Here is a list of LLM Tools and libraries. Some of them are just WOW. I simply loved the dreamstudio and few visual prompt generators.
I was like ROFL when I saw the picture of “A robot looking at sky in mars with 100s of minions around”. I could hardly imagine something like that, but the output was super awesome.
But it failed when I said “A tomato in mars with IBM Mainframe system/360 in the front with lots of children around”
Was that a complicated prompt? :)
What is your favorite tool from the list? Comment some of the pictures / results you generated after using these tools.
AI Test Kitchen is a place where people can experience and give feedback on some of Google’s latest AI technologies. Our goal is to learn, improve, and innovate responsibly on AI together.
BetterPrompt is an AI tool designed to help users improve their midjourney prompts. The platform offers an easy way for users to become prompt masters and supports over 100 languages
Chainlist is a handy tool that helps users connect to an Ethereum Virtual Machine (EVM) -driven network linked list. Users can use Chainlist to connect their wallets to the required chain network for easy network configuration.
An AI chatbot prompt generator is a tool that generates prompts or suggestions for chatbots to use in their conversations with users.
click-prompt provides more beautiful interactive options for the Python click library. The library is inspired by a post on stackoverflow.com.
Start generating the images of your dreams. Get early access to the SDXL model preview and be the first to try out new features.
Harnesses the power of LLMs to help your teams craft better content, understand their environment faster, and ultimately take better decisions.
Dyno is a feature-rich and modular discord bot for your Discord server. A fully customizable server moderation Discord bot for your Discord server that features a simple and intuitive web dashboard. Server management just got a whole lot easier.
AI Powered AI News portal
A tool or platform that offers a wide range of prompts or templates for various applications and use cases.
fastRAG is a research framework designed to facilitate the building of retrieval augmented generative pipelines. Its main goal is to make retrieval augmented generation as efficient as possible through the use of state-of-the-art and efficient retrieval and generative models. The framework includes a variety of sparse and dense retrieval models, as well as different extractive and generative information processing models. fastRAG aims to provide researchers and developers with a comprehensive tool-set for exploring and advancing the field of retrieval augmented generation.
Guardrails is an open-source Python package for specifying structure and type, validating and correcting the outputs of large language models (LLMs).
Guidance enables you to control modern language models more effectively and efficiently than traditional prompting or chaining. Guidance programs allow you to interleave generation, prompting, and logical control into a single continuous flow matching how the language model actually processes the text. Simple output structures like Chain of Thought and its many variants (e.g., ART, Auto-CoT, etc.) have been shown to improve LLM performance. The advent of more powerful LLMs like GPT-4 allows for even richer structure, and guidance makes that structure easier and cheaper.GPT Index: An index or catalog of various versions, models, and resources related to OpenAI’s GPT language models.
LlamaIndex (GPT Index) is a data framework for your LLM application.
A set of tools or utilities designed to work with OpenAI’s GPT models, offering additional functionality or enhancements. This tool lets you try out different settings (engines, temp, top p, etc.) and compare the results.
Curation of prompts that are known to be adversarial to large language models. Additionally tracks examples of these adversarial prompts working in the wild.
Interactive Composition Explorer
ICE is a Python library and trace visualizer for language model programs.
Workspace for Open AI Prompts to manage and build your prompts
Large language models (LLMs) are emerging as a transformative technology, enabling developers to build applications that they previously could not. However, using these LLMs in isolation is often insufficient for creating a truly powerful app — the real power comes when you can combine them with other sources of computation or knowledge.LangChain aims to assist in the development of those types of applications.
Lexica. art is a website that acts as a search engine and art gallery for artwork created with Stable Diffusion models.
An extensible, convenient, and efficient toolbox for finetuning large machine learning models, designed to be user-friendly, speedy and reliable, and accessible to the entire community.
Loom is an experimental tree-based writing interface for GPT-3. The code is actively being developed and thus unstable and poorly documented.
