Freelancers using spaCyFreelancers using spaCy
ProjectsPeople
Anurag Nagare's avatar
Anurag Nagare
Mumbai, India
I’m an AI & Machine Learning engineer with expertise in deve
I’m an AI & Machine Learning engineer with expertise in deve
Cover image for launched TextGenix Enterprise — an AI-powered intelligent do...
launched TextGenix Enterprise — an AI-powered intelligent document processing system! This platform enhances and transforms documents (PDF, DOCX, TXT, HTML, RTF) with context-aware vocabulary improvements, grammar validation, and industry-specific terminology (legal, medical, financial, technical). It comes with a sleek Gradio-based web interface featuring modern styling, interactive analytics dashboards, and real-time quality metrics like semantic preservation, grammar score, and AI confidence levels. If you’re looking to build your own AI-powered text/document platform, enhance business workflows with custom NLP models, or integrate analytics-driven AI solutions into your enterprise apps I can help.
0
54
Cover image for Everyone's talking about quantum computing.
Everyone's talking about quantum computing. Nobody's using it to feed farmers. India loses 20–30% of its crop yield every year to diseases and pests. Not because farmers don't care — but because early detection is hard, expensive, and inaccessible to the people who need it most. The existing solutions? Either a basic image classifier trained on lab-perfect photos that fail in real field conditions, or an agronomist visit that costs time and money most small farmers don't have. So I built QuantumEdge AgriGuard — a hybrid Quantum Neural Network app where a farmer can photograph a diseased leaf on their phone and get an instant diagnosis in under 5 seconds. Here's what makes it different from just another plant disease detector: Instead of a pure classical CNN, I built a hybrid architecture — a ResNet/EfficientNet backbone extracts visual features, then passes them into a Variational Quantum Circuit (VQC) for the final classification. The quantum layer uses angle embedding + StronglyEntanglingLayers, which gives it a measurable edge on small, noisy datasets — exactly the kind of data you get from Indian field conditions. The app doesn't just tell you what disease it is. It gives you: → Confidence score → Organic + chemical remedies (India-specific) → Yield impact estimate → A live classical vs quantum accuracy comparison so you can see the difference yourself I tested the quantum advantage claim honestly — ran both models on the same downsampled PlantVillage dataset and tracked accuracy, F1-score, and inference time side by side. The results are on the dashboard. No hand-waving. Built with PennyLane + PyTorch + Plotly Dash. Designed to run on simulators today and on QpiAI-Indus 25-qubit hardware tomorrow.
0
7
Cover image for Most AI research tools are
Most AI research tools are just a chatbot with a search button. I built something different. Every time you ask an AI to research something, you're getting one model, one pass, no quality check. It writes confidently, cites poorly, and you have no idea if what it produced is actually accurate. For anyone making real decisions from AI-generated research, that's a silent risk most people ignore. The problem gets worse at scale the longer and more complex the question, the more a single model hallucinates, misses sources, and loses structure. There's no one checking its work. So I built ResearchOS a 5-agent pipeline where each agent has one job. A Supervisor breaks down your question. A Researcher runs parallel searches across 22+ sources. An Analyst extracts data and auto-generates charts. A Writer synthesises a cited report. A Critic fact-checks it and sends it back for revision if anything is wrong. The loop runs up to 3 times before the report is approved. One question in. A full cited report with charts and PDF export in under 10 minutes. I tested it live by watching the Critic catch a missing citation mid-run and send the Writer back to fix it before approval. That's the part that makes this actually usable for real work. Built on LangGraph, Groq, Tavily, ChromaDB and runs entirely on free tiers.
1
59
Cover image for It all started on a
It all started on a Sunday at the AWS User Group Mumbai meetup. I wasn't expecting to walk away with a new obsession, but then the speaker introduced me to Temporal and everything changed. Temporal is a durable execution engine that solves one of the hardest problems in agentic AI what happens when your LLM workflow crashes mid-run? Normally you lose everything So I went home and built this: an agent that monitors your competitors around the clock tracking pricing changes, product launches, hiring signals, and strategic moves. Every 24 hours it uses Mistral (running fully on-device via Ollama) to analyze the data and synthesize a structured executive briefing delivered straight to your inbox. Sometimes the best projects start with a Sunday conversation. https://github.com/AnuragNagare/Agentic-AI-.git
0
21
spaCy(1)
Syed Fatik Islam's avatar
Syed Fatik Islam
Gujrat, Pakistan
Data Scientist delivering insights through analytics and ML
Data Scientist delivering insights through analytics and ML
Cover image for Chat Data Analysis and Sales Insights Platform
Chat Data Analysis and Sales Insights Platform
0
7
Cover image for Instagram Chat Analysis
Instagram Chat Analysis
0
13
Cover image for Sales Analysis of a Clothing Retail Shop
Sales Analysis of a Clothing Retail Shop
0
13
Placeholder project card media
View more →
spaCy(1)
Varshith Gaddam's avatar
Varshith Gaddam
Hyderabad, India
AI/ML student building smart, real-world tech solutions.
AI/ML student building smart, real-world tech solutions.
