Daksh Yadav
Building systems that turn ideas into scalable products.
New to Contra
Daksh is ready for their next project!
Building intelligent agricultural AI systems requires combining machine learning with contextual knowledge retrieval and multi-step reasoning, making architecture and orchestration critical challenges.
Designed and contributed to an AI-powered Crop Yield Prediction and Farm Advisory System using machine learning, RAG, and agentic AI. Integrated ChromaDB and Hugging Face embeddings for semantic knowledge retrieval, leveraged LangGraph for multi-step reasoning, and used Groq LLM APIs to generate structured crop insights and recommendations. Built an interactive Streamlit interface for predictions and advisory reports.
Delivered an end-to-end AI solution for data-driven agricultural decision-making while strengthening expertise in machine learning pipelines, vector databases, Retrieval-Augmented Generation, agentic workflows, and LLM-powered applications.
0
17
Developed a full-stack e-commerce platform that enables users to browse products, create accounts, securely authenticate, and manage their shopping experience. The application includes user registration and login, JWT-based authentication, product listings, individual product pages, shopping cart functionality, and user profile management. Built with React for the frontend and Node.js/Express for the backend, the project focuses on creating a responsive, scalable, and user-friendly online shopping experience while implementing modern web development best practices.
0
28
Tech Stack: React, Tailwind CSS, Context API, Node.js, Express, PostgreSQL, JWT, Cloudinary, Vercel, Render
Building a social media platform requires handling complex real-time interactions, scalable state management, and production-level edge cases — challenges that expose gaps in architecture and deployment skill quickly.
Designed and built a full-stack social networking application supporting posts, real-time chat, and user profiles. Implemented centralized state management using React Context API to ensure consistent data flow across components. Engineered a secure authentication system using JWT and integrated Cloudinary for optimized media storage and delivery. Deployed the application across Vercel (frontend) and Render (backend), resolving cloud-specific production issues throughout the process.
Delivered a production-ready, fully deployed social media application. Strengthened expertise in full-stack architecture, scalable state management, cloud deployment workflows, and resolving real-world production bugs — with measurable improvements in UI/UX decisions driven by user engagement insights.
0
34
Tech Stack: React, JavaScript, FastAPI, Python, Groq, Ollama, Qdrant, Supabase, BM25, Reranking, Vercel, Render
Legal contract review is prohibitively expensive for individuals and small businesses, with enterprise software solutions costing thousands of dollars — leaving most users without access to reliable legal risk analysis.
Architected and developed a two-stage AI-powered contract review platform from the ground up. Designed a document ingestion and chunking pipeline to handle legal agreements of varying complexity. Implemented a hybrid retrieval system combining vector search (Qdrant) and BM25 keyword search with reranking to surface the most contextually relevant clauses. Integrated Groq-hosted models for fast initial analysis and Ollama for deeper local verification, enabling a dual-confidence review workflow. Built an evaluation-driven scoring system to quantify risk and identify missing contractual protections, exposed via a FastAPI backend and consumed by a React frontend.
Delivered a fully functional, production-deployed legal intelligence platform that replicates capabilities found in enterprise legal software — built entirely at zero cost. Demonstrated proficiency in full-stack product design, RAG pipeline architecture, hybrid search systems, and legal-tech workflow engineering.
0
45
Jurisight
0
0
E-Commerce
0
0
Teen Talks
0
0