Faran Taimoor Butt@faran_butt176

One of the difficulties of adopting RAG to a mass audience is lack of understanding of the underline NLP techniques required to produce good queries. With this tool, there is an AI agent that looks at the query and the results to help the user make better queries in the future. For example, If the user never used RAG before, they may ask a vague question. The agent will pick up on this and inform the user. In addition, it will provide suggestion of how to query for better results. This tool is general enough to be easy to adapt with already established RAG pipelines, in addition it is agnostic to data meaning it could be adopted to many fields.

We present our solution Lec2Learn that works on Finetuning open source learning data for providing learning objectives. We start by obtaining all textbooks from opentextbookbc, we Process HTML to obtain the lecture and learning objectives, We then have pairs of lectures with their corresponding question groups, On the server we use Microsoft Phi 1.5 model and we fine tune it, We fine tune on the opentext data which is used so that model gets better at generating learning objectives, For the Prompt we give the lecture and learning objectives, we always start with Describe so model does not generate random data.

Begin by choosing from a vast array of languages. With a simple click on "Get random sentence", you're presented with a phrase or sentence that'll challenge your translation and pronunciation capabilities. Take a moment, translate the sentence in your mind, and then confidently speak it out loud in English using state-of-the-art microphone integration. "Did you make a mistake?" No worries. With our "Hear correct translation" feature, you can both listen to and visualize the accurate English translation, ensuring you learn and adapt. Ready for another round? Just hit "Get random sentence" and continue your linguistic adventure. Language Lab isn't just another translation app; it's your personal gateway to mastering the English language.

We have used Clarifai for image recognition, we give user the option to upload image and the AI can generate prompt according to the image it recognizes, based on that it generates music prompt to be passed to Musicgen for generating Music. Currently, with the MusicGen environment we have it takes approx 20 seconds - 22 seconds to generate music. The audio output we kept is upto 6 seconds for the user to hear it and download it. We also have an option to detect and recognize live webcam feed, the AI will generate prompt according to the image recognized and will generate prompt for MusicGen to generate music. In addition, the user can also simply write the prompts on their own to generate music.

We have created an extension named IntelliSum that uses LLama2 and Clarifai for Intelligent Summarization and extraction of text from a given URL, using Stable Diffusion it can also generate AI Prompts and Images for given prompts. We have made this extension that is compatible with browsers and helps users to generate summary of texts, extract arguments from a piece of text, generate AI prompts and generate images according to the AI prompts. We have used technologies like JavaScript, Python, Llama2, Clarifai and other web technologies for creating this extension, we further in future want to extend our scope to fake news and fakeness detection in articles and AI Assitants

This app lets the user automatically scrape websites by letting Stablecode generate JavaScript code to parse a part of the HTML and convert it to a CSV. Here is how our app works: The user enters a URL and the app returns the page's HTML. The user can then tell the AI where the data is located, and Stablecode will then write javascript file to parse the HTML and convert the relevant part into a csv. We are taking inputs from the user, that input will be HTML link that user wants to scrape and parse, we have the option given to user to select an element and write a prompt accordingly to scrap and parse that element from the given HTML link. Stablecode will generate JavaScript code to parse part of HTML and convert it into CSV format. This will help users to scrape websites and get JavaScript code for the selected element as well as the Downloadable CSV format code for the selected element.

