Text Generation Web UI AI technology page Top Builders

Explore the top contributors showcasing the highest number of Text Generation Web UI AI technology page app submissions within our community.

Text Generation Web UI

The Text Generation Web UI is a Gradio-based interface for running Large Language Models like LLaMA, llama.cpp, GPT-J, Pythia, OPT, and GALACTICA. It provides a user-friendly interface to interact with these models and generate text, with features such as model switching, notebook mode, chat mode, and more. The project aims to become the go-to web UI for text generation and is similar to AUTOMATIC1111/stable-diffusion-webui in terms of functionality.

Features

Dropdown menu for switching between models
Notebook mode that resembles OpenAI's playground
Chat mode for conversation and role-playing
Instruct mode compatible with various formats, including Alpaca, Vicuna, Open Assistant, Dolly, Koala, ChatGLM, and MOSS
Nice HTML output for GPT-4chan
Markdown output for GALACTICA, including LaTeX rendering
Custom chat characters
Advanced chat features (send images, get audio responses with TTS)
Efficient text streaming
Parameter presets
Layers splitting across GPU(s), CPU, and disk
CPU mode
and much more!

Installation

There are different installation methods available, including one-click installers for Windows, Linux, and macOS, as well as manual installation using Conda. Detailed installation instructions can be found in the Text Generation Web UI repository.

Downloading Models

Models should be placed inside the models folder. You can download models from Hugging Face, such as Pythia, OPT, GALACTICA, and GPT-J 6B. Use the download-model.py script to automatically download a model from Hugging Face.

Starting the Web UI

After installing the necessary dependencies and downloading the models, you can start the web UI by running the server.py script. The web UI can be accessed at http://localhost:7860/?__theme=dark. You can customize the interface and behavior using various command-line flags.

System Requirements

Check the wiki for examples of VRAM and RAM usage in both GPU and CPU mode.

Contributing

Pull requests, suggestions, and issue reports are welcome. Before reporting a bug, make sure you have followed the installation instructions provided and searched for existing issues.

Edit on Github

Text Generation Web UI AI technology page Hackathon projects

Discover innovative solutions crafted with Text Generation Web UI AI technology page, developed by our community members during our engaging hackathons.

FDAi - Decentralized Autonomous Algorithmic FDA

🎯 Goal: Upgrade FDA.gov into dFDA - a decentralized platform that both automates clinical trials AND creates a living database of how everything affects human health. 🤖 The upgrade would transform FDA.gov to: Show you treatments ranked by real-world effectiveness for any condition Let you join trials instantly, get treatments delivered, report outcomes via phone Auto-schedule labs and track results Use AI to monitor safety and find patterns Anyone can share their diet, supplement, and health data AI analyzes the effects of every food, supplement, drug, and lifestyle factor Publishes real-time "outcome labels" showing how products change health baselines Learn exactly how combinations of foods/supplements affect specific conditions 💰 Benefits: Run automated clinical trials at 95% lower cost ($56M → $2.4M) Finally understand how everything we consume affects our health Make evidence-based health decisions using real-world data Companies can prove their products' actual health effects 🌐 Result: FDA.gov becomes the definitive source of truth about what works in human health, backed by continuous real-world evidence from millions of people.

Health Equity Explorer

The dataset consists of 907,464 members and their associated enrollment and services data. Processing the entire dataset using Pandas and Dask on my hardware, a Dell Inspiron laptop with 16 GB RAM and 4 cores, was not possible, causing memory allocation and out of disk space errors after minutes of processing. As a result, I decided to split the member dataset into groups of 100,000, in order of parquet file name in the original dataset. I called each group a "cohort". This resulted in 10 cohorts, the first 9 having 100,000 rows, and the 10th having the remaining 7,464 rows. I then analyzed each cohort separately and generated separate HTML reports for state, race, ethnicity, gender, and age comparisons, for a total of 10 reports per cohort, plus an additional report for providers by state. The analysis for each cohort takes several minutes but now could all run to completion on my laptop without crashing. With all 10x10+1 = 101 reports generated from the analysis, I wrote a web UI to display the reports. The user can select a specific cohort by number (from 1 to 10) or can expand all 10 cohorts to see their corresponding reports, or the providers report.

