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

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

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.

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.

LangChain abstractions backed by YugabyteDB Distributed SQL Backend

Monocle is a multi-modal embedding service designed for easy integration into modern applications. It provides HTTP API endpoints for generating text and image embeddings using state-of-the-art models. Monocle is ideal for semantic search, recommendation, and AI-powered content understanding.

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

DEMO using griptape package to build an agent to interact with model garden on GCP using public API.

Agentic RAG–powered assistant built with LangGraph that answers user queries from a knowledge base and guides users to create, update, or cancel Google Meet calls, managing availability and sending meeting links via email.