🌟 One-week challenge for AI founders on creating an MVP of your AI-powered product!
💻 The Hackathon is exclusively open to participants of The AI Founders Masterclass.
✔️ Explore Cohere's Generate, Embed, and Rerank endpoints, revolutionizing AI-powered applications.
🚀 Building the Future of Software with AI!

CzechPawel

root_sudo_su

Olesia Zinchenko

walaa2022

Donald Nwokoro

Muhammad Inaamullah

abdibrokhim

shebagi_mitra

sssandra

aaronr

luis_serrano

JayAlammar

Radical AIFMC x Cohere GenerativeAI Hackathon

StableHacks

shabscan

Arkimedes Team for the Radical AIFMC x Cohere GenerativeAI Hackathon. Lets build a great AI MVP!!

Arkimedes

dcarpintero

if you were looking for a description, I'll tell you a poem instead. 
That was the poem.

Amani Kiruga

FluidAI

MES_Fluid

MShahen

Join us as we kick off the hackathon with an opening address by Radical Ventures!

Radical Ventures Opening Address | Kick off

Luis Serrano will provide an introduction to Cohere, setting the stage for the hackathon.

Cohere Opening and Introduction

Get acquainted with the rules and guidelines for the hackathon.

Hackathon Rules of Engagement

Luis Serrano will lead a 45-minutes session introducing Generative AI, Semantic Search, and Reranking.

 Intro to Generative AI and Semantic Search and Rerank 

Join us for an office hour session by Radical Ventures.

Radical Office Hour

Make sure to submit your hackathon project by this deadline!

Project Submission Deadline

Judges including Aaron Rosenburg, Jay Alammar, Luis Serrano, and Sandra Kublik will evaluate projects asynchronously during the next five days.

Project Evaluation Starts

Tune in to the live broadcast where winners will pitch their projects, and the hackathon winners will be announced.

Live Broadcast: Winner Pitch and Announcement

About Cohere

Challenge

API Access

Cohere Endpoints

Radical Ventures

Quick Start

Details

Unleash the Power of Generative AI with Cohere: Transforming Ideas into Innovation.

The "Cohere-Powered Exam RAG Bot" is a cutting-edge educational platform for O Level Physics, leveraging Cohere's language models to aid learning. Cohere Embed transforms course notes into vector embeddings, creating a mathematical representation for quick information retrieval, with Qdrant ensuring a scalable vector database.

Cohere Generate, using the command-nightly model, responds to queries with contextually aware answers, simulating a tutor's assistance. Cohere ReRank refines this process, selecting the most pertinent documents to bolster the bot's response quality and speed.

At the core, Langchain weaves together document retrieval and natural language processing to form an intelligent RAG system, while Streamlit's interactive interface makes the AI accessible and user-friendly.

The app's market value stems from its innovative approach to personalized, tech-based learning. It stands out for its on-demand educational support, meeting the increasing need for accessible learning tools.

Future expansions include multimodal capabilities, enabling the bot to interpret diagrams and images, and multilingual support, broadening its user base. Plans to enrich the knowledge base and branch into subjects like Chemistry and Math will transform the app into a comprehensive academic resource. This growth trajectory positions the "Cohere-Powered Exam RAG Bot" to reshape e-learning globally.

This innovative RAG-based chatbot app leverages Cohere Embed for creating vector embeddings, Cohere Generate for AI-driven responses, and Cohere ReRank for enhanced retrieval, providing efficient and accurate solutions to O Level Physics queries.

Ayesha_Imr

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

Langchain

One of the best AI labs in the world. By using the Cohere platform we are able to use one of the best and most powerful language models for our own! There are many tutorials, including our own one, that show how to use Cohere.

Cohere

Cohere is a Canadian startup that provides natural language processing models that help companies improve human-machine interactions

Rerank offers a powerful solution for improving search quality without the need for an extensive overhaul or system replacement.

Cohere Rerank

Generate is powered by a large language model that has read billions of words, learning the patterns and idiosyncrasies of sentences. Using this knowledge, it writes content, predicts outcomes or answers questions at your command.

Cohere Generate

Turn text into numerical representations of language for deeper insights at scale. Embed makes it possible to algorithmically categorize and score text quickly to extract meaning.