Our idea is to use AI, ML and open source technologies to revolutionize the healthcare fields - specifically Mental Wellness and Eye Care using Autonomous AI Agents. These Autonomous AI Agents are using SuperAGI and deployed on AWS. We have given the choice to users on our landing page to use Eye Health or AI Therapist for their purposes. The Eye Health uses Eye Care AI Agent to track blinks of users and let them know how their eyes are and what is the blink status of their eyes using real time live webcam feed. This will help to notify users and recommend them best strategies for eye care and early stage detection and prevention from diseases like Dry Eyes Disorders. We have the AI Therapist that uses Mental Wellness AI Agent to track the moods of the user from a live webcam feed and the SuperAGI helps in replying to users based on the mood track what they should do in order to be in a good mood, this helps users to track real time their moods and get some suggestions from AI Therapist. People of all ages have the tendency to have long working hours and exposures to screens and devices. These causes issues for eyes and also mental health gets affected due to such behaviors, mental wellness and some basic guidance as initial steps for healthcare can be provided by the AI Therapist and that can help users to track their mental moods, in future we can also allow them to have chatbots and have conversations with AI Therapist and Eye Care Agent. Eye Care Agent can help in tracking blinks and how good their eye health is and can suggest if their blink count per minute is less than 12, it can suggest the users to have some time off, do exercises, take a break, engage in healthy activities and take care of themselves. Screen time and usage of users can also be tracked and it can help to suggest users what steps to be taken in terms of productivity, creative and efficient parental controls, gaining better leverage on data using insights from AI & ML

Voice Out is a revolutionary AI translation assistant that aims to solve the problem of inaccurate and ineffective communication between people from different linguistic backgrounds. In today's globalized world, communication is essential, and language barriers often cause misunderstandings and hinder productivity. Traditional translation software requires the user to speak with high accuracy and clarity to ensure a correct translation, which can be difficult for non-native speakers or in noisy environments. Voice Out uses cutting-edge deep learning algorithms to analyze the nuances of a speaker's voice, identify commonly used phrases, and provide accurate translations in real-time. This enables users to express themselves naturally, even if their grammar or pronunciation is not perfect. Additionally, Voice Out's intelligent learning capabilities allow it to adapt to a user's unique voice and vocabulary, making communication more seamless over time. Voice Out's user-friendly interface displays translations in real-time, allowing users to adjust their speech or ask follow-up questions. It also has the ability to translate both spoken and written language, making it a versatile tool for a wide range of communication needs. With Voice Out, individuals and businesses alike can communicate more effectively and efficiently across language barriers, unlocking new opportunities for collaboration, understanding, and growth.

With the technological leap in generative AI, there are countless new businesses and startups which are using AI image generation in their pipeline. A non significant amount of these ventures can get supercharged with the ability to convert their 2D images to immersive environments and 3D objects A simple and intuitive tool to produce immersive 360° views using Dall-E 2 API as Proof of Concept Further iterations include integrating this with unity engine so the immersive environment can be manipulated and populated with 3D objects like in a video game. This use case has been verified by our first customers and by the industry leader StabilityAI.

🚀 Tap into OpenAI's models for diverse app needs: text and image generation, text-to-speech, vision, and more! 🧑🏻‍💻 Go one step further. Get your application ready for production using TruLens evaluations! 🤝 Work in teams of 1 to 6 members, fostering community connections! 🏆 Prize Pool: $2,500 in Cash and $2,500 in Portkey Credits! 💡 Extend beyond the Hackathon—build your startup with support and opportunities beyond the initial project.

Step into the future of AI: Experience and innovate with the cutting-edge Gemini AI model. First-hand Experience: Dive into the latest AI technology with Gemini AI, right after its release. Elevate your AI knowledge and coding prowess in a stimulating and supportive atmosphere. Team up with like-minded innovators and tech enthusiasts. You can work solo, or in a team of up to 6 members. Enhance your LLM apps with TruLens: Use sophisticated evaluation and performance tracking tools for superior output quality. Note: Dates may change if the Gemini AI model release is postponed by Google Cloud.

Revolutionize AI with TruLens by TruEra - Your Gateway to Building Better LLM Applications! Build with TruLens, LLMs development and explainability tool by TruEra Leverage AI observability for dynamic app enhancement Collaborate with like-minded individuals! For the Hackathon you can work in a team from 1 to 6 members. In this Hackathon, you can also join with a project from the TruLens 48-Hours Hackathon, provided you adhere to the following rules. Consider it a warm-up, and explore the world of technology by participating in the TruLens 48-Hours Hackathon.