Promptwright is a Python library designed for generating large synthetic datasets using a local LLM and various LLM service providers. It offers flexible interfaces for generating prompt-led synthetic datasets. The library supports multiple providers, configurable instructions and prompts, YAML configuration for tasks, command line interface for running tasks, push to Hugging Face Hub for dataset upload, and system message control. Users can define generation tasks using YAML configuration or Python code. Promptwright integrates with LiteLLM to interface with LLM providers and supports automatic dataset upload to Hugging Face Hub.

WebRL is a self-evolving online curriculum learning framework designed for training web agents in the WebArena environment. It provides model checkpoints, training instructions, and evaluation processes for training the actor and critic models. The tool enables users to generate new instructions and interact with WebArena to configure tasks for training and evaluation.

The Neo4j GraphRAG package for Python is an official repository that provides features for creating and managing vector indexes in Neo4j databases. It aims to offer developers a reliable package with long-term commitment, maintenance, and fast feature updates. The package supports various Python versions and includes functionalities for creating vector indexes, populating them, and performing similarity searches. It also provides guidelines for installation, examples, and development processes such as installing dependencies, making changes, and running tests.

SDFX is the ultimate no-code platform for building and sharing AI apps with beautiful UI. It enables the creation of user-friendly interfaces for complex workflows by combining Comfy workflow with a UI. The tool is designed to merge the benefits of form-based UI and graph-node based UI, allowing users to create intricate graphs with a high-level UI overlay. SDFX is fully compatible with ComfyUI, abstracting the need for installing ComfyUI. It offers features like animated graph navigation, node bookmarks, UI debugger, custom nodes manager, app and template export, image and mask editor, and more. The tool compiles as a native app or web app, making it easy to maintain and add new features.

The 'bot-on-anything' repository allows developers to integrate various AI models into messaging applications, enabling the creation of intelligent chatbots. By configuring the connections between models and applications, developers can easily switch between multiple channels within a project. The architecture is highly scalable, allowing the reuse of algorithmic capabilities for each new application and model integration. Supported models include ChatGPT, GPT-3.0, New Bing, and Google Bard, while supported applications range from terminals and web platforms to messaging apps like WeChat, Telegram, QQ, and more. The repository provides detailed instructions for setting up the environment, configuring the models and channels, and running the chatbot for various tasks across different messaging platforms.

Marqo is more than a vector database, it's an end-to-end vector search engine for both text and images. Vector generation, storage and retrieval are handled out of the box through a single API. No need to bring your own embeddings.

Invariant Analyzer is an open-source scanner designed for LLM-based AI agents to find bugs, vulnerabilities, and security threats. It scans agent execution traces to identify issues like looping behavior, data leaks, prompt injections, and unsafe code execution. The tool offers a library of built-in checkers, an expressive policy language, data flow analysis, real-time monitoring, and extensible architecture for custom checkers. It helps developers debug AI agents, scan for security violations, and prevent security issues and data breaches during runtime. The analyzer leverages deep contextual understanding and a purpose-built rule matching engine for security policy enforcement.

Iceburg CRM is a metadata driven CRM with AI abilities that allows users to quickly prototype any CRM. It offers features like metadata creations, import/export in multiple formats, field validation, themes, role permissions, calendar, audit logs, API, workflow, field level relationships, module level relationships, and more. Created with Vue 3 for the frontend, Laravel 10 for the backend, Tailwinds with DaisyUI plugin, and Inertia for routing. Users can install default, admin panel, core, custom, or AI versions. The tool supports AI Assist for module data suggestions and provides API endpoints for CRM modules, search, specific module data, record updates, and deletions. Iceburg CRM also includes themes, custom field types, calendar, datalets, workflow, roles and permissions, import/export functionality, and custom seeding options.

Arch is an intelligent Layer 7 gateway designed to protect, observe, and personalize AI agents with APIs. It handles tasks related to prompts, including detecting jailbreak attempts, calling backend APIs, routing between LLMs, and managing observability. Built on Envoy Proxy, it offers features like function calling, prompt guardrails, traffic management, and observability. Users can build fast, observable, and personalized AI agents using Arch to improve speed, security, and personalization of GenAI apps.

AI Artifacts is an open source tool that replicates Anthropic's Artifacts UI in the Claude chat app. It utilizes E2B's Code Interpreter SDK and Core SDK for secure AI code execution in a cloud sandbox environment. Users can run AI-generated code in various languages such as Python, JavaScript, R, and Nextjs apps. The tool also supports running AI-generated Python in Jupyter notebook, Next.js apps, and Streamlit apps. Additionally, it offers integration with Vercel AI SDK for tool calling and streaming responses from the model.

ActionWeaver is an AI application framework designed for simplicity, relying on OpenAI and Pydantic. It supports both OpenAI API and Azure OpenAI service. The framework allows for function calling as a core feature, extensibility to integrate any Python code, function orchestration for building complex call hierarchies, and telemetry and observability integration. Users can easily install ActionWeaver using pip and leverage its capabilities to create, invoke, and orchestrate actions with the language model. The framework also provides structured extraction using Pydantic models and allows for exception handling customization. Contributions to the project are welcome, and users are encouraged to cite ActionWeaver if found useful.