Cohere Embed

Qdrant is a search engine and database designed for vector similarity. With its user-friendly API, it offers a production-ready service for storing, managing, and searching vectors, including an additional payload. Qdrant is particularly well-suited for neural-network or semantic-based matching, faceted search, and other applications that require extended filtering support.

Qdrant

Cohere-Powered Exam RAG Bot 

Voices is one of the main physical senses of a human being. Throughout history, serenades have been known to help move hearts. Using artificial intelligence to extract biomarkers or characteristics in voice can help improve matches. There has been more studies recently of vocal analysis by artificial intelligence to help detect diseases (cardiovascular, neurological, etc.) and we believe that voice can be used to help improve relationship chemistry.

For our project we looked to demonstrate from a prototype how we are training our model to best estimate what voices our user would "like." We used user inputs as well as shimmer, pitch, pitch variance, and harmonic to noise ratio to see if there were any patterns. In addition, we used Cohere's embeddings to help establish relationships.

In our analysis, we saw that Cohere's embeddings clearly was able to detect and distinguish between genders where user inputs clearly preferred one gender over another. We also saw promising relationships in vocal characteristics such as pitch, shimmer, and harmonic noise ratio where further training could help enhance accuracy.

Overall, the dating app is currently heavily weighed on appearance alone. Our app and project intends to change that. By studying further voice of existing couples/married relationships, we can further improve our model. There are also other biomarkers that are readily available that we can use in the future to improve model accuracy.

Please see our video demo here: https://www.loom.com/share/8ac63653b3c84ced8b8836fbf9c3cf3b?sid=24315fa5-6a20-4422-aec1-4a813516b06d
Please see our presentation here: https://docs.google.com/presentation/d/10vpRYgltNhEcz5yOhY6UK-9cK4PQkkBpQ5gudniXm3c/edit?usp=sharing


A dating app to help singles find their soulmate by using vocal characteristics and biomarkers

AI Voice

Tony Lau

Scientific Dating App

Note: A 3 page white paper is available upon request.

Organizations are losing valuable resources because they struggle to generate feasible innovation plans. Human ideation/creative problem solving is vastly constrained. Critically, teams typically only use 1-3 ideation techniques, have limited domain specific expertise, and have limited lateral knowledge for inspirational thinking. Ultimately, HBS research evidences that 95% of all product innovations fail and the McKinsey Global Innovation Survey reports that only 6% of executives are satisfied with their innovation performance.

AI, and Innovate AI in particular, can help by quickly iterating through the 60+ ideation techniques, and for each draw from unlimited domain specific and lateral knowledge - to generate actionable ideas in seconds.

 Innovate AI makes product innovation 10x faster and more actionable. 

The system works in three phases:
Problem & Goal Module - the system captures the comprehensive status quo/problem at hand, and desired innovation objective
Ideation Module - the system generates ideas using validated brainstorming techniques (our MVP uses 10; however future iterations of Innovate AI will incorporate more)
Decision Module - system assesses innovation feasibility and risk using standard criteria and any additional criteria requested by the team

Innovate AI is sold as B2B SaaS to Chief Innovation Officers at mid-large corporate organizations. Not only can core CSR departments benefit from the system, but the system can also be used company-wide to increase CSR efforts across the board. 

We are tapping into a $32B opportunity across the USA and Canada. 

We believe achieving leadership is attainable for multiple reasons. Most of our competition uses just one type of brainstorming technique. Our system will  draw on an exhaustive set of 60+ techniques and will, for the first time, leverage fine-tuned Gen AI to facilitate structured innovation.


InnovateAI helps organizations innovate core business offerings and corporate social responsibility strategy quickly and effectively by applying validated brainstorming techniques, expert and inspirational knowledge bases, and feasibility analysis.

InnovateAI

Arad Ashrafi

carrie_armel

evestazz

rahulkhandalkar

nlokhande7

InnovateAI is IDEO in a Box

Currently success rates for patents are 54% and 65% in the US and Canada respectively while filing costs are up to 15-20k per patent. With over 600000 patents being filed annually in the US (2019) and over 12000 in Canada, around 2.5 billion dollars is being spent on patent applications that end up failing. Furthermore, the process to file a patent is time intensive and requires legal experts and technical experts to collaborate to create high quality patents. 

