Cohere Hackathon Summary

Semantic Assist is a dynamic Chrome extension in Javascript and Backend logicin Python Flask server, that will help you to find your target paragraph in any Article and highlights it so you will not have to read the whole article and waste your time. We are using Cohere's Multilingual Embedding model which can also find your target paragraph when you write your query in any other supported language. Apart from that you can also get the video started from your target concept and not waste much time listening to other not useful things on the Video. The Chrome Extension will automatically detect the platform (Youtube/Any articles) and will work accordingly, you will not have to change even a thing just browse like you normally do and hit (Ctrl + Shift + k) and enter your query and hit the button and your video will start form the answer to that query or the article will point to the highlighted text. Keeping the Usability and short attention span of people, to use this application you do not need to move to any other website/application (which most of the solutions are till now) just stay on your current window and hit the shortcut for a prompt to appear and enter your query and let the Chrome Extension do its magic. We also save the embeddings so for request for the same URL the response is very fast and user can have a great experience will less delay imitating real case

Kraken

Psy-Q Bot is an AI-powered chatbot that provides psychology-related information and resources to users. The development of the bot was guided by the goals of creating a product that is both useful and easy to use, and leveraging the capabilities of Cohere's API as much as possible: we use both generate and embed. The system is composed of a web client built using React and a server that provides centralized access to Cohere. The key component of the application is Cohere, which is used to analyze user questions, match them with relevant sources in the dataset, and generate responses. The Embed endpoint of Cohere is utilized to analyze and compare questions, while the Generate endpoint is used to generate responses and improve the custom Cohere model. The dataset used by the bot has also been partially augmented using Cohere's Generate endpoint, allowing for continuous training and refinement of the model.

The Incremental Experience

Coherent Fox is an audit generator for Python code based on pre-trained BERT model. It is done to have a Powerful NLP Model based on Attention mechanism. We have build our own transformer from scratch. We have focused our training on a Python Code DataSet from Hugging Face. The idea is to provide a transformer that been built through main attention scores which are identifiers and separators from the study done on Java, from BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. We provide in the back-end Cohere API that will generate a response to a user prompt through our interface. We are a team of two full-stack devs with Experience in ML & Blockchain also.

Coherent Fox

Jason AI is your personal assistant powered by Cohere API to set up outreach sequences, handle prospect responses, and book meetings for you. Most of the time we lose potential clients because of wait time. Since Jason AI will be able personalize answers to respond to questions and address potential concerns, we believe the lead conversion rate will be increased significant. JasonAI will allow your business to grow exponentially. Since it can handle unlimited number of leads and interactions. JasonAI can handle many of the same tasks as a human SDR, saving resources for your business. So you can focus on delivering better products.

JasonAI

There are three essential components in the model: ‎1. Co:here Classify model that has been trained on almost 500,000 real training data ‎‎(sentence, emotion) and is capable of using NLP to truncate and classify large ‎prompts into a range of emotions. ‎2. Co:here Embedding + Sklearn model that transforms the user prompt to a list of ‎floats (embeds) and performs semantic search in a massive data base of real, ‎labeled, embedded sentences to find the closest matching example.‎ ‎3. Co:here Generate model that receives user input, classified emotions, previous ‎calls, and some hard coded psychological information to generate an accurate ‎therapist response. The model has memory of past inputs and thus can create a ‎coherent conversation.‎ These components work together in the back end, while the front end is a webpage ‎that user can access to send information and read model's responses.‎ Ultimately, the project aims to create an ongoing conversation with Co:DY and user, ‎providing emotional support, helping users work through problems, and offering ‎tailored advice.‎

