Llama2-Medical-Chatbot is a medical chatbot that uses the Llama-2-7B-Chat-GGML model and the pdf The Gale Encyclopedia of Medicine, Volume 1, 2nd Edition. It is still under development, but it has the potential to be a valuable tool for patients, healthcare professionals, and researchers.

The Llama-2-GGML-CSV-Chatbot is a conversational tool leveraging the powerful Llama-2 7B language model. It facilitates multi-turn interactions based on uploaded CSV data, allowing users to engage in seamless conversations.

A Semantic A* Pathfinding agent that navigates Wikipedia using high-dimensional vector space. Built with Python, BeautifulSoup4, and Sentence-Transformers to bridge unrelated concepts through semantic context rather than just keywords.

This project showcases how to use AWS Lambda Managed Instances with AI/ML capabilities for real-time customer analytics

NLP for yaskawa robot

Scrapping products from well known e-com. sites like Amazon, Flipkart and Myntra. This tool allows to scrape and compare the products with information like price, delivery, image, company, revirews etc.

Agentic HR Operations Assistant is an NLP-powered system that answers complex HR policy queries using RAG and executes HR actions from natural language.

👽SFSeeker - an AI assistant with a semantic engine/question writing tutor in Sci-Fi Stack Exchange service

This project uses Python, Hugging Face (sentence-transformers), Milvus + Docker (container running Vector DB) to create a vector database, populate it with details of many people (names, ages, salaries, addresses and their introductions) and enable searching and querying on the database contents using Cosine-Similarity distances on IVF Flat index.

Streamlit chatbot app that can answer questions based on a pdf. see the readme for more information

This project uses Python, Hugging Face (sentence-transformers), Milvus + Docker (container running Vector DB) to create a vector database, populate it with details of many people (names, ages, salaries, addresses and their introductions) and enable searching and querying on the database contents using Cosine-Similarity distances on IVF Flat index.

Ein lokales Frage-Antwort-Retrieval mit Sentence-BERT

This is a RAG-powered chatbot for answering questions about West End and Broadway theatre. It combines a curated PDF knowledge base with RAG pipeline to provide accurate ,source backed answers about shows , productions , venues and people behind them.

MEDAI: Production-oriented clinical cohort retrieval and summarization system built from scratch using structured medical data, hybrid retrieval, optional LLM reasoning, Dockerized and Cloud deployment.

A full-stack text-summarization system built using FastAPI (backend), HuggingFace Transformers, and a Gradio UI for accessible interaction.

building a CPU-Only "PDF Q&A System" using hugging face, chromaDB vector search, and Python

Sorted (SortedPC) is a privacy-focused, local-first file organization tool. It uses local AI (all-MiniLM-L6-v2) and FAISS vector search to automatically sort documents based on their semantic meaning rather than rigid keywords, learning your personal sorting habits over time.