PyRIT is an open access automation framework designed to empower security professionals and ML engineers to red team foundation models and their applications. It automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft). The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.

FarmVibes.AI is a repository focused on developing multi-modal geospatial machine learning models for agriculture and sustainability. It enables users to fuse various geospatial and spatiotemporal datasets, such as satellite imagery, drone imagery, and weather data, to generate robust insights for agriculture-related problems. The repository provides fusion workflows, data preparation tools, model training notebooks, and an inference engine to facilitate the creation of geospatial models tailored for agriculture and farming. Users can interact with the tools via a local cluster, REST API, or a Python client, and the repository includes documentation and notebook examples to guide users in utilizing FarmVibes.AI for tasks like harvest date detection, climate impact estimation, micro climate prediction, and crop identification.

This repository serves as a hub for Microsoft Official Build & Modernize AI Applications reference solutions and content. It provides access to projects demonstrating how to build Generative AI applications using Azure services like Azure OpenAI, Azure Container Apps, Azure Kubernetes, and Azure Cosmos DB. The solutions include Vector Search & AI Assistant, Real-Time Payment and Transaction Processing, and Medical Claims Processing. Additionally, there are workshops like the Intelligent App Workshop for Microsoft Copilot Stack, focusing on infusing intelligence into traditional software systems using foundation models and design thinking.

FoundationaLLM is a platform designed for deploying, scaling, securing, and governing generative AI in enterprises. It allows users to create AI agents grounded in enterprise data, integrate REST APIs, experiment with large language models, centrally manage AI agents and assets, deploy scalable vectorization data pipelines, enable non-developer users to create their own AI agents, control access with role-based access controls, and harness capabilities from Azure AI and Azure OpenAI. The platform simplifies integration with enterprise data sources, provides fine-grain security controls, load balances across multiple endpoints, and is extensible to new data sources and orchestrators. FoundationaLLM addresses the need for customized copilots or AI agents that are secure, licensed, flexible, and suitable for enterprise-scale production.

RecAI is a project that explores the integration of Large Language Models (LLMs) into recommender systems, addressing the challenges of interactivity, explainability, and controllability. It aims to bridge the gap between general-purpose LLMs and domain-specific recommender systems, providing a holistic perspective on the practical requirements of LLM4Rec. The project investigates various techniques, including Recommender AI agents, selective knowledge injection, fine-tuning language models, evaluation, and LLMs as model explainers, to create more sophisticated, interactive, and user-centric recommender systems.

Seismometer is a suite of tools designed to evaluate AI model performance in healthcare settings. It helps healthcare organizations assess the accuracy of AI models and ensure equitable care for diverse patient populations. The tool allows users to validate model performance using standardized evaluation criteria based on local data and workflows. It includes templates for analyzing statistical performance, fairness across different cohorts, and the impact of interventions on outcomes. Seismometer is continuously evolving to incorporate new validation and analysis techniques.

AnkiGPT is a tool that leverages GPT-3.5 or GPT-4 by OpenAI to generate flashcards from lecture slides or text input. Users can easily export the generated flashcards to Anki for effective learning. The tool allows users to edit, delete, and share flashcards, as well as generate mnemonics. AnkiGPT supports nearly all languages and ensures user privacy by not using submitted content for AI training. While powerful, the tool has limitations such as occasional errors in generated flashcards and challenges with mathematical equations. AnkiGPT is designed specifically for Anki flashcard app integration and encourages users to review and verify flashcard information for accuracy.

The Enterprise Azure OpenAI Hub is a comprehensive repository designed to guide users through the world of Generative AI on the Azure platform. It offers a structured learning experience to accelerate the transition from concept to production in an Enterprise context. The hub empowers users to explore various use cases with Azure services, ensuring security and compliance. It provides real-world examples and playbooks for practical insights into solving complex problems and developing cutting-edge AI solutions. The repository also serves as a library of proven patterns, aligning with industry standards and promoting best practices for secure and compliant AI development.

StoryToolkitAI is a film editing tool that utilizes AI to transcribe, index scenes, search through footage, and create stories. It offers features such as automatic transcription, translation, story creation, speaker detection, project file management, and more. The tool works locally on your machine and integrates with DaVinci Resolve Studio 18. It aims to streamline the editing process by leveraging AI capabilities and enhancing user efficiency.

