A complete, driver based RAG pipeline for Laravel with pgvector & sqlite-vec, streaming, agentic retrieval, hybrid search, evals, MCP server, Filament admin.

SoulCare is a mental health app using NLP to analyze social media sentiment, track symptoms, and offer AI-driven support with personalized reports, document uploads, and symptom-based prioritization.

U-PG-RAG, a campus Q&A backend system, is built on PostgreSQL (PG).U-PG-RAG是一个基于postgresql(PG)构建的校园问答后端系统

This project demonstrates how to implement a hybrid search engine for Retrieval-Augmented Generation (RAG) using Postgres with PgVector. It showcases the use of asynchronous streaming with Groq's function calling capabilities in a FastAPI application.

A starting point for building custom agentic LLM applications using Open Source tooling and models. Incorporates Ollama, Open WebUI, Langchain, Streamlit, Chroma, & PGVector using Docker and Docker Compose and optionally Codespaces.

Git Your Code implements a cutting-edge Retrieval-Augmented Generation (RAG) architecture designed for deep semantic analysis of GitHub repositories. The system leverages vector embeddings, natural language processing, and machine learning to provide intelligent code comprehension and query capabilities.

Production grade postgres docker containers

LangChain abstractions backed by YugabyteDB Distributed SQL Backend

The modern web development landscape is plagued by a peculiar paradox: despite the abundance of UI components and design systems, developers still spend countless hours reimplementing similar interfaces. S0 addresses this challenge by introducing a novel approach that combines advanced vector search capabilities.

joinai-customer-support: An AI-powered customer support platform built with Next.js, offering intelligent conversational AI, personalized responses, and task automation for seamless user interactions.

Production-ready NestJS template with Model Context Protocol (MCP) server, RAG pipeline, pgvector semantic search, Better Auth, and comprehensive developer tooling. Docker-ready with REST/GraphQL/WebSocket APIs.

End-to-end batch and streaming data pipeline on AWS to process user ratings and activity data. Leverages Amazon RDS, Glue, S3, Kinesis, and PostgreSQL with pgvector for real-time recommendation generation and model training.

An AI-powered chatbot providing accurate Islamic finance information to Muslims and organizations.

Spring Boot application that uses Spring AI implementing RAG (Retrieval-Augmented Generation) to help users understand and query documents. For this prototype I used the constitution of The Republic of Ireland, but any collection of documents can be used to achieve the state-of-the-art RAG in Java.

RAG supported Chat API using Ollama LLM

AI-powered job search platform with real-time preference filtering.

A book-inspired social platform where people are Books and posts are Chapters. It prioritizes intentional writing, slow discovery, and humane design over feeds and virality. Powered by Muse AI, a gentle creative companion that helps users write, reflect, and shape their work without taking over their voice.

AI-based SaaS Event Marketplace for user auth, profile & location, purchase & rewards, org dashboard, event listings near you, ticket bookings via affiliate links. Organizations can register, host virtual meetups with rich chat & AI features in subscription plans. AI powers recommendations, semantic search, analytics, chatbot, fraud detection, ....

Search by Image using similarity search on image vectors.