Best AI tools for< Tweak Prompts >

BuildShip is a batch processing tool for ChatGPT that allows users to process ChatGPT tasks in parallel on a spreadsheet UI with CSV/JSON import and export. It supports various OpenAI models, including GPT4, Claude 3, and Gemini. Users can start with readymade templates and customize them with their own logic and models. The data generated is stored securely on the user's own Google Cloud project, and team collaboration is supported with granular access control.

Twee is an AI-powered tool designed for English teachers to enhance their lessons by creating questions, dialogues, stories, articles, and various exercises quickly and efficiently. It covers a wide range of aspects in language teaching, such as reading, writing, vocabulary, listening, speaking, and grammar. Twee aims to streamline lesson planning and provide educators with innovative resources to engage students effectively.

Audyo is an AI tool that allows users to create human-quality AI voices easily by simply typing text. With over 100 voices to choose from, users can select speakers in various languages, accents, and even celebrity impersonators. The tool enables users to edit words, not waveforms, and export audio for use in videos, podcasts, presentations, and more. Audyo also offers features like creating conversations, mixing and matching languages, customizing pronunciations, and utilizing an AI assistant for script tweaking. Users can enjoy 15 minutes of audio generation with a free account and earn additional time by inviting friends. Audyo empowers creators to unleash their imagination and enhance their content with lifelike AI voices.

Audyo is a text-to-speech tool that allows users to create realistic-sounding audio from text. With over 100 voices to choose from, users can create audio in a variety of languages and accents. Audyo is easy to use, simply type in your text and select a voice. You can then download your audio file or embed it on your website or blog. Audyo is a great tool for creating voiceovers for videos, podcasts, audiobooks, and more.

UniqMail is an AI-powered email personalization tool that helps you create and send personalized emails at scale. With UniqMail, you can create unlimited projects, add up to 50 data items for message creation, and generate personalized messages with just a few clicks. UniqMail also offers direct sending, offline creation, and cost-saving features.

HeyPhoto is an AI photo editor online that utilizes artificial intelligence to enhance and manipulate facial features in photos. Users can tune selfies and group photos by changing gaze direction, skin tone, age, hair style, and other facial attributes. The tool offers a range of features such as face anonymization, gender transformation, age modification, emotion tweaking, skin tone adjustment, and more. HeyPhoto is user-friendly and requires no special skills, making it accessible for individuals looking to edit their photos effortlessly.

Polymorphia is an AI logo generator that offers over 100 unique logo options tailored for brands in a matter of minutes. It uses cutting-edge technologies to create exceptional logos based on user preferences and company descriptions. The AI-powered technology constantly adds new styles to provide the best results, generating logos from scratch to ensure uniqueness. Polymorphia has received positive reviews from users, including creative directors, CEOs, and product designers, who praise its creativity, efficiency, and quality. The application offers different pricing plans with various features, such as email support, 4k resolution, and customization options.

AI Anime Generator S is a free platform that utilizes state-of-the-art AI models to generate stunning anime images and videos. The user-friendly interface allows both beginners and professionals to easily create anime-style content. With fast processing capabilities, users can quickly generate and customize images to share on social media. The tool is optimized for performance, leveraging advanced machine learning algorithms and computing infrastructure to deliver high-quality results. While basic features are free, advanced options will be available through a premium plan in the future.

Quickchat AI is a custom AI assistant designed to automate customer support, lead generation, and more. It allows users to design, tweak, and deploy their own AI assistant trained on their data. Quickchat AI offers a range of features including customizable AI assistant name, conversation style, knowledge and actions, and deployment options. It also provides integrations with popular tools and systems, making it easy to use AI in everyday workflows.

Text-Mixer is a free online tool that allows you to remix your text like a DJ remixing a track. You can drop a message on the deck, tweak the dials of tone and style, and remix your words into a message that perfectly vibes with the audience. Text-Mixer is powered by artificial intelligence, which allows it to understand the meaning of your text and to generate new text that is both relevant and engaging.

The AI-powered Cambridge English Test platform offers exercises for English levels B1, B2, C1, and C2. Users can select exercise types such as Reading and Use of English, including activities like Open Cloze, Multiple Choice, Word Formation, and more. The AI, developed by Shining Apps in partnership with Use of English PRO, provides a unique learning experience by generating exercises from a database of over 5000 official exams. It uses advanced Natural Language Processing (NLP) to understand context, tweak exercises, and offer detailed feedback for effective learning.

