Butter is an AI-based integrated chatbot that utilizes specialized speech-to-text conversion to accurately output messages from live voice recordings for individuals that stutter, and answer personal questions regarding stuttering. Butter implements the state-of-the-art Whisper API created by LabLab AI to intuitively translate speech into written form and omit any unintended interruptions in their flow of speech. Our goal is to empower and improve accessibility to communication to users with speech impediments.

OpenAI Whisper Hackathon

Boss

GPT-3

OpenAI

Codex

Whisper

Butter

Using Vectara and Llamaindex we process tabular data using multiple models to get extremely accurate recommendations. Our solution can scrape product information from any e-commerce platform such as Amazon, Walmart, eBay, etc., and use RAG to incorporate customer-specific preferences to find out the best suitable products for price, features, ratings, etc. 
The solution facilitates the hybrid search mechanism i.e. keyword as well as semantic search capabilities. It also supports summarization for products e.g. concerning sales, trends, revenue, etc.
The next steps are using a voice-enabled chatbot, and an alerting mechanism with product search across internet. 

The idea is to compare products on Amazon with respect to price, ratings, and customer preferences.

RAGistan

RAG-as-a-service API-driven generative AI platform.

Vectara

LlamaIndex connects data sources to large language models, providing tools to ingest, index, and query data for building powerful AI apps augmented by your knowledge.

LlamaIndex

Shop GINI

Edulance is an open-source project that utilizes advanced technologies such as Unstructured, machine learning models, and APIs to transform text documents and PDFs into interactive educational resources. The software accepts user-uploaded files, applies optical character recognition (OCR) for text documents, or extracts valuable content from PDFs. It then generates lessons, quizzes, and lesson plans based on the content using its Lesson Graph model and agents like LessonGenerator, LessonPlanner, OCRAgent, PdfAgent, QuizAgent, and TogetherLLM. Edulance provides an immersive learning experience, enabling effective teaching and interactive knowledge acquisition.

Overall this project incorporates the following:

TogetherAI's LLM Models
Unstructured Partition pdf for making PDFs LLM Ready
Agentic AI with state management.
Features
Feature	Description
⚙️	Architecture	Edulance is a Python-based project using FastAPI as the web framework and Uvicorn for runtime serving. The application leverages containers with Docker for deployment, installing required dependencies from requirements.txt. It utilizes libraries like LangChain, PikePDF, PyTesseract for OCR, and TogetherAI's LLM models.
🔩	Code Quality	The codebase follows a modular structure with clearly defined agents and graph files, ensuring high cohesion and low coupling. Python style guides are followed consistently, including PEP8 and PEP534. There is adequate usage of comments throughout the codebase.🔌	Integrations	Key integrations include Docker for deployment, LangChain libraries, TogetherAI's LLM models, Vectara for Chat.
🧩	Modularity	
📦	Dependencies	Main dependencies include FastAPI, Docker, Python 3.10, requirements.txt, LangChain package, PikePDF, PyTesseract, and related tools.


Edulance: Open-source tool using ML, OCR, and APIs to convert text/PDFs into interactive educational content, creating lessons, quizzes, and plans.

Edulance

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

Assistants API

OpenAI is an AI research and deployment company

Empower your workflows with tailored AI models. Custom GPTs offer versatile solutions for personalized tasks and seamless integration. Create, customize, and share your GPTs effortlessly.

Custom GPTs

Discover the power of Together AI and empower AI innovation together!

Together AI

Unstructured IO

Edulance-AI


The onset of the 5G era signifies a profound shift in telecommunications, heightening the necessity for components capable of handling high-speed signals with minimal attenuation. One significant challenge lies in the inadequacy of the length and material of measurement probes within AP chips, HPC, and automotive technology to meet the surging demand.

Our innovative approach addresses this challenge by reducing probe lengths and enhancing electrical specifications. Targeting the probe card industry, where probes play a pivotal role, our solution distinguishes itself through the integration of an automated system to identify key alloy characteristics valued by customers, thus aligning with market demands. This not only ensures compliance with 5G requirements but also augments probe durability and performance.

The distinctive advantages of our approach encompass heightened measurement accuracy, minimized signal degradation, and prolonged probe lifespan, collectively generating significant value for manufacturers. Furthermore, through thorough analysis of current trends, we have identified opportunities for collaboration with material suppliers.

Such partnerships have the potential to drive the development of novel, superior materials, thereby expanding the commercial viability of our probes into broader markets. This positions us at the vanguard of innovation in the probe card industry, poised to meet the challenges of the 5G future.


The chip testing industry faces challenges in probe design due to rapid product iterations and increasing pin counts.

MaterialSupport

Our project is designed to empower lawyers by revolutionizing the process of legal research and case preparation. By harnessing the capabilities of a sophisticated legal language model (LLM), our tool aims to streamline the tedious task of finding relevant precedents. It does so by intelligently fetching similar cases and highlighting parallels, thereby assisting lawyers in constructing a robust and logically coherent argument for their cases. This innovative approach not only saves valuable time but also enhances the effectiveness of legal strategies, ensuring lawyers have a formidable foundation for every case they undertake.

Our project is designed to empower lawyers by revolutionizing the process of legal research and case preparation

Casuals

PleadSmart

EquaCare is a digital health assistant designed to increase positive health outcomes among neurodivergent patients by helping them navigate the complicated healthcare system with ease. 

EquaCare helps users schedule and prepare for doctor visits, track appointments and medications, and understand medical benefits and diagnosis. 

EquaCare leverages generative AI to provide real-time responses to the patient's most pressing questions and has been trained to be neurosensitive
This means it follows communication standards that accommodates the learning styles and language processing levels of the patient, such as using active rather than passive voice, avoiding double negatives, and writing in simple clear language using everyday words.

Providing equal access to healthcare for patients who find social interactions challenging