vector-embedding

Retrieval-Augmented Generation chatbot built with Next.js 15, Groq AI, HuggingFace embeddings, Clerk auth, and Neon PostgreSQL. Chat with your PDFs intelligently.

High-dimensional vector embedding semantic SimHash deduplication sentinel with LRU cache simulation

High-dimensional vector embedding semantic SimHash deduplication sentinel with LRU cache simulation

Lean vector embedding provider package for CitOmni with unified contracts across providers and profile-based adapters.

The Personal Portfolio RAG Agent is a live, production-ready demonstration of end-to-end AI system engineering. More than a Q&A bot, it acts as a knowledge-grounded expert on my professional profile.

AI-powered styling decision assistant, built for the YouCam API Skin AI & Apparel VTO Hackathon.

A Java implementation of HNSW with multi-vector search support

An AI-powered PDF assistant built with Next.js, MongoDB, and Gemini API that enables users to upload documents and have context-aware, semantic conversations about their contents.

寻星SeekStar-浏览器和 Chat AI 解决的是“如何回答我已经能问出的问题”。SeekStar 要解决的是“如何让我发现自己还不知道该问的问题” 寻星 是一种面向未来的浏览器 / 搜索引擎形态构想。

VectorTokenizer is a semantic, hybrid-routing AI agent that replaces brittle regex rules with real-time vector embeddings. It processes routine tasks on a zero-cost local Phi-3 model while securely escalating complex workloads to frontier cloud APIs.

싸맨들 단어 추측 게임의 프론트엔드 웹 클라이언트 데모용 버전

Local-first, agent-oriented memory substrate for engineering decisions and evolving project context

My First RAG pipeline using local ollama models

Local Retrieval-Augmented Generation (RAG) pipeline for document QA. Built with LangChain, Llama2 (via Ollama), and an in-memory DocArray vector store, featuring an interactive Streamlit interface for semantic PDF querying.

2025 새만금 공공데이터 공모전 수상작 '새길' 데이터 수집 & 소비 WAS

Experimenting with vector embeddings to build and evaluate a semantic search feature.

A Semantic Search Engine that solves the "Vocabulary Mismatch" problem. Uses Transformers (BERT) to match User Intent rather than Keywords. Features an AI Happiness Score for quality-first ranking.

A universal AI and MCP-powered plugin for Logitech's Actions Ring that adapts to the user's workflow.