Jobright is an AI-powered job search platform that acts as your co-pilot in finding the freshest job opportunities. With its advanced AI technology, Jobright scans the job market continuously to bring you up-to-date job listings, saving you time and effort in your job search. The platform matches jobs to your skills and experience, provides key company insights, and suggests resume tweaks to help you secure more interviews with the right employers. Jobright offers a wide range of job listings across various industries, making it a valuable tool for job seekers looking to stay ahead in their job search.

Wisecut is an AI automatic video editor that transforms long videos into viral clips. It minimizes editing time and maximizes content creation by using AI highlight detection to find viral-worthy snippets, storyboard-based video editing for easy tweaks, smart background music selection, auto captions and translations for enhanced engagement, and effortless removal of silences. Users can create engaging shorts in just one click, making video editing accessible to all without the need for complex skills or timelines.

The bilingual_book_maker is an AI translation tool that uses ChatGPT to assist users in creating multi-language versions of epub/txt/srt files and books. It supports various models like gpt-4, gpt-3.5-turbo, claude-2, palm, llama-2, azure-openai, command-nightly, and gemini. Users need ChatGPT or OpenAI token, epub/txt books, internet access, and Python 3.8+. The tool provides options to specify OpenAI API key, model selection, target language, proxy server, context addition, translation style, and more. It generates bilingual books in epub format after translation. Users can test translations, set batch size, tweak prompts, and use different models like DeepL, Google Gemini, Tencent TranSmart, and more. The tool also supports retranslation, translating specific tags, and e-reader type specification. Docker usage is available for easy setup.

This sample demonstrates a few approaches for creating ChatGPT-like experiences over your own data using the Retrieval Augmented Generation pattern. It uses Azure OpenAI Service to access a GPT model (gpt-35-turbo), and Azure AI Search for data indexing and retrieval. The repo includes sample data so it's ready to try end to end. In this sample application we use a fictitious company called Contoso Electronics, and the experience allows its employees to ask questions about the benefits, internal policies, as well as job descriptions and roles.

This sample demonstrates a few approaches for creating ChatGPT-like experiences over your own data using the Retrieval Augmented Generation pattern. It uses Azure OpenAI Service to access the ChatGPT model (gpt-35-turbo), and Azure AI Search for data indexing and retrieval.

LARS is an application that enables users to run Large Language Models (LLMs) locally on their devices, upload their own documents, and engage in conversations where the LLM grounds its responses with the uploaded content. The application focuses on Retrieval Augmented Generation (RAG) to increase accuracy and reduce AI-generated inaccuracies. LARS provides advanced citations, supports various file formats, allows follow-up questions, provides full chat history, and offers customization options for LLM settings. Users can force enable or disable RAG, change system prompts, and tweak advanced LLM settings. The application also supports GPU-accelerated inferencing, multiple embedding models, and text extraction methods. LARS is open-source and aims to be the ultimate RAG-centric LLM application.

WilmerAI is a middleware system designed to process prompts before sending them to Large Language Models (LLMs). It categorizes prompts, routes them to appropriate workflows, and generates manageable prompts for local models. It acts as an intermediary between the user interface and LLM APIs, supporting multiple backend LLMs simultaneously. WilmerAI provides API endpoints compatible with OpenAI API, supports prompt templates, and offers flexible connections to various LLM APIs. The project is under heavy development and may contain bugs or incomplete code.

Kobold-Assistant is a fully offline voice assistant interface to KoboldAI's large language model API. It can work online with the KoboldAI horde and online speech-to-text and text-to-speech models. The assistant, called Jenny by default, uses the latest coqui 'jenny' text to speech model and openAI's whisper speech recognition. Users can customize the assistant name, speech-to-text model, text-to-speech model, and prompts through configuration. The tool requires system packages like GCC, portaudio development libraries, and ffmpeg, along with Python >=3.7, <3.11, and runs on Ubuntu/Debian systems. Users can interact with the assistant through commands like 'serve' and 'list-mics'.

Transformer Lab is an app that allows users to experiment with Large Language Models by providing features such as one-click download of popular models, finetuning across different hardware, RLHF and Preference Optimization, working with LLMs across different operating systems, chatting with models, using different inference engines, evaluating models, building datasets for training, calculating embeddings, providing a full REST API, running in the cloud, converting models across platforms, supporting plugins, embedded Monaco code editor, prompt editing, inference logs, all through a simple cross-platform GUI.

