A framework for rapid development and deployment of production-ready RAG systemsR2R: Production-ready RAG systems. A semi-opinionated RAG framework. R2R was conceived to bridge the gap between experimental RAG models and robust, production-ready systems. Our semi-opinionated framework cuts through the complexity, offering a straightforward path to deploy, adapt, and maintain RAG pipelines in production. We prioritize simplicity and practicality, aiming to set a new industry be…
Windows in a Docker container.Windows Windows in a Docker container. Features ISO downloader KVM acceleration Web-based viewer Usage Via docker-compose.yml version: "3" services: windows: image: dockurr/windows container_name: windows devices: - /dev/kvm cap_add: - NET_ADMIN ports: - 8006:8006 - 3389:3389/tcp - 3389:3389/udp stop_grace_period: 2m restart: on-failure Via docker run docker run -it --rm --name windows -…
📱 user interfaces for react-three-fiber@react-three/uikit Build performant 3D user interfaces for Three.js using @react-three/fiber and yoga Changes over Koestlich higher performance (GPU + CPU) no suspense (similarly to html/css images and texts don't suspend) objects are nested for correct event propagation no default animations complete freedom to use R3F inside of UI => ... better scroll experiences (scrollbar + overscroll) overall DX improvements (hover, responsive, ...) TODO Rele…
Lightweight Postgres packaged as WASM into a TypeScript library for the browser, Node.js, Bun and DenoPGlite - Postgres in WASM PGlite is a WASM Postgres build packaged into a TypeScript client library that enables you to run Postgres in the browser, Node.js and Bun, with no need to install any other dependencies. It is only 3.7mb gzipped. import { PGlite } from "@electric-sql/pglite" const db = new PGlite() await db.query("select 'Hello world' as message;") // -> […
Accelerate your Hugging Face Transformers 6-7x. Native to Hugging Face and PyTorch.GPTFast Accelerate your Hugging Face Transformers 6-7x with GPTFast! Background GPTFast was originally a set of techniques developed by the PyTorch Team to accelerate the inference speed of Llama-2-7b. This pip package generalizes those techniques to all Hugging Face models. Demo GPTFast Inference Time Eager Inference Time Getting Started Make sure that your python version >= 3.10, and you are on …
Fuel Network Rust SDKfuels-rs Rust SDK for Fuel. It can be used for a variety of things, including but not limited to: Compiling, deploying, and testing Sway contracts; Launching a local Fuel network; Crafting and signing transactions with hand-crafted scripts or contract calls; Generating type-safe Rust bindings of contract methods; And more, fuels-rs is still in active development. Documentation See the fuels-rs book Features Launch Fuel nodes Deploy contracts Interact with deployed…
A framework for prompt tuning using Intent-based Prompt Calibration 📝 AutoPrompt Auto Prompt is a prompt optimization framework designed to enhance and perfect your prompts for real-world use cases. The framework automatically generates high-quality, detailed prompts tailored to user intentions. It employs a refinement (calibration) process, where it iteratively builds a dataset of challenging edge cases and optimizes the prompt accordingly. This approach not onl…
The distributed financial transactions database designed for mission critical safety and performance.
OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement [🏠Homepage] | [🛠️Code] 🌟 Upcoming Features 💡 Open Sourcing OpenCodeInterpreter-GM-7b Model with gemma-7b Base; 🚀 Deploying Demo on HuggingFace Spaces; 🛠️ Open Sourcing Demo Local Deployment Code with a Setup Guide 🔔News ✨[2024-02-26]: We have open-sourced the OpenCodeInterpreter-DS-1.3b Model. 📘[2024-02-26]: We have open-sourced the CodeFeedback-Filtered-Instruction Dataset. 🚀[2024-02-23]: We ha…