Freelancers using Streamlit in India
Freelancers using Streamlit in India
Sign Up
Post a job
Sign Up
Log In
Filters
2
Projects
People
Abu Aasif Ansari
Bhiwandi, India
I build AI-powered data apps and dashboards
8
Followers
Follow
Message
I build AI-powered data apps and dashboards
1
AI-Powered Data Cleaning Tool Development
1
1
1
AI-Powered Data Cleaning Tool
1
1
1
Smart Data Analyst — AI-Powered Data Analysis App
1
2
1
PersonaSkill AI — Career Assessment Tool
1
4
Streamlit
(5)
Follow
Message
Mohammad Umar
India
Freelance Data Scientist | Python & ML Expert
10
Followers
Follow
Message
Freelance Data Scientist | Python & ML Expert
1
Fraud Transaction Detection System
1
7
1
Hybrid AI Movie Recommendation System for Pre-2015 Films
1
4
0
Lung Cancer Survival Prediction Model Development
0
6
View more →
Streamlit
(3)
Follow
Message
Trashu Vashisth
Delhi, India
Building Production-Grade AI Agents & RAG Systems
13
Followers
Follow
Message
Building Production-Grade AI Agents & RAG Systems
0
The Problem: Sales teams waste 60% of their time researching leads instead of closing them. The Solution: I built a custom Agentic AI Pipeline that automates deep-dive business intelligence and lead scoring. Key Technical Highlights: Multi-Agent Architecture: Built using CrewAI, featuring a 'Business Intelligence Specialist' (for real-time research) and a 'Senior Sales Director' (for strategic scoring). High-Speed Intelligence: Powered by Llama 3.3-70B for near-instant reasoning and decision-making. Real-time Web Scoping: Integrated Tavily AI to fetch live revenue data, employee counts, and market positioning. Enterprise Storage: A robust SQLite backend to manage lead pipelines with a sleek Streamlit dashboard. Smart Throttling: Engineered custom rate-limiting and token-trimming logic to ensure 99.9% uptime even under heavy API constraints. How it works: Simply enter a company name and URL. The AI agents scour the web, analyze the company's "AI potential," calculate a priority score (0-100), and even write a personalized sales pitch—all in under 30 seconds.
0
58
1
An autonomous AI system that turns a simple voice command into a deep-dive research report in seconds. No typing, no manual searching. Key Highlights: Voice Control: Uses Speech-to-Text for hands-free research triggers. Multi-Agent Intelligence: Powered by CrewAI & Llama 3.3 (Groq) to find, verify, and summarize live web data. Voice Synthesis: Delivers an instant audio summary via ElevenLabs. Automated Export: Generates a professional PDF report automatically. Tech Stack: CrewAI, Groq, ElevenLabs, Streamlit, DuckDuckGo API.
1
90
0
I built a professional, end-to-end AI Receptionist system designed to automate clinic appointment management. This isn't just a chatbot; it's an AI Agent that can reason, use tools, and manage a live database autonomously. Key Contributions: Agentic Reasoning: Integrated CrewAI with Llama 3.3 (Groq) to enable the agent to understand complex user intents (Booking vs. Cancellation) and relative time (e.g., "next Tuesday at 3pm"). Autonomous Tool Use: Developed custom Python tools that allow the agent to verify real-time availability in a SQLite database and execute atomic transactions without human intervention. High-Performance Backend: Built a robust API using FastAPI to handle asynchronous requests between the AI agent and the database. Premium Dashboard: Designed a modern, Glassmorphic UI using Tailwind CSS that provides a real-time sync of the clinic’s schedule. The Result: A seamless, hands-free system that reduces administrative overhead by 100%, allowing clinic staff to focus on patients while the AI handles the entire scheduling lifecycle. Tech Stack: Python, CrewAI, Groq API, FastAPI, SQLite, Tailwind CSS
0
70
2
Developed a highly responsive AI Voice Agent using Vapi that handles real-time conversations with exceptional clarity. The agent is designed to engage users naturally, gather specific information during the call, and accurately extract that data for further use. The voice quality for both the user and the bot is seamless, making the interaction feel professional and human-like
2
130
Streamlit
(2)
Follow
Message
Bulbul Gupta
Indore, India
AI Automation & Chatbot Developer | Flutter Developer
38
Followers
Follow
Message
AI Automation & Chatbot Developer | Flutter Developer
4
Built an AI-powered resume analyzer that evaluates resumes and provides instant feedback to improve job success rates. The system analyzes resume content, structure, and keywords using AI to generate a score and actionable suggestions. It helps users optimize their resumes based on industry standards and ATS (Applicant Tracking System) requirements. This tool is designed for job seekers and professionals to enhance their resumes and increase their chances of getting shortlisted. "Open to building similar AI-powered tools for businesses". 🚀
