An open-source RAG-based tool for chatting with your documents.

LOTUS: A semantic query engine for fast and easy LLM-powered data processing

open-source framework for creating and managing simulations populated with AI-powered agents. It provides an intuitive platform for designing complex, interactive environments where agents can act,…

A comprehensive list of books on Software Architecture.

Open Source Customer Engagement Platform (Customer.io Alternative)

This is a repo with links to everything you'd ever want to learn about data engineering

pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. Demo: https://tidb.ai

🪄 Create rich visualizations with AI

A massively parallel, high-level programming language

Python toolkit for quantitative finance

Automating Android apps with ChatGPT-like LLM.

"실무로 통하는 인과추론 with 파이썬" (한빛미디어, 2024) 소스코드 저장소입니다.

Drag & drop UI to build your customized LLM flow

A JAX research toolkit for building, editing, and visualizing neural networks.

Python programs, usually short, of considerable difficulty, to perfect particular skills.

PRQL is a modern language for transforming data — a simple, powerful, pipelined SQL replacement

Monte Carlo simulation of the NBA season, leveraging dbt, duckdb and evidence.dev

Chronon is a data platform for serving for AI/ML applications.

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

A collection of awesome resources for Evidence

DSPy: The framework for programming—not prompting—language models

Redpanda is a streaming data platform for developers. Kafka API compatible. 10x faster. No ZooKeeper. No JVM!

Business intelligence as code: build fast, interactive data visualizations in SQL and markdown

Supplementary material for my book, Probably Overthinking It.

dbt package to monitor BigQuery assets (tables & queries)

The data-validation toolkit for enhanced dbt (data build tool) PR review

DeltaPy - Tabular Data Augmentation (by @firmai)

Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting