The idea is to develop streamlit app enables you to engage in interactive conversations with arXiv, a vast repository of scholarly articles, using GPT-4o. With this RAG application, you can easily access and explore the wealth of knowledge contained within arXiv. Problem Statement: Researchers and academics often struggle to quickly understand the vast number of papers published on ArXiv. ArXiv is an open-access repository for research papers in fields like physics, mathematics, and computer science, allowing researchers to share preprints before peer review. It promotes rapid dissemination and accessibility of scientific knowledge. Solution: Our web application leverages GPT-4 to provide concise summaries and explanations of ArXiv papers based on user prompts. Features Engage in conversational interactions with arXiv Access and explore a vast collection of research papers Utilize OpenAI GPT-4o for intelligent responses

Project Name: HireFit - AI-Enhanced CV Optimizer In today’s competitive job market, many candidates are unaware that their CVs are rejected by automated ATS (Applicant Tracking Systems) before they even reach human recruiters. The main reason for these rejections is the lack of alignment between the CV content and the specific job description. To solve this challenge, we developed HireFit, an AI-powered tool designed to automatically analyze your CV and compare it to the job description, identifying missing information and generating an optimized version of the CV for the best possible ATS score. With HireFit, users simply upload their CV and the job description. The tool uses advanced AI models (like Meta-Llama-3.1) to evaluate the CV content and identify gaps based on the job's requirements. It then regenerates the CV, filling in the necessary details and matching it to the job description, creating a professional CV optimized for ATS. In addition to this, HireFit provides interview preparation notes that highlight areas the candidate should focus on based on the changes made to the CV. These notes offer valuable insights into the missing skills or experience the candidate needs to prepare for, helping them be fully ready for their interview. Users can download the updated CV and interview preparation notes in various formats (PDF, DOCX), allowing easy customization and further edits according to their needs. HireFit ensures that candidates no longer face the disappointment of automated rejections and can confidently apply for jobs knowing their CV stands a better chance of being noticed.

Project Name: FILL IT Author: Umar Majeed Description: FILL IT is an automated system designed to streamline data entry processes. The project utilizes the Whisper model for transcribing audio recordings into text and the IBM Granite model for extracting information and filling out forms. The workflow involves: Audio Transcription: Converts audio files (e.g., WAV, MP3) into text using the Whisper model. Text Extraction: Extracts text and questions from a PDF form. Form Generation: Uses the IBM Granite model to generate completed form data based on the transcribed text and extracted questions. Due to technical issues, I was unable to deploy the application before the submission deadline. I am actively working on deploying it and will make it available soon. For now, I am submitting the project in its current state. The Kaggle notebook detailing the implementation is shared for reference.

We are excited to present our project, which focuses on addressing emergencies and environmental issues through an advanced AI-driven solution. In this hackathon, our team has developed an application that can generate accurate responses to a variety of emergency scenarios and environmental challenges. Project Overview: Model and Dataset: We utilized the LLaMA 3.1 model with 405B parameters to generate a synthetic dataset of approximately 2,000 question-answer pairs. This dataset was initially created in Excel and later converted into JSON format for model training. The TinyLLaMA 1.1 billion parameter chat version was fine-tuned using this dataset, allowing our model to provide highly contextual and relevant responses. Training and Fine-Tuning: We leveraged the resources available on Google Colab, specifically using T4 GPUs to generate the dataset. We leveraged the resources available on Kaggle, specifically using T4 x2 GPUs to train our model. After completing the fine-tuning process, we pushed the model to Hugging Face, making it accessible for deployment and further testing. Deployment: The model was deployed on Hugging Face Spaces, where we integrated a user-friendly Gradio UI interface. This interface enables users to input queries and receive real-time responses directly from the model. All project files and necessary documentation have been committed to our repository, ensuring full transparency and accessibility. Team: Our project was made possible by the collaborative efforts of a dedicated team of six members: Team Lead: Umar Majeed LinkedIn Profile Team Members: Moazzan Hassan LinkedIn Shahroz Butt LinkedIn Sidra Hammed LinkedIn Muskan Liaqat LinkedIn Sana Qaisar LinkedIn We would like to thank LabLab AI for this opportunity, and we look forward to the impact our application can make in real-world scenarios.

WorkUp is a project management tool designed to streamline and automate the process of project setup and management. Using AI-powered algorithms, the tool efficiently distributes tasks to team members based on their expertise, ensuring optimal productivity. WorkUp allows users to upload project descriptions and team expertise in various formats (PDF, DOCX, TXT) or manually input the data. The AI system analyzes this information to assign tasks, generate detailed workflows, and create visual flowcharts for a clearer understanding of the project’s progression. Additionally, WorkUp suggests creative project names and generates a starter code structure to kickstart development. Built on a user-friendly Streamlit interface, the tool allows for seamless interaction and feedback collection, enabling continuous improvement. WorkUp saves time, enhances collaboration, and scales easily to accommodate projects of different sizes and complexities. Future enhancements include advanced customization options, integration with existing project management tools, and mobile support.

The "Optimized Code Generator" is an innovative platform designed to simplify coding tasks and enhance the quality of code generation using advanced AI models. Built on Streamlit, it offers an interactive interface where users can enter coding problems, select their preferred programming languages (like Python, Java, or C++), and choose from various AI models (including o1-preview, o1-mini, Llama_3.2, GPT4o, Gemini, and Mistral). The tool generates optimized code along with detailed line-by-line explanations. Users can analyze the time and space complexity of the generated code through interactive graphs, enabling them to understand performance implications. Furthermore, a comparison mode allows for side-by-side evaluations of outputs from different models, fostering learning and improving coding practices.