Prompt suggestions for GPT-3, ChatGPT, and DALLE-2
OpenICL provides an easy interface for in-context learning, with many state-of-the-art retrieval and inference methods built in to facilitate systematic comparison of LMs and fast research prototyping. Users can easily incorporate different retrieval and inference methods, as well as different prompt instructions into their workflow.
Prompt-learning is the latest paradigm to adapt pre-trained language models (PLMs) to downstream NLP tasks, which modifies the input text with a textual template and directly uses PLMs to conduct pre-trained tasks. This library provides a standard, flexible and extensible framework to deploy the prompt-learning pipeline. OpenPrompt supports loading PLMs directly from huggingface transformers.
The prompt engineering platform to experiment with different prompt versions, evaluate and compare prompts across a suite of tests, optimize prompts with one-click, share and more.
Playground AI allows users to create and share AI art. It offers a platform for making use of AI tools like DALL-E2 and Stable Diffusion 1.5 & 2.0 to generate original images in response to textual instructions. The platform provides a variety of filters to assist users in achieving their preferred look.
Prodia — AI Art and Music is an AI tool that allows users to create art using artificial intelligence. The tool offers various AI-generated art options, including Analog V1, Anything V3, Anything V4.
A bunch of ChatGPT apps used to play around with in a playground.
PromptBase is a marketplace for buying and selling quality prompts for creating specific AI generated images. They call this “prompt engineering”. As we are quickly learning, there is definitely something valuable about being able to craft prompts that best leverage the AI model’s capabilities.
This repo contains an NPM utility library for creating and maintaining prompts for Large Language Models (LLMs).
Promptable is a Typescript library for building fullstack AI applications. Promptable consists of a collection of utilities and interfaces that help you build applications with LLMs. It is designed to be flexible and extensible so that you can use it with any LLM or Embeddings provider.
Transformer-based large language models (LLMs) provide a powerful foundation for natural language tasks in large-scale customer-facing applications. However, studies that explore their vulnerabilities emerging from malicious user interaction are scarce. By proposing PROMPTINJECT, a prosaic alignment framework for mask-based iterative adversarial prompt composition, we examine how GPT-3, the most widely deployed language model in production, can be easily misaligned by simple handcrafted inputs. In particular, we investigate two types of attacks — goal hijacking and prompt leaking — and demonstrate that even low-aptitude, but sufficiently ill-intentioned agents, can easily exploit GPT-3’s stochastic nature, creating long-tail risks.
An advanced GPT-3 playground.
It has two main goals:
- Help first-time GPT-3 users to discover capabilities, strengths and weaknesses of the technology.
- Help developers to experiment with prompt engineering by optimizing the product for concrete use cases such as creative writing, classification, chat bots and others.
Compose, test, optimize, and deploy reliable prompts for the leading language models and AI platforms to supercharge your apps and workflows.
PromptPerfect is a prompt optimization tool designed to enhance the quality of large language model and large model results.
Create AI Apps & Chatbots in Minutes. Build tailor-made generative AI applications and chatbots that cater to your users’ unique needs. Seamlessly integrate your own data and GPT-powered models without any coding experience.
PromptSource is a toolkit for creating, sharing and using natural language prompts.
Recent work has shown that large language models exhibit the ability to perform reasonable zero-shot generalization to new tasks. For instance, GPT-3 demonstrated that large language models have strong zero- and few-shot abilities. FLAN and T0 then demonstrated that pre-trained language models fine-tuned in a massively multitask fashion yield even stronger zero-shot performance. A common denominator in these works is the use of prompts which have gathered of interest among NLP researchers and engineers. This emphasizes the need for new tools to create, share and use natural language prompts.
Build, compare, and deploy large language model apps with Scale Spellbook.
Share your wildest ChatGPT conversations with one click.
ThoughtSource is a central, open resource and community centered on data and tools for chain-of-thought reasoning in large language models (Wei 2022). Our long-term goal is to enable trustworthy and robust reasoning in advanced AI systems for driving scientific research and medical practice.
Build prompts visually for DALL-E, Midjourney, and other AI art generation tools.
