Oracle Game to access text completion as a service to play with mental states powered by I-ching

AI21 Labs Hackathon

AI21 Labs

aixing

Welcome to the Paul Graham Life Coach AI App! 🎉 This app brings the wisdom of Paul Graham—legendary entrepreneur, venture capitalist, and essayist—right to your fingertips. By leveraging AI-powered vector search combined with insights from his iconic essays, the app delivers witty, edgy, and profound advice, just as if Paul Graham himself were guiding you through your toughest challenges. Whether you’re seeking startup tips or life advice, AI Paul Graham is here to offer sharp, candid responses tailored to your queries
How does the app works?
- The app connects to a MongoDB Atlas database containing Paul Graham's essays. 📚
- When a user inputs a query, the app uses OpenAI embeddings to convert the query into a vector. 🧠
- MongoDB Atlas performs a similarity search to find the most relevant essay snippets based on the query. 🔍
- These snippets are then passed into a system prompt where the AI simulates Paul Graham's advice. 📝
- The response is returned in the chat interface, formatted in Paul Graham's unique style. 💬

Welcome to the Paul Graham Life Coach AI! 🎉 Get sharp, witty advice from legendary entrepreneur and essayist Paul Graham. Powered by AI and his iconic essays, this app offers candid, edgy guidance on startups, life, and everything.

Guardians of the Galaxy

Unleash the potential of Streamlit for rapid deployment of data applications.

streamlit

A powerful and flexible document-based NoSQL database that has gained popularity among developers.

MongoDB

OpenAI is an AI research and deployment company

OpenAI

ElevenLabs is a voice technology research company, developing the most compelling AI speech software for publishers and creators.

ElevenLabs

Paul Graham Founder Mode AI App

Learning Assistant named Laitent is built using AI ML Capabilities along with O1 Model's reasoning capabilities. We have used OpenAI's O1 Model, API Keys provided to us and it's reasoning capabilities to better help users learn things at different levels of difficulty and different stages of lives! This means we have simplified the prompt inputs with providing drop-down that tells users whether they want an explanation suitable to kids aged between 5-12 years or they want it for teenagers or they need answers/replies for adults with minimal knowledge, this subset categorization further helps user to reduce the needs for prompt engineering and get better responses from O1 Model which has reasoning capabilities according to the option chosen from  drop-down menu and this helps the user to learn things easily - be it simple daily tasks to complex tasks or coding concepts!

Learning Assistant named Laitent is built using AI ML Capabilities along with O1 Model's reasoning capabilities.

O1AI

The OpenAI o1 models, including o1-preview and o1-mini, excel in complex reasoning, making them ideal for research, advanced coding, and data analysis tasks.

Empower your projects with customizable language models, prompt precision, and extensive tool integration through OpenGPTs by LangChain.

OpenGPTs

Large language models (LLMs) have transformed the way we approach machine learning and artificial intelligence. These models are incredibly powerful, but their true potential lies in their ability to work in harmony with other sources of data and computation. This library has been developed to assist developers in building applications that combine LLMs with other technologies, allowing them to create truly intelligent and innovative products.

Langchain

Learning Assistant - Laitent

AI VoiceVision is an innovative public announcement system designed to revolutionize communication in public spaces. By leveraging ElevenLabs AI technology, this system converts text-based messages into lifelike audio announcements and generates AI-powered visuals displayed on large digital screens. The system is ideal for public transport, government offices, shopping malls, airports, and emergency services, providing a dynamic and engaging way to broadcast important information.With real-time text-to-speech conversion, language diversity, and customizable voice profiles, AI VoiceVision ensures that messages are clearly understood by diverse audiences. The AI-generated visuals that accompany the announcements add an additional layer of engagement, making the system both informative and visually appealing.

 cutting-edge public announcement system that transforms text into lifelike audio and dynamic AI-generated visuals for large screen displays using ElevenLabs AI technology.

