Vector Storage is a vector database that enables semantic similarity searches on text documents in the browser's local storage. It uses OpenAI embeddings to convert documents into vectors and allows searching for similar documents based on cosine similarity.

VQLite - Simple and Lightweight Vector Search Engine based on Google ScaNN

⚡ PDX: A Library for Fast Vector Search and Indexing on CPUs (x86, ARM) — for Python and C++. Index millions of vectors in seconds. Search them in milliseconds.

Cloud-native vector similarity search and storage with efficient, serverless scale-out

Embed anything.

A vector similarity search engine for humans🥳

Locality Sensitive Hashing (LSH) based recommendation system. Integrates with Redis and your own database.

An Effective and Scalable Framework for Multimodal Search with Target Modality

Sample application written in Java (JDK 21, Spring Boot, Redis OM Spring) that implements a hybrid search strategy (Full-Text Search and Vector Similarity Search) to allows for movies search.

[WIP] A state-of-the-art IVF index for lightweight but fast (filtered) vector similarity search in DuckDB.

No description provided.

It's the Repo containing a model for summarization and classification of the Indian legal cases.

🗃️✨ Mebox is an open-source RAG multi model tool, designed to efficiently process, store, and retrieve file-based information using Supabase and open source embeddings.

Scalable API extension for advanced vector database functions. Enhance machine learning, search, and analytics applications with an API that supports efficient embedding storage and similarity searches.

Research project to enable natural language interaction with Pennsieve medical database.

Penn Course Information System is designed to provide students with a comprehensive tool to navigate and explore the courses offered at the University of Pennsylvania. It offers several features to simplify the course selection process and help students make informed decisions.

A smart, conversational FAQ system using LangGraph and sentence-transformer embeddings that semantically retrieves answers from a CSV knowledge base and routes user queries based on confidence. Built with LangChain, FAISS, and HuggingFace for efficient semantic search.

Utilizing Redis Vector Similarity Search, this demo project streamlines expense categorization from bank transactions. The approach harnesses pre-trained models, sidestepping the need for finetuning. This ensures efficient, accurate expense categorization without complex model adjustments

Invoice de-duplication via Azure Form Recognition, OpenAI, Apache Airflow and Redis Enterprise VSS

API REST em NestJS + TypeScript que combina chat interativo, RAG e geração de imagens (DALL·E) para recomendar a tinta ideal, orquestrando agentes de intenção, ambiente, resistência, uso e visualização, com armazenamento de embeddings em PostgreSQL. Interface frontend e swagger prontos para testes.

EchoMind is an AI-powered voice document assistant that leverages hybrid RAG pipelines, vector embeddings, and streaming large language models to transform uploaded documents into an interactive knowledge base accessible through natural voice queries.

Approximate vector similarity search and clustering using Locality Sensitive Hashing (LSH), Hypercube, and k-medians

Comparison of IVFFlat and HNSW Algorithms

Production-Ready RAG Chatbot for Abwisk Inc - A comprehensive Retrieval-Augmented Generation (RAG) system that processes business documents (PDFs, DOCX, TXT) and provides intelligent, source-backed responses through a professional web interface. Built with OpenAI GPT-4o-mini, ChromaDB vector storage, and Gradio UI.

A website to match future physics PhD applicants to professors at universities across the U.S. who conduct physics in the user's niche.

Implementation of various vector rank fusion algorithms