AI-powered document analysis platform built with Next.js, LangChain, PostgreSQL + pgvector. Upload, organize, and chat with documents. Includes predictive missing-document detection, role-based workflows, and page-level insight extraction.

A lodging recommendation service for properties in San Francisco, powered by OpenAI and the PostgreSQL pgvector extension.

NutritionAI is an AI-driven application that allows users to upload meal images for nutritional analysis. It provides personalized dietary recommendations based on user profiles and food item embeddings.

Metal Gear Solid codec calls Chrome extension , with realtime AI & local vector DB

Easily batch create vectors with OpenAI

The Image Search Engine is a modern AI-powered web application leveraging Retrieval-Augmented Generation (RAG) to combine large language models (LLMs) with advanced image retrieval techniques.

Prisma extension to support PGVector

A mindfulness journaling app, using NLP to help users track their emotions

VLib is a digital library platform targeting college library systems that utilises a vector database for discovering required resources and thereby making information accessible to all users irrespective of their knowledge level. It overcomes the incapability of present systems to handle descriptive queries thereby limiting information access.

Hia (Health Insights Agent) - AI Agent to analyze blood reports and provide detailed health insights.

PostgreSQL Primary-Replica Servers (with Pgvector Extension) on Docker

ErBlogX: An AI-powered sematic search pipeline to search and chat with engineering blogs/articles/transcripts. Built with Next.js, FastAPI, Supabase/pgvector, and sentence-transformers (all-mpnet-base-v2 ) embeddings.

Workers 反代

This repository will guide you to build up a data retrieval system by semantic search and filtering with metadata using timescale hosted PostgreSQL and pgvectors

Convenience Docker Postgres images with pre-installed pgvector

Vector search implementation using LLAMA, ExpressJS and postgres.

A lodging recommendation service for properties in San Francisco, powered by OpenAI and the PostgreSQL pgvector extension.

Architected and deployed a full-stack natural language communication platform enabling policy analysts to interact with large language models (LLMs) through scalable, cloud-hosted infrastructure. Engineered a multi-container microservices system using Docker for backend (FastAPI APIs, pgvector database, Redis caching) and frontend integration.

Embedded PostgreSQL with pgvector extension for Node.js applications