A project to show howto use SpringAI with OpenAI to chat with the documents in a library. Documents are stored in a normal/vector database. The AI is used to create embeddings from documents that are stored in the vector database. The vector database is used to query for the nearest document. That document is used by the AI to generate the answer.

PDF Q&A API is a modular FastAPI backend that lets you upload PDF documents and ask context-aware questions about their content. Powered by Groq LLM, SentenceTransformers, and ChromaDB, it delivers accurate, semantic answers based on your PDFs, with a clean architecture for easy maintenance and extension.

ETL, Analytics, Versioning for Unstructured Data

NekoRec is a full-stack web application for personalized anime recommendations. It features anime browsing, detailed views, genre exploration, and content-based recommendations using FastAPI (Python) for the backend with Gemini Embeddings and React (TypeScript) for the frontend.

Stateful AI agent memory layer for PostgreSQL with pgvector - TypeScript-first with intelligent context management

🧠 AI second brain with reasoning, analysis & synthesis. Knowledge graphs, topic modeling, spaced repetition, automated reports. Real-time voice assistant, semantic search, smart plugins. Qdrant vectors + PostgreSQL + transformers. From conversations to connected intelligence - memory that thinks like you do.

AI-based classification of BIM elements using sentence embeddings and bSDD

This project allows to upload, train and evaluate AI models based on your own data. You are also able to generate synthetic datasets from already existing ones.

The Postgres development platform. Supabase gives you a dedicated Postgres database to build your web, mobile, and AI applications.

ASR model

SQL as a Function for Rust

A robust, cross-platform builder and launcher for Python apps using UV. Built with Rust.

the AI-native open-source embedding database

A fully functional LLM chat backend with FastAPI and Async operations, with a built in MCTS conversation analyzer

Admin UI for Chroma embedding database built with Next.js

A microservice that convert text to embeddings to search on vector database

Simple, Composable, High-Performance, Safe and Web3 Friendly AI Agents and LazAI Gateway for Everyone

local-first semantic code search engine

Canvas Server runtime

Build production-ready backends in minutes