Trace is a new AutoDiff-like tool for training AI systems end-to-end with general feedback. It generalizes the back-propagation algorithm by capturing and propagating an AI system's execution trace. Implemented as a PyTorch-like Python library, users can write Python code directly and use Trace primitives to optimize certain parts, similar to training neural networks.

The Oracle Cloud Infrastructure Data Science and AI services Examples repository provides demos, tutorials, and code examples showcasing various features of the OCI Data Science service and AI services. It offers tools for data scientists to develop and deploy machine learning models efficiently, with features like Accelerated Data Science SDK, distributed training, batch processing, and machine learning pipelines. Whether you're a beginner or an experienced practitioner, OCI Data Science Services provide the resources needed to build, train, and deploy models easily.

TypeChat is a library that simplifies the creation of natural language interfaces using types. Traditionally, building natural language interfaces has been challenging, often relying on complex decision trees to determine intent and gather necessary inputs for action. Large language models (LLMs) have simplified this process by allowing us to accept natural language input from users and match it to intent. However, this has introduced new challenges, such as the need to constrain the model's response for safety, structure responses from the model for further processing, and ensure the validity of the model's response. Prompt engineering aims to address these issues, but it comes with a steep learning curve and increased fragility as the prompt grows in size.

This repository contains materials for the Microsoft Learn AI Fundamentals module. It covers the basics of artificial intelligence, machine learning, and data science. The content includes hands-on labs, interactive learning modules, and assessments to help learners understand key concepts and techniques in AI. Whether you are new to AI or looking to expand your knowledge, this module provides a comprehensive introduction to the fundamentals of AI.

An opinionated .NET framework, that is built on top of Semantic Kernel and Orleans, which helps creating and hosting event-driven AI Agents.

The Conversational Azure OpenAI Accelerator is a tool designed to provide rapid, no-cost custom demos tailored to customer use cases, from internal HR/IT to external contact centers. It focuses on top use cases of GenAI conversation and summarization, plus live backend data integration. The tool automates conversations across voice and text channels, providing a valuable way to save money and improve customer and employee experience. By combining Azure OpenAI + Cognitive Search, users can efficiently deploy a ChatGPT experience using web pages, knowledge base articles, and data sources. The tool enables simultaneous deployment of conversational content to chatbots, IVR, voice assistants, and more in one click, eliminating the need for in-depth IT involvement. It leverages Microsoft's advanced AI technologies, resulting in a conversational experience that can converse in human-like dialogue, respond intelligently, and capture content for omni-channel unified analytics.

AI Agents Framework is a .NET framework built on Semantic Kernel and Orleans for creating and hosting event-driven AI Agents. It is currently in an experimental phase and not recommended for production use. The framework aims to automate requirements engineering, planning, and coding processes using event-driven agents.

PyRIT is an open access automation framework designed to empower security professionals and ML engineers to red team foundation models and their applications. It automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft). The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.

FastTrackML is an experiment tracking server focused on speed and scalability, fully compatible with MLFlow. It provides a user-friendly interface to track and visualize your machine learning experiments, making it easy to compare different models and identify the best performing ones. FastTrackML is open source and can be easily installed and run with pip or Docker. It is also compatible with the MLFlow Python package, making it easy to integrate with your existing MLFlow workflows.

ScandEval is a framework for evaluating pretrained language models on mono- or multilingual language tasks. It provides a unified interface for benchmarking models on a variety of tasks, including sentiment analysis, question answering, and machine translation. ScandEval is designed to be easy to use and extensible, making it a valuable tool for researchers and practitioners alike.

OpenCompass is a one-stop platform for large model evaluation, aiming to provide a fair, open, and reproducible benchmark for large model evaluation. Its main features include: * Comprehensive support for models and datasets: Pre-support for 20+ HuggingFace and API models, a model evaluation scheme of 70+ datasets with about 400,000 questions, comprehensively evaluating the capabilities of the models in five dimensions. * Efficient distributed evaluation: One line command to implement task division and distributed evaluation, completing the full evaluation of billion-scale models in just a few hours. * Diversified evaluation paradigms: Support for zero-shot, few-shot, and chain-of-thought evaluations, combined with standard or dialogue-type prompt templates, to easily stimulate the maximum performance of various models. * Modular design with high extensibility: Want to add new models or datasets, customize an advanced task division strategy, or even support a new cluster management system? Everything about OpenCompass can be easily expanded! * Experiment management and reporting mechanism: Use config files to fully record each experiment, and support real-time reporting of results.

