This project is an AI-powered interview preparation platform designed to help users practice job-specific interviews in the most realistic and personalized way possible. Users can upload their resume (PDF or text), and the system automatically analyzes their experience to generate tailored interview questions using the Gemini 2.0 Flash model and Groq-powered inference. The platform supports both voice and text-based mock interviews, allowing candidates to speak naturally and receive real-time feedback on their answers, tone, clarity, and confidence. In addition to smart question generation, the platform provides detailed performance insights, progress tracking, and a full history of previous sessions. With secure JWT-based authentication and a responsive, mobile-friendly UI, users can seamlessly log in, practice, and improve anytime. Voice-enabled sessions, instant scoring, and personalized tips make this tool ideal for students, job seekers, and professionals looking to upgrade their interview skills.
19 Nov 2025
Problem Statement: Weather often disturbs daily plans, events, and travel. Many People and organizations donot have any easy way to get real-time, personalized weather guidance. Solution: ClimeAI solves this Problem and Provide an AI powered weather assistant that combines real-time weather data with smart advice for event planning, travel guidance, and safety decisions. It understands the user queries and keep the context through chat memory, deliver recommendations such as best travel times, event safety plans, and packing suggestions. Technology Stack: The platform built using FastAPI (Python), LangGraph, MongoDB, and Docker, with APIs including OpenWeatherMap, OpenCageData, AIML API, Mistral API Key, and Eleven Labs for smart intelligence, orchestration, and natural voice. Value: ClimeAI help users and businesses to make smarter, safer, and faster weather-aware decisions, save time, reduce risks, and improving their planning efficiency.
21 Sep 2025
MindHaven is an AI-powered mental health companion designed to offer emotional support, mindfulness, journaling, stress relief and personalized well-being insights. In today’s fast-paced world, mental health struggles such as stress, anxiety, and burnout are increasingly common, yet access to professional help remains a challenge for many. MindHaven bridges this gap by providing an accessible, AI-driven support system that users can turn to anytime, anywhere. Our platform enables users to express their thoughts, track their moods, and receive empathetic responses. Unlike generic chatbots, MindHaven integrates document-based retrieval, allowing users to upload self-help materials, therapy guides, or mental wellness PDFs or other documents. The AI then provides context-aware responses based on both real-time interactions and relevant content from uploaded documents. MindHaven is ideal for individuals seeking mental well-being support, therapists looking for an AI-assisted journaling tool for clients, and organizations promoting workplace mental health. With features like guided meditation, daily wellness tips, and a private journal, MindHaven creates a safe space for users to navigate their emotions, develop mindfulness, and build healthier mental habits.
16 Feb 2025
ScholarShelf is a next-generation AI-powered platform designed to revolutionize the way students, researchers, and professionals interact with their study and work materials. The platform allows users to upload documents in various formats, including PDFs, DOCX, and TXT, and provides context-specific answers to their queries using cutting-edge AI technology. ScholarShelf eliminates the hassle of manually searching through multiple documents by offering personalized, context-aware responses derived exclusively from the uploaded content. Key Features: Document Uploads: Supports multiple formats, including academic papers, textbooks, research notes, and more. Context-Aware Assistance: AI provides accurate answers tailored to the content in the uploaded materials. User-Centric: Designed to cater to students, researchers, educators, and professionals across different fields. Lightweight and Efficient: Operates without complex embeddings, making it accessible on minimal hardware. Benefits Beyond Education: ScholarShelf's capabilities extend beyond traditional learning environments: Healthcare: Doctors and medical researchers can upload clinical guidelines, research papers, or patient reports and ask precise questions to support decision-making and diagnosis. Corporate Training: Companies can use ScholarShelf to manage training materials, enabling employees to ask questions and quickly learn from company policies, handbooks, or training guides. Legal Industry: Legal professionals can upload case files and ask specific questions to streamline legal research and case preparation. Knowledge Management: Organizations can manage large repositories of documents, making it easy for teams to retrieve critical information on demand.