4
237
1
I built an AI chatbot that can answer questions from PDFs in seconds 🤯 No manual search. Just ask and get instant answers.🤔🤔Companies struggle to search information across documents manually. It wastes time and reduces productivity.👍So I built a RAG-based AI chatbot that understands documents and gives accurate answers instantly. Tach stack :- Python, FastAPI, LangChain, OpenAI API, Vector Database (FAISS) Ask questions from PDFs Context-aware answers Fast semantic search Easy UI chatbot Scalable backend
1
129
1
Raksha - Women Safety & Emergency Alert App
1
1
0
This project demonstrates an AI chatbot that responds instantly to user queries and automates customer conversations. It is designed to save time, improve response speed, and capture leads without manual effort. The chatbot can be customized for websites, Instagram DMs, and other platforms based on business needs. Perfect for businesses looking to automate customer support and increase conversions.
0
354
Streamlit
(2)
Follow
Message
Ravish paul
Vadodara, India
AI Product Designer & Developer
9
Followers
Follow
Message
AI Product Designer & Developer
0
🚀 Ultimate AI Image Verifier Developed an AI-powered image verification system using CLIP and BLIP models to analyze whether a user-provided description matches an uploaded image. ✨ Features: AI image caption generation Image-text similarity verification Confidence score prediction Human-like explanation system Modern Streamlit interface 🛠️ Tech Stack: Python, Streamlit, PyTorch, CLIP, BLIP 🌐 Live Demo: https://image-text-verifier.streamlit.app/ 🔗 GitHub: https://github.com/paulkr-sketch/image_text_verifier
0
121
0
📄 AI PDF Chatbot (RAG + Gemini) Built an AI-powered PDF chatbot using LangChain, FAISS, HuggingFace Embeddings, and Google Gemini API. Users can upload PDFs and ask questions directly from document content using Retrieval-Augmented Generation (RAG). ✨ Features: PDF upload & parsing Semantic search with FAISS Gemini-powered responses Chat-style UI Modular architecture Streamlit deployment 🛠 Tech Stack: Python, Streamlit, LangChain, FAISS, HuggingFace, Gemini API 🌐 Live Demo: https://rag-pdf-chatbot-gemini.streamlit.app 🔗 GitHub: https://github.com/Ravish-sketch/RAG-pdf-chatbot
0
125
3
🎵 Introducing Aura Music — an AI-powered music streaming experience designed to make music discovery feel alive. For the Google Stitch Challenge, I wanted to explore how AI-native design tools can help transform a simple idea into an immersive product experience faster than traditional workflows. Using Google Stitch, I started with a text prompt and rapidly generated a complete mobile app concept. I then iterated on the design using Stitch's AI-powered in-place editing workflow, refined user flows, enhanced the visual experience, and created a futuristic interface focused on discovery, personalization, and interaction. ✨ Key Features: • AI DJ Assistant • Mood-Based Music Discovery • AI Playlist Generation • Dynamic Visual Experiences • Social Listening Rooms • Interactive Music Universe Exploration One of my goals was to align with the challenge theme, "Build interfaces that feel alive." The result is a modern music platform where users can discover music through immersive interactions rather than traditional browsing. 🔗 Project Link: https://stitch.withgoogle.com/projects/2340622733448831121 💭 Feedback on Google Stitch: My favorite part of Stitch was the speed of iteration. Being able to move from a simple prompt to a polished interface in minutes made experimentation much easier. The AI-powered generation and editing workflow allowed me to focus more on user experience, interaction design, and creativity rather than spending hours building layouts manually. Built with Google Stitch using AI-powered generation, rapid iteration, and interactive design workflows. Feedback is welcome! @stitchbygoogle #stitchchallenge #GoogleStitch #UIDesign #UXDesign #ProductDesign #AI #MusicApp #MobileDesign #CreativeTechnology #AppDesign
2
3
226
0
Designed and launched my AI/LLM portfolio website 🚀 Showcasing projects focused on: • RAG Systems • AI Applications • Browser Automation • Computer Vision • AI Workflows Built while exploring real-world AI product development, LLM systems, and autonomous AI tools. Currently learning and building in: Python • LLMs • AI Agents • Automation • NLP Excited to keep building and sharing more AI projects 🔥
0
81
Streamlit
(2)
Follow
Message
Karan Singh
Kangra, India
AI/ML Engineer crafting intelligent systems & AI solutions.