LightEval is a lightweight LLM evaluation suite that Hugging Face has been using internally with the recently released LLM data processing library datatrove and LLM training library nanotron. We're releasing it with the community in the spirit of building in the open. Note that it is still very much early so don't expect 100% stability ^^' In case of problems or question, feel free to open an issue!

Dwata is a desktop application that allows users to chat with any AI model and gain insights from their data. Chats are organized into threads, similar to Discord, with each thread connecting to a different AI model. Dwata can connect to databases, APIs (such as Stripe), or CSV files and send structured data as prompts when needed. The AI's response will often include SQL or Python code, which can be used to extract the desired insights. Dwata can validate AI-generated SQL to ensure that the tables and columns referenced are correct and can execute queries against the database from within the application. Python code (typically using Pandas) can also be executed from within Dwata, although this feature is still in development. Dwata supports a range of AI models, including OpenAI's GPT-4, GPT-4 Turbo, and GPT-3.5 Turbo; Groq's LLaMA2-70b and Mixtral-8x7b; Phind's Phind-34B and Phind-70B; Anthropic's Claude; and Ollama's Llama 2, Mistral, and Phi-2 Gemma. Dwata can compare chats from different models, allowing users to see the responses of multiple models to the same prompts. Dwata can connect to various data sources, including databases (PostgreSQL, MySQL, MongoDB), SaaS products (Stripe, Shopify), CSV files/folders, and email (IMAP). The desktop application does not collect any private or business data without the user's explicit consent.

A Rust based tool to evaluate LLM models, prompts and model params. It automates the process of selecting the best model parameters, given an LLM model and a prompt, iterating over the possible combinations and letting the user visually inspect the results. The tool assumes the user has Ollama installed and serving endpoints, either in `localhost` or in a remote server. Key features include: * Automatically fetches models from local or remote Ollama servers * Iterates over different models and params to generate inferences * A/B test prompts on different models simultaneously * Allows multiple iterations for each combination of parameters * Makes synchronous inference calls to avoid spamming servers * Optionally outputs inference parameters and response metadata (inference time, tokens and tokens/s) * Refetching of individual inference calls * Model selection can be filtered by name * List experiments which can be downloaded in JSON format * Configurable inference timeout * Custom default parameters and system prompts can be defined in settings

Eval-Scope is a framework for evaluating and improving large language models (LLMs). It provides a set of commonly used test datasets, metrics, and a unified model interface for generating and evaluating LLM responses. Eval-Scope also includes an automatic evaluator that can score objective questions and use expert models to evaluate complex tasks. Additionally, it offers a visual report generator, an arena mode for comparing multiple models, and a variety of other features to support LLM evaluation and development.

Weave is a toolkit for developing Generative AI applications, built by Weights & Biases. With Weave, you can log and debug language model inputs, outputs, and traces; build rigorous, apples-to-apples evaluations for language model use cases; and organize all the information generated across the LLM workflow, from experimentation to evaluations to production. Weave aims to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.

LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

The VisionCraft API is a free API for using over 100 different AI models. From images to sound.

Kaito is an operator that automates the AI/ML inference model deployment in a Kubernetes cluster. It manages large model files using container images, avoids tuning deployment parameters to fit GPU hardware by providing preset configurations, auto-provisions GPU nodes based on model requirements, and hosts large model images in the public Microsoft Container Registry (MCR) if the license allows. Using Kaito, the workflow of onboarding large AI inference models in Kubernetes is largely simplified.

PyRIT is an open access automation framework designed to empower security professionals and ML engineers to red team foundation models and their applications. It automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft). The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.

Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features: * Self-contained, with no need for a DBMS or cloud service. * OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE). * Supports consumer-grade GPUs.

SPEAR (Simulator for Photorealistic Embodied AI Research) is a powerful tool for training embodied agents. It features 300 unique virtual indoor environments with 2,566 unique rooms and 17,234 unique objects that can be manipulated individually. Each environment is designed by a professional artist and features detailed geometry, photorealistic materials, and a unique floor plan and object layout. SPEAR is implemented as Unreal Engine assets and provides an OpenAI Gym interface for interacting with the environments via Python.

Magick is a groundbreaking visual AIDE (Artificial Intelligence Development Environment) for no-code data pipelines and multimodal agents. Magick can connect to other services and comes with nodes and templates well-suited for intelligent agents, chatbots, complex reasoning systems and realistic characters.