NexusLabs

Simplify AI integration with OpenAI's Assistants API, empowering developers to create AI assistants effortlessly.

Assistants API

VoiceVision

Magic Bedtime Stories is the English version of our successful Swedish podcast, Magiska Godnattsagor, which has over 15,000 daily listeners. While the Swedish version is produced manually, the English one leverages AI and automation to create every episode. We chose to use AI and voice cloning because we’re more comfortable recording in Swedish, and this way, we can deliver the same high-quality experience in English without compromising on language fluency.

Here’s how it works: We receive voice requests from kids around the world via our website, where they share their unique story ideas. Using Make.com, we automatically retrieve these recordings and transcribe them with Whisper. The transcripts are stored in Notion, which acts as our central hub for organizing all data and keeping track of requests.

Our custom-built Flask app then takes over. It uses the transcript to generate a script with the help of Claude, and creates the full episode using cloned versions of our voices through ElevenLabs, including Aida’s—our AI co-host. Aida’s voice allows her to participate naturally in each episode, making her an integral part of the show. Each episode also features a fun segment where Aida presents five fascinating facts about a specific theme, designed to spark curiosity and encourage learning in our young listeners.

Once the episode is ready, the Flask app produces a summary for social media, and the final episode is automatically uploaded to Dropbox, making it available for release. The entire process is fully automated, enabling us to create personalized, high-quality stories that feel just as authentic as our original podcast series, with the added educational twist of Aida’s five facts in every episode.

Magic Bedtime Stories is a Flask Python app that creates AI-generated podcast episodes based on kids' voice requests from around the world. Using AI, voice cloning, and automation, we produce scripts, episodes, and social media content – fully automated.

Magiska

Claude is your friendly and versatile AI language model that can assist you as a company representative, research assistant, creative partner, or task automator.

Anthropic Claude

Anthropic’s Constitutional AI training approach research focuses on developing AI systems safe by design  and aligned with human values.

Anthropic

ChatGPT is a large language model trained by OpenAI to generate human-like text in a conversational style. It is a variant of the GPT-3 model, which was specifically designed to be used to generate text in response to user input. The ChatGPT model has been trained on a vast amount of text data, including conversations and other types of human-generated text, which allows it to generate text that is similar in style and content to human conversation. ChatGPT can be used to generate responses to questions, code, make suggestions, or provide information in a conversational manner, and it is able to do so in a way that is often indistinguishable from human-generated text. The initial model has been trained using Reinforcement Learning from Human Feedback (RLHF), using methods similar to InstructGPT, but with slight differences in the data collection setup. The model is trained using supervised fine-tuning, where human AI trainers provided conversations in which they played both sides—the user and an AI assistant. The trainers would have had access to model-written suggestions to help them compose their responses.

ChatGPT

Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification.

Whisper

Magic Bedtime Stories

Our project aims to deliver personalized financial advice through a user-friendly, AI-driven platform. By harnessing the power of OpenAI's GPT-3.5 and Whisper models, users can submit audio queries, which are then transcribed, analyzed, and answered with accurate, concise financial recommendations. The platform simplifies complex financial advice by converting user queries into actionable insights. Additionally, Eleven Labs' advanced text-to-speech technology ensures that responses are delivered clearly and naturally, creating a seamless voice interaction experience. Our mission is to make financial guidance accessible, intuitive, and engaging for users of all backgrounds.

This AI-powered financial advisor uses speech-to-text and voice generation to provide concise financial advice. Users submit audio queries and receive both text and audio responses, offering an interactive and accessible experience.

Tech explorer

The AI/ML API provides advanced features like text completion, image inference, speech-to-text, and text-to-speech with seamless integration and secure API key management.

aixing

Paul Graham Founder Mode AI App

Learning Assistant - Laitent

VoiceVision

Magic Bedtime Stories

AI-powered Financial Advisor

Paul Graham Founder Mode AI App

Learning Assistant - Laitent

VoiceVision

Magic Bedtime Stories

AI-powered Financial Advisor