Enable Vector Art - Moozonian Search

GitHub Repo https://github.com/arsath-eng/RAG1-NVIDIA-GENAI

arsath-eng/RAG1-NVIDIA-GENAI

A powerful Retrieval Augmented Generation (RAG) application built with NVIDIA AI endpoints and Streamlit. This solution enables intelligent document analysis and question-answering using state-of-the-art language models, featuring multi-PDF processing, FAISS vector store integration, and advanced prompt engineering.

GitHub Repo https://github.com/KrushithaJ/RAG_Pinecone

KrushithaJ/RAG_Pinecone

This RAG system enables you to upload documents, extract their content, convert text into vector embeddings, store them in Pinecone's vector database, and then ask questions about the content. The system retrieves relevant information and generates accurate answers using state-of-the-art NLP models.

GitHub Repo https://github.com/Rishabhporwal/Document-Hub

Rishabhporwal/Document-Hub

Document‑Hub is an AI-powered document intelligence platform that enables efficient information retrieval and processing across multiple file types using state-of-the-art LLMs, embeddings, and vector search techniques.

GitHub Repo https://github.com/lalithsagar10/Article-Semantic-Search-Tool

lalithsagar10/Article-Semantic-Search-Tool

News Article Retrieval and Query System is a Streamlit app that leverages LangChain, OpenAI embeddings, and FAISS vector database to efficiently process and search news articles from URLs. It enables users to ask questions and get precise answers backed by the source content.

GitHub Repo https://github.com/sushantkai/GEN-AI_Vector-Databases.ipynb

sushantkai/GEN-AI_Vector-Databases.ipynb

This project demonstrates how Vector Databases enable semantic search by understanding meaning instead of keywords. Using FAISS and state-of-the-art sentence embeddings, we retrieve the most relevant text even when exact words do not match.

GitHub Repo https://github.com/dineshdinz12/DocuAi

dineshdinz12/DocuAi

A comprehensive Retrieval-Augmented Generation (RAG) system that enables intelligent question-answering over multiple PDF documents. This production-grade implementation combines state-of-the-art natural language processing with persistent vector storage to deliver accurate, contextual responses with full source attribution.

GitHub Repo https://github.com/edsonlourenco/Vector-Brain

edsonlourenco/Vector-Brain

This project showcases how to build an intelligent chatbot using LLMs and PDF document vectorization. The goal is to enable contextual Q&A over a technical e-book using state-of-the-art AI.

GitHub Repo https://github.com/aquacommander/VectorBrain

aquacommander/VectorBrain

⭐This project showcases how to build an intelligent chatbot using LLMs and PDF document vectorization. The goal is to enable contextual Q&A over a technical e-book using state-of-the-art AI⭐

GitHub Repo https://github.com/lokiiicoded/PatentScope-LEANN-Privacy-First-Prior-Art-Search

lokiiicoded/PatentScope-LEANN-Privacy-First-Prior-Art-Search

PatentScope-LEANN enables secure, local patent search on standard hardware by slashing storage needs by 97%. Using the LEANN architecture, it replaces heavy vector storage with efficient graph reconstruction. Inventors can now perform deep, semantic prior art discovery offline - ensuring total privacy for unreleased IP without cloud reliance.

GitHub Repo https://github.com/Ighina/VQ-VAE_Topic

Ighina/VQ-VAE_Topic

An implementation of the paper [Vector-Quantization-Based Topic Modeling](https://dl.acm.org/doi/10.1145/3450946), providing a series of VQ-VAE models for topic modelling. The model reaches state-of-the-art performance on Ng20 and enables the extraction of dense topic vectors for downstream tasks.