bastienboutonnet

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Verba

Retrieval Augmented Generation (RAG) chatbot powered by Weaviate

JsonGenius

Get structured JSON data from any page.

modal-dbt

fern

Input OpenAPI. Output SDKs and Docs.

kaguya

A ChatGPT plugin that allows you to load and edit your local files in a controlled way, as well as run any Python, JavaScript, and bash script.

mlops-python-package

Kickstart your MLOps initiative with a flexible, robust, and productive Python package.

spacy-streamlit

👑 spaCy building blocks and visualizers for Streamlit apps

sqlmesh

Efficient data transformation and modeling framework that is backwards compatible with dbt.

sqlglot

Python SQL Parser and Transpiler

knowledge_gpt

Accurate answers and instant citations for your documents.

alpa

Training and serving large-scale neural networks with auto parallelization.

private-gpt

Interact with your documents using the power of GPT, 100% privately, no data leaks

the-algorithm

Source code for Twitter's Recommendation Algorithm

koboldcpp

A simple one-file way to run various GGML and GGUF models with KoboldAI's UI

typst

A new markup-based typesetting system that is powerful and easy to learn.

stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.

yobulkdev

🔥 🔥 🔥Open Source & AI driven Data Onboarding Platform:Free flatfile.com alternative

duke-data-science

All of my work and lecture notes from my ongoing time spent studying Data Science and Political Science at Duke that I can share wthout violating academic terms.

cloudquery

The open source high performance ELT framework powered by Apache Arrow

pygwalker

PyGWalker: Turn your pandas dataframe into an interactive UI for visual analysis

LazyVim

Neovim config for the lazy

dbt-codegen

Macros that generate dbt code

manage-fastapi

:rocket: CLI tool for FastAPI. Generating new FastAPI projects & boilerplates made easy.

data-diff

Compare tables within or across databases

dss-plugin-model-drift

Model drift detection

pyemd

Fast EMD for Python: a wrapper for Pele and Werman's C++ implementation of the Earth Mover's Distance metric

elementary

The dbt-native data observability solution for data & analytics engineers. Monitor your data pipelines in minutes. Available as self-hosted or cloud service with premium features.

minos-python

🐍 Minos is a framework which helps you create reactive microservices in Python

midarr-server

🔥Midarr, the minimal lightweight media server.