Stars
Azure MLOps (v2) solution accelerators. Enterprise ready templates to deploy your machine learning models on the Azure Platform.
DSPy: The framework for programming—not prompting—foundation models
Open-source vector similarity search for Postgres
Terraform module to create AWS ECS resources 🇺🇦
Terraform module to create Amazon Elastic Kubernetes (EKS) resources 🇺🇦
Retrieval Augmented Generation (RAG) chatbot powered by Weaviate
Docker image for Radicale calendar and contact server 📆 + security 🔐 + addons 🚀
AI-Powered Photos App for the Decentralized Web 🌈💎✨
Deploy production-grade Metaflow cloud infrastructure on AWS
🏡 Open source home automation that puts local control and privacy first.
Joining the modern data stack with the modern ML stack
A repository for my PyCon talk: "Building a personal assistant with Haystack and GPT: How to feed facts to large language models and reduce hallucinations"
🔍 LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your d…
Simply, faster, sentence-transformers
Poetry plugin that updates dependencies and bumps their versions in pyproject.toml file
Hamilton helps data scientists and engineers define testable, modular, self-documenting dataflows, that encode lineage/tracing and metadata. Runs and scales everywhere python does.
Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.
Python code for "Probabilistic Machine learning" book by Kevin Murphy
This repository contains an easy and intuitive approach to few-shot classification using sentence-transformers or spaCy models, or zero-shot classification with Huggingface.
Zulip server and web application. Open-source team chat that helps teams stay productive and focused.
The Data Cards Playbook helps dataset producers and publishers adopt a people-centered approach to transparency in dataset documentation.
FastAPI framework, high performance, easy to learn, fast to code, ready for production
A list of free data matching and record linkage software.
Kedro is a toolbox for production-ready data science. It uses software engineering best practices to help you create data engineering and data science pipelines that are reproducible, maintainable,…
Open source book dedicated to helping you to make the best possible sourdough bread at home.
Learn how to master the art of baking the programmer way.