MindSight - AI-Powered Therapy Progress Tracker

The AI-Powered Therapy Progress Tracker revolutionizes mental health care by bridging the gap between therapy sessions with real-time data, insights, and progress visualization. This solution leverages cutting-edge technologies to streamline the patient-therapist interaction, enabling therapists to measure progress and identify critical patterns objectively. This workflow integrates multiple advanced tools and APIs to handle voice logs, text transcriptions, emotion recognition, and therapy goal assessments, ensuring a seamless experience for both therapists and clients. 1. Therapist Therapists play a vital role in the therapy process but often struggle with fragmented and incomplete data about their patients. Through the platform: • Therapists upload session recordings, which are analyzed for meaningful insights. • They review weekly summaries, patient progress, and emotion analysis to refine therapy plans. • With real-time updates, they gain a clear understanding of each patient’s journey between sessions. 2. Client (Patient) Patients often face challenges logging their emotions, triggers, and responses daily. The tracker simplifies this by: • Allowing patients to submit voice or text logs effortlessly. • Encouraging consistent engagement with reminders and user-friendly tools. • Presenting visual insights, such as emotion trends and progress graphs, to keep them motivated. ---------------- The Technology Stack Next.js • Role: Serves as the frontend framework, enabling therapists and patients to interact with the platform. 2. WebSocket • Role: Facilitates real-time communication between the frontend and backend. 3. Supabase • Role: Acts as the secure database and backend service for data storage 4. AssemblyAI • Role: Converts voice logs and session recordings into accurate text transcripts. 5. OpenAI • Role: Performs sentiment analysis, and therapy goal evaluation. 6. HumeAI • Role: Conducts emotion recognition and behavioral analysis.

Hawaii Health Risk Assessment System

The Hawaii Health Risk Assessment System is an AI-powered healthcare solution designed to assess individual health risks, focusing on cardiovascular, metabolic, and infectious diseases while ensuring health equity across diverse populations. By using a generative AI model, this system generates detailed risk reports based on user-provided information, facilitates appointment scheduling, and offers data-driven insights for public health administrators. The project aligns with the innovation criteria of Population Health, Public Health and Patient Safety, and Clinical Research, aiming to reduce healthcare disparities and promote preventative care. Flowchart of the System: User Input: Users provide their personal and health-related information via a form. Form Submission: Data entered by the user is submitted to the backend. Generative AI Model Processing · The system processes the submitted data using a generative AI model. · Outputs a Health Risk Assessment Report. Health Risk Report Evaluation Two outcomes: · No Risk Detected: Display health tips and lifestyle recommendations to the user. · Risk Detected: Navigate to the Health Risk Status Panel. Health Risk Status Panel: · Displays the risk detected. · Includes a Book Appointment button. Book Appointment Workflow: User clicks Book Appointment, opening the Appointment Booking Panel. Features: · Dropdown to select hospital. · Calendar to choose date and time. · Health risk status is auto-filled and displayed. Data Storage: User responses and health reports are saved in: · SQLite Database: For structured storage and analysis. · .json File: For backup and interoperability. Admin Dashboard: Connects to the SQLite database and JSON files. Provides: · City/state health trend visualizations. · Patient-level insights. · Data for clinical research and public health policy-making. This project aims to bring fair healthcare to everyone, connect remote communities with providers, and guide better health decisions.

Carpi IA

Con Carpi IA la idea es desarrollar una plataforma versátil y adaptable que pueda abordar múltiples sectores, como la salud, la industria automotriz, la industria gastronómica y la educación. La visión de Carpi IA a futuro consiste en entrenar modelos especializados para cada área de interés. Por ejemplo, en el ámbito de la salud, podemos entrenar modelos para detectar anomalías en imágenes médicas, mientras que en la industria automotriz, los modelos pueden ser entrenados para identificar fallos en piezas de vehículos. O en la educación que niños o adultos con problemas neurológicos puedan recibir información detallada de lo que están viendo.

cultAI

cultAI is an innovative AI-powered chatbot designed to bridge the gap between cultural heritage and accessibility. Serving as a virtual curator, it provides users with access to over 4,000 pages of rich content about artworks, leveraging museum collections like MASP and others. By applying Retrieval-Augmented Generation (RAG), cultAI ensures precise and engaging responses, connecting users to detailed information about art, history, and science. Targeting regions with limited infrastructure and cultural resources, cultAI addresses challenges like long travel distances to museums and technological barriers. Its features include personalized learning experiences, allowing users to explore collections interactively and receive tailored answers to their questions. Accessible via a simple mobile device and internet, it democratizes cultural education. With integration of virtual and augmented reality, cultAI transforms the learning process into an immersive journey. Museums can digitize and share their collections on the platform, expanding their reach and fostering greater engagement. Using a subscription model, cultAI offers sustainability while promoting cultural inclusion, revolutionizing how individuals connect with museums and their vast repositories of knowledge.