Private & local AI personal knowledge management app for high entropy people.

The collaborative spreadsheet for AI. Chain cells into powerful pipelines, experiment with prompts and models, and evaluate LLM responses in real-time. Work together seamlessly to build and iterate on AI applications.

Comprehensive Vector Data Tooling. The universal interface for all vector database, datasets and RAG platforms. Easily export, import, backup, re-embed (using any model) or access your vector data from any vector databases or repository.

A LLM RAG system runs on your laptop. 大模型检索增强生成系统，可以轻松部署在笔记本电脑上，实现本地知识库智能问答。

RAG on codebases using treesitter and LanceDB

A full-stack serverless RAG workflow. This is thought for running PoCs, prototypes and bootstrap your MVP.

Vector search over tweets from the tweet archive using OpenAI embeddings and LanceDB

Benchmark study on LanceDB, an embedded vector DB, for full-text search and vector search

Graph RAG workshop using Kùzu and LanceDB for hybrid RAG

spaCy pipeline component for ANN Entity Linking using LanceDB

A simulation experiment based on X interactions

🤖 Next.js AI Chatbot - Chat with any website

Transcribe it using OpenAI's Whisper, generate embeddings with Sentence Transformers, and store/query data in LanceDB.

The missing index for the Heritage Foundation's Project 2025

Generative AI projects using openAI, llama, langchain, vectordb

An implementation of Retrieval-Augmented Generation (RAG) indexing using Rust and LanceDB. It leverages the power of Rust for efficient and safe performance, combined with LanceDB for advanced indexing capabilities.

A serverless embedded streaming OLAP data pipeline

Projects Implemented for the Udacity Generative AI Engineer Nanodegree Program

An embedded streaming OLAP data pipeline with LanceDB

API service to search vectorized Cursor IDE chat history using LanceDB and Ollama