The Cyber Savvy Ninjas

Understand yourself better through stories of yourself from 'alternate reality'. A language model learns about your personality and tell you about a story that can help you understand yourself and your decisions in life.https://github.com/mube1/insight Understand yourself better through stories of yourself from 'alternate reality'. A language model learns about your personality and tell you about a story that can help you understand yourself and your decisions in life.https://github.com/mube1/insightUnderstand yourself better through stories of yourself from 'alternate reality'. A language model learns about your personality and tell you about a story that can help you understand yourself and your decisions in life.https://github.com/mube1/insightUnderstand yourself better through stories of yourself from 'alternate reality'. A language model learns about your personality and tell you about a story that can help you understand yourself and your decisions in life.https://github.com/mube1/insightUnderstand yourself better through stories of yourself from 'alternate reality'. A language model learns about your personality and tell you about a story that can help you understand yourself and your decisions in life.https://github.com/mube1/insightUnderstand yourself better through stories of yourself from 'alternate reality'. A language model learns about your personality and tell you about a story that can help you understand yourself and your decisions in life.https://github.com/mube1/insightUnderstand yourself better through stories of yourself from 'alternate reality'. A language model learns about your personality and tell you about a story that can help you understand yourself and your decisions in life.https://github.com/mube1/insight

Yesew team

Large language models (LLMs) are emerging as a transformative technology, enabling developers to build applications that they previously could not. We have used Cohere.ai developed models to create a web application using stramlit library for many known script generations like movie script, song lyrics, story generation, poem generation, blog post generation In our current situation we offer a unique platform for creative expression with three distinct functions: writing poems, stories, and posts. It provides users with a convenient and user-friendly interface to unleash their imagination and bring their creative ideas to life. ​

Neural Ninjas

The modern music landscape is dictated by viral trends. The most successful artists are the ones most capable of repeatedly generating some "buzz". Viral hits have given the opportunities to up-and-comers to rise-up and bring new flavors to the market! In this world, artists want to be able to know both "what is trendy right now" and "where is there room for originality"? Are those realistic questions to ask? I'd say yes! With the increasing amount of algorithms used by media diffusion platform (Spotify, YouTube, TikTok, etc.), a good analysis of "what works" in these environments can give you a competitive edge. OneMusic is a platform that aims to fulfill this objective by allowing artists to inspect the audio and lyrical features of songs on the hitlist! pulls from Spotify's "Top 50" playlists for all countries

OneMusic

Scrip2life is a new tool that utilises Co:here’s Large language model to save time by breaking down movie scripts and generating summaries, character traits, and backstories for actors to use as inspiration while preparing for their upcoming auditions. Our goal is to improve their odds of finding and landing suitable and inspiring roles to portray stories for the viewers. We achieve this by streamlining the script comprehension using ai tools, so that actors focus on always standing out with the depth of understanding and world-building they manage to portray through the limited amount of preparation time before an audition or role. Our solution is validated by Deepmind’s discussions with industry Professionals evaluating their co-writing system, Dramatron. The writers expressed they would rather use the system for “world building,” for exploring alternative stories by changing characters or plot elements, and for creative idea generation than to write a full play. We focused on building scrip2life based on this market validation with the additional advantage that it is accessible to everyone, not just theatre professionals. Our MVP targets budding ad working actors who are looking for ways to save time while applying to hundreds of casting calls throughout the year. We additionally provide inspiration to be immersed into their characters and script for upcoming auditions and roles. Scrip2life was written collaboratively in Replit IDE. The frontend is written in html, css and js. We used flask to bring the code to life, enabling the calls to the cohere api. We prioritised the co:here generate api due to the creative nature of Scrip2life.

we-r-artiste

This bot is capable of automation of interview stages in which respondent is to answer questions with firm correct and wrong responses. Bot will communicate with interview respondents via web-application.​ This application will be like chatbots used on sites to help students and other scholars write academic papers. Bot sends question to the candidate and a person input answer in the provided field.​ Afterwards, model estimates the quality of provided answer and bot informs respondent about it.​ Our model utilizes https://api.cohere.ai/classify endpoint.​ The set of questions available to choose from is in the database and predefined (for this version of project).​ The training sets of answers are also in the database with links to their respective questions.​ There must be at least some number (to be estimated) of answers per quality per question for the model to be well-trained.​

