RAG architecture: index and query any data using LLM and natural language, track sources, show citations, asynchronous memory patterns.

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

Semantic cache for LLMs. Fully integrated with LangChain and llama_index.

JVector: the most advanced embedded vector search engine

State-of-the-Art Text Embeddings

Code and pretrained models for the paper: "MatMamba: A Matryoshka State Space Model"

Matryoshka Multimodal Models

A vector search SQLite extension that runs anywhere!

A SQLite extension for efficient vector search, based on Faiss!

Android Database - first and fast, lightweight on-device vector database

MSVBASE is a system that efficiently supports complex queries of both approximate similarity search and relational operators. It integrates high-dimensional vector indices into PostgreSQL, a relati…

A library for efficient similarity search and clustering of dense vectors.

ai4db and db4ai work

MIMIC Code Repository: Code shared by the research community for the MIMIC family of databases

This project describes a bank offering services to private customers . The services provided by the bank include account managing, loan sanctioning , etc. Task description The bank wants to improve…

Play around with Yelp dataset in Python (in progress and very messy repo)

联邦学习

Scripts for optimization class

Parallel Multi-Block ADMM with o(1/k) Convergence

Implemented ADMM optimizer for solving Lasso regression problem

Scalable Machine Learning with Dask

Parallel computing with task scheduling

A Python-embedded modeling language for convex optimization problems.

This is the knowledge repository of the I-BiDaaS project

ADMM based large scale logistic regression

ADMM based Scalable Machine Learning on Spark

Admm l1/2 logistic regression using MPI and GSL