Fragments is an open-source tool that leverages Anthropic's Claude Artifacts, Vercel v0, and GPT Engineer. It is powered by E2B Sandbox SDK and Code Interpreter SDK, allowing secure execution of AI-generated code. The tool is based on Next.js 14, shadcn/ui, TailwindCSS, and Vercel AI SDK. Users can stream in the UI, install packages from npm and pip, and add custom stacks and LLM providers. Fragments enables users to build web apps with Python interpreter, Next.js, Vue.js, Streamlit, and Gradio, utilizing providers like OpenAI, Anthropic, Google AI, and more.

Elia is a powerful terminal user interface designed for interacting with large language models. It allows users to chat with models like Claude 3, ChatGPT, Llama 3, Phi 3, Mistral, and Gemma. Conversations are stored locally in a SQLite database, ensuring privacy. Users can run local models through 'ollama' without data leaving their machine. Elia offers easy installation with pipx and supports various environment variables for different models. It provides a quick start to launch chats and manage local models. Configuration options are available to customize default models, system prompts, and add new models. Users can import conversations from ChatGPT and wipe the database when needed. Elia aims to enhance user experience in interacting with language models through a user-friendly interface.

The Python Redis Vector Library (RedisVL) is a tailor-made client for AI applications leveraging Redis. It enhances applications with Redis' speed, flexibility, and reliability, incorporating capabilities like vector-based semantic search, full-text search, and geo-spatial search. The library bridges the gap between the emerging AI-native developer ecosystem and the capabilities of Redis by providing a lightweight, elegant, and intuitive interface. It abstracts the features of Redis into a grammar that is more aligned to the needs of today's AI/ML Engineers or Data Scientists.

CredSweeper is a tool designed to detect credentials like tokens, passwords, and API keys in directories or files. It helps users identify potential exposure of sensitive information by scanning lines, filtering, and utilizing an AI model. The tool reports lines containing possible credentials, their location, and the expected type of credential.

GPT-4V-Act is a multimodal AI assistant that combines GPT-4V(ision) with a web browser to mirror human operator input and output. It facilitates human-computer operations, boosts UI accessibility, aids workflow automation, and enables automated UI testing through AI labeling and set-of-marks prompting.

Promptwright is a Python library designed for generating large synthetic datasets using a local LLM and various LLM service providers. It offers flexible interfaces for generating prompt-led synthetic datasets. The library supports multiple providers, configurable instructions and prompts, YAML configuration for tasks, command line interface for running tasks, push to Hugging Face Hub for dataset upload, and system message control. Users can define generation tasks using YAML configuration or Python code. Promptwright integrates with LiteLLM to interface with LLM providers and supports automatic dataset upload to Hugging Face Hub.

QGate-Model is a machine learning meta-model with synthetic data, designed for MLOps and feature store. It is independent of machine learning solutions, with definitions in JSON and data in CSV/parquet formats. This meta-model is useful for comparing capabilities and functions of machine learning solutions, independently testing new versions of machine learning solutions, and conducting various types of tests (unit, sanity, smoke, system, regression, function, acceptance, performance, shadow, etc.). It can also be used for external test coverage when internal test coverage is not available or weak.

LLM Datasets is a repository containing high-quality datasets, tools, and concepts for LLM fine-tuning. It provides datasets with characteristics like accuracy, diversity, and complexity to train large language models for various tasks. The repository includes datasets for general-purpose, math & logic, code, conversation & role-play, and agent & function calling domains. It also offers guidance on creating high-quality datasets through data deduplication, data quality assessment, data exploration, and data generation techniques.

LLM4IR-Survey is a collection of papers related to large language models for information retrieval, organized according to the survey paper 'Large Language Models for Information Retrieval: A Survey'. It covers various aspects such as query rewriting, retrievers, rerankers, readers, search agents, and more, providing insights into the integration of large language models with information retrieval systems.

This repository contains material related to the new book _Synthetic Data and Generative AI_ by the author, including code for NoGAN, DeepResampling, and NoGAN_Hellinger. NoGAN is a tabular data synthesizer that outperforms GenAI methods in terms of speed and results, utilizing state-of-the-art quality metrics. DeepResampling is a fast NoGAN based on resampling and Bayesian Models with hyperparameter auto-tuning. NoGAN_Hellinger combines NoGAN and DeepResampling with the Hellinger model evaluation metric.

Open-Source Evaluation for LLM Applications. `continuous-eval` is an open-source package created for granular and holistic evaluation of GenAI application pipelines. It offers modularized evaluation, a comprehensive metric library covering various LLM use cases, the ability to leverage user feedback in evaluation, and synthetic dataset generation for testing pipelines. Users can define their own metrics by extending the Metric class. The tool allows running evaluation on a pipeline defined with modules and corresponding metrics. Additionally, it provides synthetic data generation capabilities to create user interaction data for evaluation or training purposes.

eShopSupport is a sample .NET application showcasing common use cases and development practices for building AI solutions in .NET, specifically Generative AI. It demonstrates a customer support application for an e-commerce website using a services-based architecture with .NET Aspire. The application includes support for text classification, sentiment analysis, text summarization, synthetic data generation, and chat bot interactions. It also showcases development practices such as developing solutions locally, evaluating AI responses, leveraging Python projects, and deploying applications to the Cloud.

A collection of papers related to knowledge distillation of large language models (LLMs). The repository focuses on techniques to transfer advanced capabilities from proprietary LLMs to smaller models, compress open-source LLMs, and refine their performance. It covers various aspects of knowledge distillation, including algorithms, skill distillation, verticalization distillation in fields like law, medical & healthcare, finance, science, and miscellaneous domains. The repository provides a comprehensive overview of the research in the area of knowledge distillation of LLMs.

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.