Pampushka

With an automatic script breakdown interface and a script AI assistant, our platform empowers producers and writers throughout the pre-production workflow, enabling them to focus on creating amazing content. Script breakdown is an important part of the filmmaking pre-production stages for scheduling and budgeting. We will automatically create the script breakdown with all the categories you need: Cast, Props, Locations, Makeup, etc. Taking to few producers from Netflix and huge production houses, we realised traditional script breakdown software is an absolute chore, and don't even get us started on the script breakdown sheet templates that line producers and assistant directors have to print and fill out by hand. Breaking down a screenplay doesn't have to be a bummer. Script breakdown, understanding, and scheduling should become more accessible, accurate, and intuitive with cutting-edge AI solutions, saving numerous man-hours and introducing structure and best practices to the pre-production workflow.

Cinematix AI

TubeTalk is an application that helps any YouTube content creator to better understand their community and understand how their viewers interact and what they think about the videos they post. The application automatically identifies topics of discussions in the comment threads of a video as well as making sure to remove any comments that are rude or harmful. The application also allows the content creator to go in-depth into the contents of his video's comment section by asking open questions and get back the comments that would best fit his question. The application is built on top of Cohere's language models as well as embeddings generator. Dive into our application and get better insights from your video's comment section!

LastMinute

Smart Study is a cutting-edge web application designed for students, teachers, and anyone looking to enhance their learning experience. The app provides a unique and convenient way to test and evaluate your understanding of a specific topic or YouTube video. By generating multiple choice quizzes, users can quickly and easily assess their knowledge, retain information better, and identify areas that require further study. The app's interface is user-friendly and intuitive, making it easy for anyone to get started. To generate a quiz, simply input the text content or provide a link to the desired YouTube video. Smart Study will then extract the most important information and create a comprehensive quiz, complete with multiple choice questions and answers. This makes studying for exams, completing homework assignments, or just keeping your knowledge up-to-date more efficient and enjoyable. One of the most significant benefits of Smart Study is its ability to personalize the learning experience for each user. With the app's adaptive learning technology, the difficulty level of the quizzes adjusts based on the user's performance, ensuring that the user is always challenged and engaged. As a result, users can make faster progress and retain information better.

Seeker

This project aims to provide users with a realistic interview experience, thereby boosting their confidence. By simulating real-life interview scenarios, users will get the opportunity to practice and perfect their interview skills, including answering questions, body language, and overall demeanor. Additionally, the project will also help users overcome their anxiety and nervousness, allowing them to perform at their best during actual interviews. This project will be beneficial for job seekers, students, and anyone looking to improve their interview skills. With a focus on helping users achieve their goals, this project will provide an engaging and supportive environment that will encourage users to achieve their full potential. By the end of the project, users will leave with a renewed sense of confidence and the skills they need to succeed in any interview setting.

Confidence Builder with AI

Project Peace is a Multilingual Text Detoxifier. It is an innovative solution to identify and neutralize toxic or harmful language in written text. It utilizes advanced AI algorithms powered by Cohere’s multilingual models to understand and analyze text across multiple languages, and flag potentially toxic language, including the ability to convert that toxic language into neutral and non-toxic one. Project Peace’s ability to process text in multiple languages, allows it to address the problem of toxic language on a global scale. Project Peace can be integrated into online platforms, such as social media websites, online forums, and online communities, to help prevent the spread of toxic language and promote a safer online environment. It can be used by businesses and organizations to monitor and control the language used on their website and even in their customer care services. It can also be used by governments and public institutions to monitor and control the language used in online communication channels and to promote social harmony and inclusion. It can be used by educators and schools to help prevent bullying and toxic language in online learning environments, ensuring that students have a safe and supportive learning environment. private individuals as well who want to promote a safer and more inclusive online environment, or who want to ensure that the language they use online is respectful and non-toxic. Project Peace has an appealing future by its scalability and customization. By integrating it with the existing social platforms, it can be made accessible to a wide range of users. Moreover, it has the potential to become an industry standard for detecting and detoxifying toxic texts. The goal of the project remains to create a safer online community by reducing the spread of hate speech, cyberbullying, and other forms of harmful language.

