Collection of links, tutorials and best practices of how to collect the data and build end-to-end RLHF system to finetune Generative AI models

A modular and comprehensive solution to deploy a Multi-LLM and Multi-RAG powered chatbot (Amazon Bedrock, Anthropic, HuggingFace, OpenAI, Meta, AI21, Cohere, Mistral) using AWS CDK on AWS

Tutorial on how to properly send intermediate LlamaIndex events to vercel ai sdk via server-sent events during RAG.

Resource list for generating JSON using LLMs via function calling, tools, CFG. Libraries, Models, Notebooks, etc.

Open Source alternative to Algolia + Pinecone and an Easier-to-Use alternative to ElasticSearch ⚡ 🔍 ✨ Fast, typo tolerant, in-memory fuzzy Search Engine for building delightful search experiences

Interact with Amazon Lex using Python in an easy way

the AI-native open-source embedding database

Drag & drop UI to build your customized LLM flow

A library for building fast, reliable and evolvable network services.

🏬 modelstore is a Python library that allows you to version, export, and save a machine learning model to your filesystem or a cloud storage provider.

Official Dockerfile for Delta Lake

MLX: An array framework for Apple silicon

Inference code for CodeLlama models

Robust recipes to align language models with human and AI preferences

Fast and memory-efficient exact attention

Examples in the MLX framework

Tools for merging pretrained large language models.

A tiny JavaScript debugging utility modelled after Node.js core's debugging technique. Works in Node.js and web browsers

Infinite Red's battle-tested React Native project boilerplate, along with a CLI, component/model generators, and more!

Next-generation ORM for Node.js & TypeScript | PostgreSQL, MySQL, MariaDB, SQL Server, SQLite, MongoDB and CockroachDB

Examples and templates from the 1Password Solutions team

Metasploit Framework

Yarn on Docker Boilerplate

Node Version Manager - POSIX-compliant bash script to manage multiple active node.js versions

A framework for building native applications using React

The library for web and native user interfaces.

FastAPI framework, high performance, easy to learn, fast to code, ready for production

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Like PyTorch for ML infra. Iterable, debuggable, multi-cloud, 100% reproducible across research and production.