A lightweight Streamlit web app built for developers who need a quick, visual way to manage and understand their Weaviate cluster. It's designed for development, staging, and testing environments (not for production-scale use).
Desktop admin GUI for Weaviate vector database clusters, manage collections, shards, RBAC, search, backups, and Kubernetes infra from one app.
WeaviateDB Scripts & Snippets For Python Client
weaviate performace lab
This app helps you estimate storage requirements for Weaviate vector database based on your data characteristics. You can either calculate estimates from basic parameters or extrapolate from existing measurements.
A state-of-the-art Retrieval-Augmented Generation (RAG) system that transforms document processing and knowledge retrieval through hierarchical organization, advanced embedding techniques, and intelligent conversation management. This project combines cutting-edge AI technologies to create a sophisticated document intelligence platform.
Weaviate Memory & CPU Estimator: Resource planning tool based on official Weaviate documentation.
Enterprise-ready RAG template: semantic chunking, NLI hallucination detection, latency budgeting, Prometheus observability. Battle-tested at scale.
Learning journey with Vector Databases for GenAI RAG applications, exploring Chroma, Pinecone, and Weaviate for efficient retrieval, indexing, and querying in AI-driven systems.
A browser app presenting data from the Georgia Project.
Personal knowledge management
Find orphan vectors with no metadata in Pinecone or Weaviate. Keep your vector DB clean.
MediProc-AI is a high-performance, multi-agent medical intelligence system designed to unify siloed clinical data. It transforms raw medical documents (images/PDFs) into actionable clinical insights using a "Triple-Database Hybrid RAG" architecture.
Leo’s Search is an open-source AI-powered multimodal search engine built with Python, Flask, and Weaviate-client. It enables intelligent, context-aware search across text, images, and more. Fast, flexible, and fully customizable, it brings modern semantic search to developers and organizations.
A clean, context-managed Python wrapper for simplifying multi-tenant data isolation in Weaviate.
a Retrieval-Augmented Generation (RAG) architecture using OpenAI, FastAPI, and Streamlit, with vector storage support via Weaviate, Azure Cosmos DB, or Elasticsearch.
weaviate local gui
How to use AI in SWE ?
Problem Statement:RAG Powered Website CHatbot
To associate your repository with the weaviatedb topic, visit your repo's landing page and select "manage topics."