26 Jan 2025
Provide a Decision Support System (DSS) designed to enhance decision-making by providing data-driven insights and predictive analysis for optimizing sector investments. It leverages advanced analytics and AI algorithms to process large volumes of data, offering real-time performance tracking and actionable recommendations for various departments at both state and national levels. The system optimizes state-level investments across departments, such as police, healthcare, and education, by analyzing data and predicting resource needs. It generates projections across states, offering insights into performance and resource allocation at a national scale, enabling more efficient decision-making and better-targeted investments.
15 Dec 2024
Aslan AI relapse prevention in healthcare, particularly in mental health and addiction recovery. Many individuals struggle with emotional crises and lack accessible, immediate support during these vulnerable moments. To address this, Aslan offers an innovative AI-driven solution that provides real-time emotional support, helping users navigate challenging moments and prevent relapse. Aslan engages users in conversational, nonjudgmental interactions, dynamically adjusting its responses to validate emotions, identify underlying needs, and offer personalized interventions. The system is designed to help users express their emotions freely, offering them a safe space for self-reflection and growth. Aslan helps users develop a deeper understanding of their feelings and take actionable steps toward emotional well-being. Key functionalities include journaling prompts, mindfulness exercises, and value-driven decision-making tools that empower users to cope with stress and regain control during difficult times. The AI also features an adaptive response mechanism, which determines the best approach, whether to suggest an intervention first or help the user clarify their emotions and needs. A standout feature is the rant-friendly space, where users can vent freely, with built-in flagging mechanisms to detect concerning content based on varying threat levels (white, yellow, orange, red). This ensures that users in crisis are promptly directed to appropriate resources, such as crisis hotlines or clinical professionals. The primary target audience for Aslan includes individuals in recovery from addiction, those dealing with mental health issues, and anyone who needs ongoing emotional support. By offering real-time interventions and a supportive environment, Aslan reduces the risk of relapse and creates long-term emotional resilience.
11 Dec 2024
VitalGuide is an offline emergency assistance app designed to save lives during natural disasters or situations where connectivity is unavailable. The app addresses the critical need for reliable survival guidance and emergency first-aid instructions. It uses a Retrieval-Augmented Generation (RAG) system and the Gemma 2 model to provide quick and accurate answers by leveraging government datasets and trusted sources like PDFs and guides. This is important because FEMA's manual is large and unwieldy, and slower to leaf through than our LLM tool, when the seconds matter. Gemma 2 also has general knowledge that the FEMA manual doesn't have and can be asked follow-up questions if information is unclear. Specialized for individuals, communities, and first responders, it features multilingual support, ensuring accessibility for diverse users. Its unique offline functionality guarantees availability anytime, anywhere. VitalGuide empowers users with lifesaving knowledge, bridging the gap when conventional communication methods fail.
1 Dec 2024
Solution Overview With the development of advanced AI models, developers, and data scientists face the challenge of efficiently evaluating and comparing multiple models for some particular tasks.LlamaEval addresses this challenge by offering a streamlined, easy-to-use evaluation dashboard for comparing Llama model outputs. By integrating the Together AI API, users can select and test multiple models. The results are displayed on an interactive dashboard with two key features: a benchmark description expander and a performance scoreboard featuring metrics. So the user has information about the benchmark used and the final evaluation scores. Tech Stack Backend: Python, Together AI, requests, pandas, nltk, scikit-learn and Hugging Face datasets Frontend: Streamlit for creating the user interface, displaying results, and providing interaction Deployment: Docker, Azure Cloud Services: Container Registry (store the docker container) and Container App (deploy and provide a url link that can be copy-pasted on the web.) Target Audience This tool is designed for data scientists, AI researchers, developers and, machine learning Engineers from enterprises, academia, and government sectors. They need efficient solutions for quick model assessment in real-world applications roughly estimating a serviceable market of ~$10B. Unique Features/Benefits • Simplicity and speed: LlamaEval offers a simple interface to quickly assess multiple models without the need for complex setups or long runtimes. • Comprehensive insights: Real-time results and detailed comparison panels. • Customizable: In the future, the users will be able to select any number of models for comparison and evaluate them on any dataset, making it versatile for a wide range of use cases.
11 Nov 2024
