🌌 A complete search engine and RAG pipeline in your browser, server or edge network with support for full-text, vector, and hybrid search in less than 2kb.

The universal tool suite for vector database management. Manage Pinecone, Chroma, Qdrant, Weaviate and more vector databases with ease.

A Python vector database you just need - no more, no less.

A modern desktop application for exploring, managing, and analyzing vector databases

A Python library to chunk/group your texts based on semantic similarity.

S3 vector database for LLM Agents and RAG.

Embed anything.

ToucanDB is a brand-new micro ML-first database engine 🦜

Examples of vector DB indexing and query with various vector databases.

High-performance database management system

Privacy-focused RAG chatbot for network documentation. Chat with your PDFs locally using Ollama, Chroma & LangChain. CPU-only, fully offline.

Machine Learning, LLM and other Jupyter Notebooks and resources

A powerful **two-stage multimodal retrieval pipeline** for ComfyUI, enabling semantic image search using natural language queries or image similarity. Built on the **Qwen3-VL foundation model** from Alibaba.

AI-Powered Lecture Navigation System. An intelligent learning platform that uses machine learning models to provide personalized lecture navigation and content discovery for students.

A chrome extension for chating with the webpage

AI Voice Assistant with RAG | LiveKit + LLaMA Index | Intelligent document retrieval for coaching conversations

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.

Complete pipeline for generating DBpedia text embeddings using OpenAI's embedding models and publishing them as Hugging Face datasets.

RAG chatbot for the National Electrical Code using Next.js, ChromaDB, and Claude AI

Experimenting with Pinecone as vector data continues to take center stage in AI-native systems. The purpose of this project is to explore the core capabilities, benchmark performance across different embedding models, and better understand what is possible with vector search in production environments.

Create a ChatGPT-like experience with your data.

A web app that uses Retrieval-Augmented Generation (RAG) to create an AI expert over a codebase. The app allows users to interact with a codebase via chat, retrieving relevant code snippets from a Pinecone vector database and generating responses using LLMs.

This repository contains source code which encompasses usage of the Langchain framework to extract information from distinct types of documents and subsequently perform Retrieval Augmented Generation(RAG) on these documents as well.

End-to-End Research Bot for Summarizing and Extracting Insights from Multiple URLs using advanced text processing, FAISS vector storage, and OpenAI services for accurate and concise responses.

🔍 Scalable microservices-based visual search engine using deep learning embeddings and vector databases. Search for similar images with REST API, powered by Docker, Redis, Qdrant, and PyTorch.

S3 Vectors RAG System with Shakespearean Content.

The Credit Decision LLM RAG Platform is an enterprise-grade solution that automates and enhances credit decision-making processes using cutting-edge AI technology. Built with modern architecture principles, it provides intelligent risk assessment, automated decision-making, and comprehensive audit trails for financial institutions.

임베딩(vector) 스토어를 위한 캐시 매니저

Enterprise-grade Retrieval Augmented Generation (RAG) system using FastAPI, Milvus, Confluence ingestion, and LLMs for internal knowledge search and Q&A.

Production-ready RAG document ingestion service with TypeScript, Express, and ChromaDB. Multi-format processing, flexible chunking, and vector embeddings.