple ML/DL pre-trained models, with addition to relational and vector databases.

This repository demonstrates Cache-Augmented Generation (CAG) using the Mistral-7B model.

Coursera - deeplearning.ai crewai course

This is AI Research Assistant repository using Gen AI and RAG model. This AI Research Assistant app is powered by Google Gemini. It helps in question answering about the provided research paper by uploading them through Streamlit, we save it in the Data folder and clean the document, index it by using Llamma-Index using Gemini Embedding Model.

All my AI Agent projects in one place. Smart, interactive, and tool-powered! 🚀

Health Query Chatbot using LLM (Mistral-7B-Instruct)

End-to-end AI hackathon platform enabling users to train ML models, deploy AI agents, and get evaluated via an automated leaderboard and intelligent AI judge system.

🎬 Semantic movie recommendation system using transformer embeddings, ChromaDB, LangChain, and Gradio.

This course is designed to take you from the basics to advanced concepts, providing hands-on experience in building, deploying, and optimizing AI models using Langchain and Huggingface. Perfect for AI enthusiasts, developers, and professionals

Agentic AI Learning

Artificial Intelligence-Yearning Fulfilment Unit

The workshop content I presented titled "Development of an Offline Persian AI Assistant using RAG" at the WTLAB 2025 workshops.

LLM Workshop : OpenAI and Langchain Jupyter Notebook

RAG with LM studio, local LLMs, Scientific PDF text extraction,

projet utilisant Ollama, expérimentation de RAG, agents, chat à but de faire un assistant perso

End-to-End Python implementation of Ang et al's (2026) Agentic 'Self-Driving Portfolio'. Implements: Black-Litterman equilibrium priors, Grinold-Kroner building blocks, Campbell-Shiller CAPE analysis, Ledoit-Wolf covariance shrinkage, Risk Parity, Hierarchical Risk Parity, and Robust Mean-Variance optimization across 18 asset classes.

A Repository for Intelligent Agents Integrated with Retrieval-Augmented Generation for Querying Automotive Manuals.

Multi-agent RL solution for scheduling work within a graph-based digital twin of a residential complex

An efficient open Mixture-of-Experts (MoE) agent that runs on a single 24 GB GPU. Agent-first design: coding, terminal, computer-use, tool-use. v0.1.0 documentation preview — weights/code follow staged open release.

A chatbot to help coursera student with their difficulty.

This is a Frequently Asked Questions(FAQ) answering chatbot, customly built from scratch to answer any question related to IEEE-VIT.

Resigned Yann-LeCun

The future of AI is speaking Chilean, cachai?

Compact LLM domain adaptation benchmark: LoRA vs RAG with custom IVF retrieval in PostgreSQL/pgvector.

Hybrid AI healthcare assistant integrating OpenBioLLM (modern biomedicine) and AyurParam (Ayurveda). Mental wellness support (via Mistral) medical report simplification, and Ayurvedic guidance ; in one system.

A notebook-driven exploration of next-gen agentic RAG architectures and intelligent retrieval pipelines.

Multi-agent RL environment for urban bus systems

A hands-on implementation of Deep Agents and Sub-Agents using LangGraph, featuring autonomous planning, tool calling, web research, task delegation, and multi-agent orchestration workflows.

deal.II Assistant (Large Language Model & RAG Application)

Sample Steam reviews with the GPT-2 language model.

This is a Speech to text project which uses openAI's Whisper model.

Sample Steam reviews with different approaches.

Fact checking OpenAI's GPT-3 with structured queries from the Wikidata Taxonomy