Project Peace

notifAI, a note-taking assistant powered by Artificial Intelligence, is a practical tool for students, teachers, or anyone that needs to read and understand large amounts of text. It can be challenging to process complex paragraphs of information, which is why we made notifAI. Using it is as simple as opening the app and taking a picture of the text, and the user will have access to an easy-to-read summary and main ideas. This is made possible with Cohere's large language model for summarizations as well as the Google Cloud Vision API to translate images to text. With this tool, we hope to help others understand the world around them efficiently and effectively.

ABG Hunters

Patients with disabilities or difficulty to hold conversations with a therapist, or with high levels of ADHD may prefer to perform therapy entirely on in parts by text, or text to speech. Colink:Therapy allows patients to do that, and have access to therapy's chat history. Psychotherapists, and counselors guide the therapy session with through a premium-subscription Analytics Panel only visible to them (not the patient), where they can obtain insights of conversation such as sentiment analysis, raised flags, and speech-to-text options for transcribing audio to text in case normal audio conversation happens. Colink:Therapy saves time for the Therapist, especially for children therapy, as their parents often need to be updates before or after sessions to keep them in the loop about their children's treatment. Therapists often need to provide a summary of sessions to their patient's parents, which is very time consuming. Colink:therapy may turn this into a few seconds task, one-click away, powered by Cohere:Generate's xlarge model's text summarizations. We aim to become the default hub for therapists to do more in less time with wholistic control of their present session and all previous ones.

UCC Team

What problems are we trying to solve? People are generally struggling with day-to-day living. Typical well-being structures are cost and time prohibitive. People are missing opportunities to improve because of disconnected systems. What’s our solution? A low-friction mobile application tailored to users unique interests. A conversational experience similar to that of a friend, accountability partner, or licensed practitioner
 A programmatic method to connect what they say and actions they need to take. What makes us unique and valuable? Interconnected systems that cut through the burden of organizing your daily actions Overall, it’s a more cost effective solution as it combines multiple solutions together (journaling, virtual assistants, therapists/life coaches) 
 Low barrier to entry, minimal effort required from the user, no subscription model that gates features Fast feedback loop Who is this product for? Young Adults 18 - 25 that are tech savvy and are looking to improve themselves but cannot afford professional services
 Adults 25 - 45 that cannot commit time or effort on a professional service but understand its value
 Introverted individuals who are self-sufficient or self-reliant but don’t have a strong accountability system

Ahmed - Chan Enterprise

We have created a service AI NLP model aimed towards customer service. By using the cohere API, companies can save money and time while providing top-notch customer service to their clients. This model uses advanced natural language processing algorithms to understand customer queries and respond accordingly. It can handle a wide range of customer queries, from product-related questions to technical issues, thus reducing the workload of customer service agents. In addition, the model can be fine-tuned and trained to suit the specific needs of the company, ensuring maximum efficiency. By using this innovative technology, companies can significantly improve their customer service operations while simultaneously reducing costs and boosting customer satisfaction.

AI Assistants

Newsboy is an AI technology that parses the data from different news outlets around the world and process them through machine learning so that users can search for news and facts in a disruptive way. The main objective of this project is to democratize the access to information and help fight misinformation, fake news and sensationalism by providing users with a language model that process and analyze the data obtained from the main news outlets in the world and deliver them through a search query that is able to interpret different levels of sentiments and parameters input by the user. - Informed Newsboy: The software will provide an up-to-date and comprehensive summary of the world's news. - Time savings: The software will automate the process of analyzing news articles, saving time and resources compared to manual data processing. - Toxicity & Stereotypes: The software will be able to filter news articles that are classified as negative information in different aspects - Machine Learning: The software will be able to understand the profile of its users and deliver personalized results - Increased insights: The software will provide a comprehensive summary of the news, giving users a broader understanding of current events and trends. - Customized data analysis: Users will have the ability to customize the data analysis process to focus on specific topics or geographic regions. - Data visualization: The software will provide data visualization tools to help users easily interpret and understand the analyzed news data. This will allow users to identify patterns and make informed decisions based on the information presented.

