DEV
Thariq Khalfani@ariankhalfani
is under improvement
4
Events attended
2
Submissions made
AI Engineer
Indonesia
2 years of experience
About me
Final-Year student at Gadjah Mada University. Currently mentored at Korika (Indonesia AI Acceleration Collaborator) to build Responsive Large Language Model for Costumer Service. Passionate about Artificial Intelligence, Machine Learning, and Deep Learning.
is under improvement
🤝 Top Collabolators
.png&w=640&q=75)
🤓 Submissions
Wellness Nexus
Wellness Nexus is a groundbreaking integrated healthcare application meticulously crafted to empower individuals in managing their health and fitness effectively. At its core, the app is designed to provide users with a holistic approach to wellness, combining advanced technologies and personalized assistance to cater to individual needs. The standout feature of Wellness Nexus is Nexus-Scan, leveraging cutting-edge computer vision models to analyze food images and provide users with an approximation of their calorie intake. This not only simplifies tracking dietary habits but also fosters mindful eating practices by offering real-time feedback. Moreover, Nexus-Sugar adds another layer of functionality by predicting the sugar content of various food items, enabling users to make informed dietary choices and manage their sugar intake more effectively. This feature is particularly valuable for individuals with specific dietary requirements or health conditions such as diabetes. Additionally, Wellness Nexus incorporates Nexus-Fit, a tool that utilizes user-provided parameters to determine the range of their ideal weight, thereby facilitating goal-setting and progress tracking within their fitness journey. By offering personalized insights and guidance, this feature encourages users to pursue their health goals with confidence and clarity. Furthermore, the app boasts Nexus-Bot, a friendly and intuitive virtual assistant designed to assist users in navigating the application and understanding its functionalities. Whether it's providing information about how the app works or offering tips for maximizing its benefits, Nexus-Bot serves as a reliable companion throughout the user's wellness journey. In essence, Wellness Nexus represents a paradigm shift in healthcare technology, bridging the gap between innovation and user-centric design to promote holistic well-being.
Adapt-a-RAG
Introduction Adapt-a-RAG is an innovative application that leverages the power of retrieval augmented generation to provide accurate and relevant answers to user queries. By adapting itself to each query, Adapt-a-RAG ensures that the generated responses are tailored to the specific needs of the user. The application utilizes various data sources, including documents, GitHub repositories, and websites, to gather information and generate synthetic data. This synthetic data is then used to optimize the prompts of the Adapt-a-RAG application, enabling it to provide more accurate and contextually relevant answers. How It Works Adapt-a-RAG works by following these key steps: Data Collection: The application collects data from various sources, including documents, GitHub repositories, and websites. It utilizes different reader classes such as CSVReader, DocxReader, PDFReader, ChromaReader, and SimpleWebPageReader to extract information from these sources. Synthetic Data Generation: Adapt-a-RAG generates synthetic data using the collected data. It employs techniques such as data augmentation and synthesis to create additional training examples that can help improve the performance of the application. Prompt Optimization: The synthetic data is used to optimize the prompts of the Adapt-a-RAG application. By fine-tuning the prompts based on the generated data, the application can generate more accurate and relevant responses to user queries. Recompilation: Adapt-a-RAG recompiles itself every run based on the optimized prompts and the specific user query. This dynamic recompilation allows the application to adapt and provide tailored responses to each query. Question Answering: Once recompiled, Adapt-a-RAG takes the user query and retrieves relevant information from the collected data sources. It then generates a response using the optimized prompts and the retrieved information, providing accurate and contextually relevant answers to the user.