This project provides a proof of concept for deploying a scalable, serverless LLM Generative AI inference engine on AWS Lambda. It leverages the llama.cpp project to enable the usage of more accessible CPU and RAM configurations instead of limited and expensive GPU capabilities. By deploying a container with the llama.cpp converted models onto AWS Lambda, this project offers the advantages of scale, minimizing cost, and maximizing compute availability. The project includes AWS CDK code to create and deploy a Lambda function leveraging your model of choice, with a FastAPI frontend accessible from a Lambda URL. It is important to note that you will need ggml quantized versions of your model and model sizes under 6GB, as your inference RAM requirements cannot exceed 9GB or your Lambda function will fail.

h2oGPT is an Apache V2 open-source project that allows users to query and summarize documents or chat with local private GPT LLMs. It features a private offline database of any documents (PDFs, Excel, Word, Images, Video Frames, Youtube, Audio, Code, Text, MarkDown, etc.), a persistent database (Chroma, Weaviate, or in-memory FAISS) using accurate embeddings (instructor-large, all-MiniLM-L6-v2, etc.), and efficient use of context using instruct-tuned LLMs (no need for LangChain's few-shot approach). h2oGPT also offers parallel summarization and extraction, reaching an output of 80 tokens per second with the 13B LLaMa2 model, HYDE (Hypothetical Document Embeddings) for enhanced retrieval based upon LLM responses, a variety of models supported (LLaMa2, Mistral, Falcon, Vicuna, WizardLM. With AutoGPTQ, 4-bit/8-bit, LORA, etc.), GPU support from HF and LLaMa.cpp GGML models, and CPU support using HF, LLaMa.cpp, and GPT4ALL models. Additionally, h2oGPT provides Attention Sinks for arbitrarily long generation (LLaMa-2, Mistral, MPT, Pythia, Falcon, etc.), a UI or CLI with streaming of all models, the ability to upload and view documents through the UI (control multiple collaborative or personal collections), Vision Models LLaVa, Claude-3, Gemini-Pro-Vision, GPT-4-Vision, Image Generation Stable Diffusion (sdxl-turbo, sdxl) and PlaygroundAI (playv2), Voice STT using Whisper with streaming audio conversion, Voice TTS using MIT-Licensed Microsoft Speech T5 with multiple voices and Streaming audio conversion, Voice TTS using MPL2-Licensed TTS including Voice Cloning and Streaming audio conversion, AI Assistant Voice Control Mode for hands-free control of h2oGPT chat, Bake-off UI mode against many models at the same time, Easy Download of model artifacts and control over models like LLaMa.cpp through the UI, Authentication in the UI by user/password via Native or Google OAuth, State Preservation in the UI by user/password, Linux, Docker, macOS, and Windows support, Easy Windows Installer for Windows 10 64-bit (CPU/CUDA), Easy macOS Installer for macOS (CPU/M1/M2), Inference Servers support (oLLaMa, HF TGI server, vLLM, Gradio, ExLLaMa, Replicate, OpenAI, Azure OpenAI, Anthropic), OpenAI-compliant, Server Proxy API (h2oGPT acts as drop-in-replacement to OpenAI server), Python client API (to talk to Gradio server), JSON Mode with any model via code block extraction. Also supports MistralAI JSON mode, Claude-3 via function calling with strict Schema, OpenAI via JSON mode, and vLLM via guided_json with strict Schema, Web-Search integration with Chat and Document Q/A, Agents for Search, Document Q/A, Python Code, CSV frames (Experimental, best with OpenAI currently), Evaluate performance using reward models, and Quality maintained with over 1000 unit and integration tests taking over 4 GPU-hours.

The LLM course is divided into three parts: 1. 🧩 **LLM Fundamentals** covers essential knowledge about mathematics, Python, and neural networks. 2. 🧑‍🔬 **The LLM Scientist** focuses on building the best possible LLMs using the latest techniques. 3. 👷 **The LLM Engineer** focuses on creating LLM-based applications and deploying them. For an interactive version of this course, I created two **LLM assistants** that will answer questions and test your knowledge in a personalized way: * 🤗 **HuggingChat Assistant**: Free version using Mixtral-8x7B. * 🤖 **ChatGPT Assistant**: Requires a premium account. ## 📝 Notebooks A list of notebooks and articles related to large language models. ### Tools | Notebook | Description | Notebook | |----------|-------------|----------| | 🧐 LLM AutoEval | Automatically evaluate your LLMs using RunPod |  | | 🥱 LazyMergekit | Easily merge models using MergeKit in one click. |  | | 🦎 LazyAxolotl | Fine-tune models in the cloud using Axolotl in one click. |  | | ⚡ AutoQuant | Quantize LLMs in GGUF, GPTQ, EXL2, AWQ, and HQQ formats in one click. |  | | 🌳 Model Family Tree | Visualize the family tree of merged models. |  | | 🚀 ZeroSpace | Automatically create a Gradio chat interface using a free ZeroGPU. |  |