Sentient AI

JobAdvocate is a cutting-edge AI-powered platform designed to help job seekers streamline their job search process. With its custom cover letter generator and email generator, JobAdvocate empowers individuals to create compelling and personalized job applications that stand out from the crowd. The platform uses advanced algorithms and natural language processing to analyze job descriptions, identify the key requirements, and generate a custom cover letter that highlights the individual's relevant skills, experiences, and achievements. The email generator takes this one step further by composing an eye-catching email that effectively conveys the cover letter and resume to the hiring manager. With JobAdvocate, job seekers can save time and effort by automating the application process, and increase their chances of landing their dream job by presenting themselves in the best possible light. Whether you're an experienced professional or just starting out, JobAdvocate has everything you need to streamline your job search and succeed in today's competitive job market.

PakDev

Our goal is to develop a system that can take documents in any language and allow users from different parts of the world with different languages to interact with those documents. This can help spread knowledge without any language barrier. We are first testing it out with Quranic text, which is in Arabic, and building a chatGPT-style bot for question answering. In future, we would like to expand it to additional documents in any language. We first perform embedding of the text using Cohere's multilingual embed model and save those embeddings in a vector database, Pinecone DB in our case. We then take user queries and also embed them and perform a similarity-based search to provide the most relevant results based on the query. The app is currently deployed and publicly available. Streamlit app link: https://taqihaider7-tafsir-quran-sementic-search-llm-app-fwh2if.streamlit.app/

Menlo Park Lab

Usually firms have excess liquidity from their operations and people have savings that want to invest so that they can protect themselves from inflation or to generate a passive income. The problem is that in order to invest in the financial markets they either have to hire an specialist or they need to manage their investments themselves and this can expose them to high risks since they aren't usually experts on the field. There have been cases of companies even going into bankruptcy for preciselly investing in the financial markets with poor management or little understanding of the complexity of the markets. Here's where we come in, our solution powered by AI enalbes firms and people to invest in the financial markets without having to hire an expensive investment manager or having to learn themselves. It is a virtual portfolio manager. First the user has to provide financial information and a news or article related to him, with this an ML classifier using the Cohere API determines the risk profile of the user. With this information the platform generates a tailored portfolio, out of a selected financial asset universe specific to each risk profile. The available assets vary between different types of US stocks, FOREX pairs and even cryptocurrencies for the more risk taker profiles. Once the portfolio has been created it reports an overview of its composition as well as a backtest of its performance on the market. At this point the user has the option to decide whether to pursue a passive portfolio management strategy or an active one with just the click of a button. If he prefers a passive strategy the platform will take positions for a classic buy and hold strategy of the selected assets. If, in contrast, the user selects the use of trading bots then he will opt for an active portfolio management and trained DL bots will be buying and selling the assets at convenience for a better portfolio performance.

FINXAI

We track emotional states within text, then we provide a recommendation or simply show an ad that is suitable with what the user really feels. This project is using many  machine learning algorithms to train a classifier. We deployed cohere embedding system API. The backend service was built using python django framework. The motivation behind this work is that a big share of people spends a long time online, and although they express their negative emotions freely, they don’t actively take action to improve them. Even when they have positive emotions, they don’t make use of their excitement and energy. On the other hand, many local activities and services are available out there, but not everyone knows about them. Besides, the truth is that a single type of activity isn’t suitable for all. So, a strategy must be followed to recommend a specific activity to people with a specific type of emotions. Many companies and organizations will be interested in advertising, especially the ones that offer life coaching services, trip organizers, fitness and massage centers, comedy shows, therapists, and many other activity organizers and human well-being services.