Of the 600000 patents filed in the US, ~20% of are for inventions classified as deep tech in fields such as materials science, pharma, semi-conductors, etc. Patents in these fields are generally complex as strong expertise is required for prior art searches and for defining embodiments during patent generation. 

Current solutions are generalized to enable lawyers to perform prior art searches and to generate for fields of patents, however we believe there is an opportunity to build specialized tools specifically for deep tech fields where patent application costs are higher. 

Therefore we've started developing SciPat (scientific patents) a set of tools to help both lawyers and inventors in these spaces to perform specialized prior art searches and generate specialized drafts. To accomplish this we are developing a set of specialized models by fine-tuning cohere's generative model, embedding model and summarization model using field specific patents and literature while also providing the base functionality provided by other generative patent and prior art search tools. 



AI tools for prior art search, researching and generating patents for deep tech inventions such as drug molecules, new materials, medical devices, etc. 

Pickles and Jam

LiamMadly

KiranEdwardson

SciPat - Scientific Patents

Arkimedes is a conversational AI Agent, powered by the Cohere platform, and designed to bridge Enterprises with Global Talent. It is readily already in any mobile phone (and web) at [https://t.me/ArkimedesBot], providing a new way for enterprises to attract and to be discovered by top-tier talent. For individual users, it offers a conversational interface to answer questions about their career, and to find exciting job opportunities that align with their skills and professional aspirations. Key Features include:

- Starts in a narrow niche: Jobs within the AI and ML sectors at companies like Cohere, Waavi, Anthropic, Mistral, Lamini, and The AI Institute.
- Turbo Search: Implements an Ultra Fast Semantic Job Search - built with Cohere embed-v3, Cohere Summarize and a vector store (Weaviate).
- Chat Mode: Engage with a personal AI Career Agent to discover trending skills, scout companies in an area, understand salary scales, and get insights on the research topics companies are working on, and scout companies - developed with Cohere Chat grounded on our custom Connector.
- Custom Connector: Enhands the Command model with a knowledge-base of current Job postings - built with Cohere, this component supports composability enabling to build other Apps on top.
- Telegram Bot Integration (https://t.me/ArkimedesBot): Reduces friction to the minimum, and makes this AI Career Agent seamlessly available to over 550 million mobile users at one click.

Built for AI Founders/Radical Ventures Hackathon 2024

Conversational AI Career Agent built w/ Cohere for mobile and web, bridges enterprises w/ global talent. It helps users land their dream job. Features include a test dataset w/ jobs in AI/ML, ultra-fast job search, AI chat, and a custom Cohere connector.

Weaviate is an open-source vector database that enables you to store data objects and vector embeddings from your preferred ML models. Moreover, it offers smooth scalability for handling billions of data objects.

Weaviate

Consider the following: healthcare professionals spend 16 hours per week on paperwork and administrative tasks. One out of every five days is dedicated to post-consultation paperwork and referencing HCPCS codes for insurance companies. In the US, an inefficient administration and overhead in healthcare squander $600 billion annually, accounting for 30% of the total healthcare expenditure.

Leveraging Cohere's Summarize API and the Coral Chat API, along with OpenAI's Whisper model, Charting enables physicians and patients to record conversations during clinical visits or video call sessions. The Whisper model generates transcriptions by accessing the device's microphone, and then Cohere's Summarize API produces insightful bullet-point summaries of the full transcriptions. Another key feature of Charting is its Search function. Using Cohere's Chat API, physicians and patients can search the internet and obtain ad-free answers. To build trustworthiness, the top 5 sources of these answers, along with their original URLs, are displayed for further research.

Radical AIFMC x Cohere GenerativeAI Hackathon Summary

Hackathon Overview

Winners and Finalists

SciPat - Scientific Patents

Speakers, Mentors, and Organizers

Submitted Concepts, Prototypes and Pitches

Cohere-Powered Exam RAG Bot

Scientific Dating App

InnovateAI is IDEO in a Box

SciPat - Scientific Patents

Arkimedes

Charting