10
Followers
Follow
Message
AI/ML Engineer crafting intelligent systems & AI solutions.
0
In this project, I developed a Sentiment Analysis Web App using deep learning (CNN) and traditional models to classify text sentiment with high accuracy. The system includes a complete evaluation pipeline comparing CNN, LSTM, Logistic Regression, Random Forest, and Naive Bayes — analyzing performance across multiple iterations and datasets. Key Highlights: Built a Streamlit-based web app for real-time sentiment classification Developed and evaluated multiple models for accuracy and F1-score Created detailed analysis reports and prototype schematics Project here → GitHub Repository (https://github.com/Imkaran04/Sentiment_Analysis_Web_App/tree/main) Reports: Sentiment Analysis Report (PDF), Product Prototype Diagram Tech Stack: Python, Streamlit, TensorFlow/Keras, Scikit-learn, Matplotlib
0
43
0
Scientific Image Forgery Detection — Kaggle Competition Participated in the ongoing Kaggle competition on Copy-Move Forgery Detection in Scientific Images, aimed at identifying manipulated biomedical figures that can compromise research integrity. For this challenge, I developed a ResNet50 + U-Net hybrid segmentation model using PyTorch, designed to detect and segment forged regions at the pixel level. My approach combines Dice and Focal losses for balanced training, WeightedRandomSampling to oversample forged images, and Test-Time Augmentation (TTA) to improve prediction robustness. Achieved an initial score of 0.303 on the public leaderboard. I’m continuing to experiment with architecture tuning, learning rate schedules, and other loss functions to further enhance performance and generalization.
0
69
0
Introducing QuickSynopsis, a fully-featured AI-based summarization and text comparison web app designed for speed, simplicity, and scalability. This project lets users: Generate efficient, context-aware summaries for any text. Compare multiple Summaries to highlight key differences. Enjoy a responsive UI with user authentication. Built using Python (Flask), HTML/CSS/JS, and SQLite/MySQL, QuickSynopsis can easily be customized or deployed to your preferred cloud platform. Key Features: AI-powered summarization & text comparison Signup/login authentication Integrated payment gateway (customizable) Responsive, modern UI/UX Ready-to-deploy setup for Heroku, AWS, or local hosting Explore the repo: GitHub – QuickSynopsis-Version-Control (https://github.com/Imkaran04/QuickSynopsis-Version-control)
0
43
0
I recently fine-tuned the Mistral 7B Instruct model on a dataset of NDA (Non-Disclosure Agreement) documents — building an AI reviewer capable of identifying compliance issues and clause inconsistencies. To make the model more accessible, I converted the trained weights to CPU-compatible files, allowing efficient inference without GPU requirements. Model: Mistral 7B Instruct v0.1 Focus: Legal text review & semantic understanding Tech: PyTorch, Transformers, Kaggle Check out the full notebook here → [Kaggle Project Link (https://www.kaggle.com/code/karansingh123456/nda-reviewer-model-training)] My Kaggle account here → Profile (https://www.kaggle.com/curiouscyborgs) #AI #NLP #SentimentAnalysis #DeepLearning #CNN #LSTM #DataScience #GitHub
0
33
Streamlit
(1)
Follow
Message
DHANRAJ SHARMA
Mehsana, India
AI Automation Specialist — I build AI workflows that ship
New to Contra
Follow
Message
AI Automation Specialist — I build AI workflows that ship
0
Built during my Generative AI internship at SmartBridge. An AI assistant that combines computer vision with conversational LLMs — upload any vehicle image and get structured, detailed insights through a chatbot interface. Designed an image-to-insight pipeline using Gemini API vision models and prompt engineering, wrapped in an interactive Streamlit application that supports dynamic follow-up queries. Demonstrates multimodal AI, RAG-style retrieval, and real-time LLM interaction in a single product.