ASU-FITers

NegotiazeAI is a web based product for businesses to help increase their sales through negotiation and keep customers interested in the product. We used the Cohere API which generates more information about a product so that customers can stay engaged into buying it. The front end for this product was built through Javascript and CSS, meanwhile the backend was built through Python. Members of the team, Kudos was in charge of the product management and presentation creation. Dimitrije helped in all sorts of ways, exploring ideas, backend product development, graphics design and even helping with the presentation. Ahtesham was the genius behind the beautiful front end. He used CSS and Javascript to create a beautiful front end of the product for customer use. Kevin is a crucial member of the backend team. He helped in programming the backend and debugging it. And last but not least Maria helped us in coming up with the idea and the product recommendation system, which became a vital part of our product. Now the product is capable of generating negotiation points for a customer to keep invested in buying the product.

NegotiazeAI

Racconti is an app that uses state of the art AI and voice synthesis technology to generate bed time stories for children and reads them out using the voice of a loved one. It is known that establishing a bedtime routine is important for the wellbeing of the children, and that voices are something we can recognise easily and hearing a loved one’s voice can help soothe and calm down. Based on the Cohere API (https://www.cohere.ai/), we've build a tool that is able - generate a story with a given morale that the child should learn - create the main character of the story based on the input - read out the story in a custom voice generated from only 1 minute of audio

Engels

The idea is to create a roadmap, because everything is in the roads. Meaning that when you know the road, you will know how to explore it. If you want to be iOS-developer, then you have to literally study while loving to become an iOS-Developer. Please, see the instructions in iOS applications. The goal we wanted to achieve was being able to reference secret values within our source code, without these values themselves needing to be kept in source control. The two solutions we have looked at are quite different, but both achieve the same goal. By using cocoapods-keys, we can avoid the manual setup and also avoid the values being stored in plain-text anywhere in the project. However, our solution using Sourcery can be used without Cocoapods and will still require very little maintenance. There will definitely be even more solutions available online for more use cases, it will come down to using the most appropriate solution for the situation.

AI isnt AI

Ainfer is an innovative AI solution that transforms the way students and researchers access information. Equipped with cutting-edge Cohere technology, Ainfer quickly extracts key information from articles and delivers accurate answers to complex questions. Designed to streamline the research process, Ainfer allows users to summarize articles and work with multiple files simultaneously. By leveraging Cohere's advanced embedding model, Ainfer identifies the most relevant parts of an article and uses Cohere's state-of-the-art generative model to process the information and provide reliable answers. With Cohere's multilingual embeddings, Ainfer can search for answers in over 100 languages, making it a powerful tool for audiences worldwide. Ainfer was created with Streamlit, offering a visually appealing and user-friendly interface for customers. Whether it's for academic research or just personal knowledge-seeking, Ainfer is the ultimate information extraction tool.

Ainfer

Are you tired of endlessly scrolling through pages of champions in League of Legends, trying to find the perfect fit for your playstyle? Look no further! Co:mpass is here to introduce an innovative solution that will change the way you choose your champions forever. With a simple prompt text, our application will recommend the best champions for you, based on your preferences for playstyle and strategy. Imagine having the perfect champion recommended to you, every time you play. No more guesswork, no more hesitation, just pure gaming bliss. Get ready to experience the future of champion selection, with our cutting-edge application!

Bing Chilling

Co-writeme is a project that aims to make story writing easier and more accessible. It is a platform that generates stories based on the writer's input, which is analyzed and transformed into a unique, original story. The system is user-friendly and offers real-time generation, allowing writers to generate a story quickly. It also includes resources to improve writing skills and a community for support and feedback. The team developing the project is composed of experienced writers, editors, and developers. Co-writeme is the ideal platform for writers of all levels to bring their stories to life.

