Data validation using Python type hints

Well tested & Multi-language evaluation framework for text summarization.

The Self-hosted AI Starter Kit is an open-source template that quickly sets up a local AI environment. Curated by n8n, it provides essential tools for creating secure, self-hosted AI workflows.

A programming framework for agentic AI 🤖

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…

Python library to parse ANT/Garmin .FIT files

Transformer Explained Visually: Learn How LLM Transformer Models Work with Interactive Visualization

gpx-py is a python GPX parser. GPX (GPS eXchange Format) is an XML based file format for GPS tracks.

Module for automatic summarization of text documents and HTML pages.

Processamento de acórdãos do TJSP.

Lime: Explaining the predictions of any machine learning classifier

🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models

Superfast AI decision making and intelligent processing of multi-modal data.

BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

draw.io is a JavaScript, client-side editor for general diagramming.

Official repository of Trino, the distributed SQL query engine for big data, formerly known as PrestoSQL (https://trino.io)

💻 Padrões de Projeto em Python

List of resources and tools developed with focus on Portuguese.

Python packaging and dependency management made easy

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

Chat with your database (SQL, CSV, pandas, polars, mongodb, noSQL, etc). PandasAI makes data analysis conversational using LLMs (GPT 3.5 / 4, Anthropic, VertexAI) and RAG.

Official style files for papers submitted to venues of the Association for Computational Linguistics

Code and documentation for the MariTalk API

BARTScore: Evaluating Generated Text as Text Generation

BLEURT is a metric for Natural Language Generation based on transfer learning.

Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

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