LiveBench is a benchmark tool designed for Language Model Models (LLMs) with a focus on limiting contamination through monthly new questions based on recent datasets, arXiv papers, news articles, and IMDb movie synopses. It provides verifiable, objective ground-truth answers for accurate scoring without an LLM judge. The tool offers 18 diverse tasks across 6 categories and promises to release more challenging tasks over time. LiveBench is built on FastChat's llm_judge module and incorporates code from LiveCodeBench and IFEval.

torchchat is a codebase showcasing the ability to run large language models (LLMs) seamlessly. It allows running LLMs using Python in various environments such as desktop, server, iOS, and Android. The tool supports running models via PyTorch, chatting, generating text, running chat in the browser, and running models on desktop/server without Python. It also provides features like AOT Inductor for faster execution, running in C++ using the runner, and deploying and running on iOS and Android. The tool supports popular hardware and OS including Linux, Mac OS, Android, and iOS, with various data types and execution modes available.

Complexity is a community-driven, open-source, and free third-party extension that enhances the features of Perplexity.ai. It provides various UI/UX/QoL tweaks, LLM/Image gen model selectors, a customizable theme, and a prompts library. The tool intercepts network traffic to alter the behavior of the host page, offering a solution to the limitations of Perplexity.ai. Users can install Complexity from Chrome Web Store, Mozilla Add-on, or build it from the source code.

This plugin extends and creates `a`/`i` textobjects in Neovim. It enhances some builtin textobjects (like `a(`, `a)`, `a'`, and more), creates new ones (like `a*`, `a`, `af`, `a?`, and more), and allows the user to create their own (like based on treesitter, and more). It supports dot-repeat, `v:count`, different search methods, consecutive application, and customization via Lua patterns or functions. It has builtins for brackets, quotes, function call, argument, tag, user prompt, and any punctuation/digit/whitespace character.

Palera1n-Jailbreak is a comprehensive guide and tool for jailbreaking iOS 17.6.1 to iOS 15 and iPadOS 18.1 beta 4, 17. It provides information on compatibility, installation, achievements, research data, and working tweak list. The tool is based on the checkm8 exploit, allowing customization of iOS devices with third-party apps and tweaks. Palera1n offers features like root access, tweak injection, and custom themes, making it a valuable tool for iOS customization enthusiasts.

AgentForge is a low-code framework tailored for the rapid development, testing, and iteration of AI-powered autonomous agents and Cognitive Architectures. It is compatible with a range of LLM models and offers flexibility to run different models for different agents based on specific needs. The framework is designed for seamless extensibility and database-flexibility, making it an ideal playground for various AI projects. AgentForge is a beta-testing ground and future-proof hub for crafting intelligent, model-agnostic autonomous agents.

fish-ai is a tool that adds AI functionality to Fish shell. It can be integrated with various AI providers like OpenAI, Azure OpenAI, Google, Hugging Face, Mistral, or a self-hosted LLM. Users can transform comments into commands, autocomplete commands, and suggest fixes. The tool allows customization through configuration files and supports switching between contexts. Data privacy is maintained by redacting sensitive information before submission to the AI models. Development features include debug logging, testing, and creating releases.

A discord bot built to interface with the InvokeAI fork of stable-diffusion. It is a work in progress for a major rewrite of the arty project, compatible with `invokeai 5.1.1`. The bot supports various functionalities like building node graphs from job requests, refreshing renders using png metadata, removing backgrounds, job progress tracking, and LLM integration. Users can install custom invokeai nodes for advanced functionality and launch the bot natively or with docker. Patches and pull requests are welcomed.

LLM-Minutes-of-Meeting is a project showcasing NLP & LLM's capability to summarize long meetings and automate the task of delegating Minutes of Meeting(MoM) emails. It converts audio/video files to text, generates editable MoM, and aims to develop a real-time python web-application for meeting automation. The tool features keyword highlighting, topic tagging, export in various formats, user-friendly interface, and uses Celery for asynchronous processing. It is designed for corporate meetings, educational institutions, legal and medical fields, accessibility, and event coverage.

This repository contains a hand-curated list of great machine (deep) learning resources for Natural Language Processing (NLP) with a focus on Generative Pre-trained Transformer (GPT), Bidirectional Encoder Representations from Transformers (BERT), attention mechanism, Transformer architectures/networks, Chatbot, and transfer learning in NLP.

🎨 Unleash creativity with your AI sidekick for scripting 3D models! Generate, tweak, and perfect scripts efficiently! 🚀✨