0
70
0
I build custom AI-powered contract analysis web applications that help users review contracts, identify risks, and generate clear recommendations in minutes. Using LangChain, RAG, Llama models, Hugging Face embeddings, Flask, and Docker, I create production-ready solutions that can analyze PDFs, DOCX files, and text documents, detect risky clauses, generate plain-English summaries, and provide structured risk scores. Perfect for LegalTech startups, law firms, procurement teams, HR departments, and founders looking to automate contract review workflows. Includes source code, deployment, customization, and post-launch support.
0
21
0
Built SiteScope AI, an AI-powered client intake and discovery call automation system using Make.com (http://Make.com), Google Gemini AI, Jina AI Reader, Tally, Google Sheets, Google Calendar, Gmail, and Google Meet. The system automatically processes client submissions, extracts and analyzes website content, generates business insights, creates discovery call strategy briefs, produces personalized recommendations, schedules meetings with automatic calendar invites, sends branded confirmation emails, and logs all data into a structured CRM. The automation eliminates manual pre-call research, scheduling, and follow-ups while enabling faster lead response times and fully prepared discovery calls within minutes of form submission.
0
29
1
Developed ReviewRadar, an AI-powered customer review monitoring and business intelligence system built with n8n, Google Gemini AI, SERPAPI, Google Sheets, Gmail, Slack, Twilio WhatsApp, and Looker Studio. The platform continuously collects Google Reviews, classifies sentiment, identifies complaint categories, assigns urgency scores, generates AI-powered response drafts, and instantly notifies stakeholders of critical feedback. Weekly executive summaries and interactive dashboards provide actionable insights into customer sentiment, review trends, top complaints, top praise, and business performance. The automation eliminates manual review monitoring while enabling proactive reputation management and faster customer response times.
1
108
Streamlit
(1)
Follow
Message
Anurag Nagare
Mumbai, India
I’m an AI & Machine Learning engineer with expertise in deve
Follow
Message
I’m an AI & Machine Learning engineer with expertise in deve
0
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
33
0
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
62
1
Everyone's racing to add biometrics to logins. Almost nobody's asking what happens when you can't — or shouldn't — touch the sensor. Shared kiosks, clinical settings, accessibility needs, hygiene-sensitive environments. Fingerprint readers and face unlock assume contact or a stored faceprint. Sometimes you want authentication that touches nothing and stores no biometric image of you at all. So I built GestureAuth — a contactless authentication system where your "password" is a sequence of hand gestures performed in front of a standard webcam.
1
9
0
Everyone's talking about AI in healthcare. Nobody's building low-cost tools for the people who actually need early answers. Neurologists are overbooked. Clinical tremor assessments require in-person visits, specialist equipment, and months of waiting. The 10 million people living with Parkinson's globally and the millions more who don't yet know have no accessible way to flag early symptoms from home. So I built TremorLens a real-time hand tremor detection tool that runs entirely on a standard webcam. Here's what makes it more than just a webcam project: Instead of simple motion detection, I built a full signal processing pipeline on top of computer vision. MediaPipe tracks 21 hand landmarks per frame. The index fingertip's x/y displacement is buffered across a 3-second rolling window. scipy FFT then decomposes that signal into its frequency components and flags dominant activity in the 4–6 Hz range clinically associated with Parkinson's resting tremors. The live overlay shows you everything: → Real-time FFT power spectrum with the tremor zone highlighted → Dominant frequency readout in Hz with a 10-frame rolling average for stability → Color-coded STABLE / TREMOR DETECTED indicator → Fingertip displacement graph and movement trail → Auto-saved CSV session log timestamp, frequency, amplitude, tremor flag every session
0
13
Streamlit
(2)
Follow
Message
Explore people