Cover image for Voice-Based Cognitive Decline Pattern Detection
Voice-Based Cognitive Decline Pattern Detection
0
2
Cover image for Stock Analysis Project with AutoGen
Stock Analysis Project with AutoGen
0
1
Cover image for Paisa Controller: AI-Powered Finance Management App
Paisa Controller: AI-Powered Finance Management App
0
0
Placeholder project card media
View more →
spaCy(1)
Bindupautra Jyotibrat's avatar
Bindupautra Jyotibrat
Guwahati, India
AI mentor | Hackathon pro | CHI 2025 researcher
AI mentor | Hackathon pro | CHI 2025 researcher
Cover image for AI-Powered Document Summarizer Development
AI-Powered Document Summarizer Development
0
6
Cover image for AI-Powered Floor Planning Solution
AI-Powered Floor Planning Solution
0
2
Cover image for TRMSCII - Terminal-based School Management System
TRMSCII - Terminal-based School Management System
0
2
Placeholder project card media
View more →
spaCy(1)
Waqas Ahmed's avatar
Waqas Ahmed
Islamabad, Pakistan
Data Scientist | NLP | GenAI | Automation
Data Scientist | NLP | GenAI | Automation
Cover image for 🧠 Introducing NLP-Assistant! > Smart Workflow Detection: AI...
🧠 Introducing NLP-Assistant! > Smart Workflow Detection: AI suggests the optimal analysis path for maximum insight. > Specialized Workflows: Dedicated analysis for diverse content, including PII detection, hashtag extraction, and citation analysis. > Comprehensive Analytics: Get detailed text stats, VADER sentiment scoring, and interactive Plotly visualizations. >> Check out the repo, give it a star, and try transforming your text data into actionable insights! 👇 github.com/WaqasAhmed27/NLP-Assistant (https://github.com/WaqasAhmed27/NLP-Assistant)
0
9
Cover image for Here is a short post you can use for your project, ParhAI: �...
Here is a short post you can use for your project, ParhAI: 🚀 Just launched ParhAI! I'm excited to share my new AI-powered educational platform, ParhAI. It's built on a modern stack (Next.js 14, TypeScript, Supabase) and integrates cutting-edge AI features to revolutionize learning and content creation. Key Features: 🤖 AI Content Generation (Powered by Google Gemini) 🖼️ OCR for text recognition from images 🗣️ Speech Services (TTS & STT) 📊 Presentation Tools (Reveal.js/PPTXGenJS) Check out the repo, give it a star, and let me know what you think! 👇 github.com/WaqasAhmed27/ParhAI (https://github.com/WaqasAhmed27/ParhAI) #NextJS #TypeScript #GenAI #Education #OpenSource #ParhAI
0
5
Cover image for Introducing F1 Strategy Sim, a machine-learning powered race...
Introducing F1 Strategy Sim, a machine-learning powered race-strategy simulator. It uses 29+ features to predict the outcome of each formula 1 session! Check it out: github.com/WaqasAhmed27/f1-strategy-sim (https://github.com/WaqasAhmed27/f1-strategy-sim?utm_source=chatgpt.com)
0
12
Cover image for NLP Assistant: Automated Text Analysis App with AI
NLP Assistant: Automated Text Analysis App with AI
0
0
spaCy(1)
Ashish Chaudhary's avatar
Ashish Chaudhary
Lucknow, India
AI Engineer | AI Researcher
AI Engineer | AI Researcher
Cover image for Chatbots provide instant conversational responses
Chatbots provide instant conversational responses and make connecting simple for patients. And when implemented properly, they can help care providers to surpass patient expectations and improve patient outcomes. However, AI solutions sometimes lack the most important quality to good care delivery. So Task was to create a chatbot using python , flask , Javascript , machine learning and NLP techniques.
0
26
Cover image for Designed and built a production-grade
Designed and built a production-grade AI automation system that replaces manual job searching on LinkedIn. The workflow parses resumes using AI, extracts skills and preferences, scrapes relevant LinkedIn job listings, evaluates each role using semantic AI matching, and ranks opportunities by relevance score. It automatically filters low-quality roles, identifies recruiter contacts, and generates personalized outreach messages. The system outputs a centralized tracking dashboard, reducing manual job search effort by over 90% while improving application relevance and response rates.
0
21
Cover image for A RAG-based real estate chatbot
A RAG-based real estate chatbot built to answer queries from Dubai property listings stored in private PDFs. The system uses OpenAI GPT to generate natural language responses, while LangChain orchestrates the full retrieval-augmented generation pipeline including document ingestion, chunking, and retrieval. Pinecone is used for semantic vector search to ensure relevant property information is retrieved quickly and accurately. SerpAPI is integrated to provide optional external insights when needed. The chatbot answers strictly from the uploaded documents and transparently responds with “I don’t know” when the information is not present, ensuring reliable and document-grounded property details.
0
24
Cover image for Interact with databases using natural
Interact with databases using natural language with this NL2SQL system built using LangChain. Users can ask questions in plain English, and it generates and executes SQL queries, returning clear answers.
0
34
spaCy(1)
Rithik Gour's avatar
Rithik Gour
Mysuru, India
AI Engineer | WEB Developer | ML Engineer
AI Engineer | WEB Developer | ML Engineer
Cover image for pubMed-paper-fetcher
pubMed-paper-fetcher
0
1
Cover image for wealth-ai-navigator
wealth-ai-navigator
0
3
Cover image for Lead AI Harvest - Intelligent Lead Generation Tool
Lead AI Harvest - Intelligent Lead Generation Tool
0
0
Cover image for YouTube Video Transcript AI
YouTube Video Transcript AI
0
5
spaCy(1)