CowLover

Slyngshot is a product that allows users to create Natural Language Processing (NLP) workflows through a drag-and-drop interface, leveraging cohere's platform. This makes it easy for users to build custom NLP solutions without the need for extensive technical knowledge or programming skills. With Slyngshot, users can connect different NLP components, such as text generation, embedding, and vector storage, to create sophisticated workflows. The drag-and-drop interface provides a visual representation of the workflow, making it easy to understand and manage. The product is designed to simplify the process of creating NLP solutions and is suitable for both technical and non-technical users.

Slyngshot

Emo-Pulse helps to 'listen' to live sales meeting and conversations and transcribes the text from the conversation. It also provies an autocorrect feature for the transcribed text. It can provides the features for sentiment analysis, conversation summary, toxicity analysis ( to check if the conversation is getting toxic) and further suggestions for next dialogues and steps in the sales. We use the generate endpoints of Cohere for sales suggestions and conversation summary (by providing the necessary examples for training) and the classify endpoints of Cohere for sentiment analysis and toxicity analysis.

Guide

Voice Clue is an AI powered assistant that assists in generating descriptions about a given keyword and reads them out aloud. Our Voice Clue is an AI-powered read-aloud descriptor that uses artificial intelligence and Natural Language Generation algorithms to generate text by itself about a given keyword. Our descriptor also reads the generated text out loud using a TTS (text to speech) engine to produce spoken language. This technology can be used in various applications, such as writing articles, understanding various topics. The descriptor provides a good intuition on any given keyword. The Voice Clue works well with many word groups. The Voice Clue works with cohere generate api under its hood. It is trained on large amounts of text data / corpus. It learns patterns and relationships in language and generates new information from the learning. It mimics the human way of interpreting the information and generates unseen data analytically.

WeM2

Docs Buddy is a cutting-edge medical semantic search engine that combines the power of coherence embeddings with the reach of Google search. It offers healthcare professionals and pharmaceutical associates an efficient way to access relevant information about symptoms, medications, and treatment procedures. By simply inputting symptoms, users can retrieve a comprehensive list of documents that match their search criteria. Additionally, Docs Buddy also allows users to search for specific medications, providing images, prices, and even the option to buy online. Say goodbye to endless scrolling and hello to fast and accurate results with Docs Buddy. 🚀 Upgrade your medical search game today! 💻

team phoeniks

Cyclops is a smart assistant device that takes input from an inbuilt camera and microphone and gives response through inbuilt speaker it understands and responds to human commands using both visual and audio cues. The camera captures live video while the microphone picks up spoken commands. By integrating both visual and audio input, Cyclops smart assistant is able to provide a more intuitive and natural user experience. The device uses facial recognition to identify the user and then use voice commands to perform specific actions. This is useful for tasks like home automation, where visual instructions are necessary. Cyclops improve its understanding of the user's commands over time, continually learning from its interactions, provides a unique and versatile user experience, offering a new level of convenience and accessibility. We have built cyclops using an IP camera and used raspberry pi model zero w as its computing unit, video images captured by the inbuilt camera are converted into a string by means of a TensorFlow image processing code while voice to is turned into a string via speech to text this is then sent to cohere for processing via the API

Quantum Analytics limited

SymbiotAI - the ultimate solution for seamless human and AI interaction. Our platform is designed to bridge the gap between people and AI, helping them work together to create something truly amazing. Whether you're an individual looking to harness the power of AI for personal projects or a business looking to integrate AI into your operations, our platform has got you covered. Our platform works with any AI model, you can be sure that you're getting the best possible results. And because our platform is user-friendly, you don't need to be an AI expert to use it.

SymbiotAI

The traditional foreign-language training methods are ineffective since the learners are not engaged in the learning process. These methods focus mainly on vocabularies memorization and grammar-translations. However, foreign-language learners needs to be engaged through active storytelling and reading comprehension according to their skills level. This project is intended to leverage Generative AI and help foreign-language teachers to create personalized and compelling stories based on the learner’s skills level and interests. To train the Chinese sentence generator, we fine-tune Cohere’s Generative AI with “20k+ Chinese sentence translations and pinyin based on HSK level” dataset by Brian Vaughan. The model accuracy is 72.95%.

Kala