Freelancers using Streamlit in Delhi

Freelancers using Streamlit in DelhiFreelancers using Streamlit in Delhi

Projects People

Trashu Vashisth

Building Production-Grade AI Agents & RAG Systems

14: Followers

Building Production-Grade AI Agents & RAG Systems

Cover image for The Problem: Sales teams waste 60%

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

84

Cover image for An autonomous AI system that

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

111

Cover image for I built a professional, end-to-end

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

99

Cover image for Developed a highly responsive AI

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

157

Python & Django developer for web apps and APIs

New to Contra

Python & Django developer for web apps and APIs

Cover image for Built a Python-powered automated trading

Built a Python-powered automated trading tool that pulls live market data, runs technical analysis, and generates real-time trade signals. Features normalized comparison charts across multiple assets (Nifty, USD Index, Brent Crude, US 10Y Yield), a macro pressure table, correlation analysis, and a portfolio helper. Backend built in Python with automated data pipelines, live market feeds, and signal interpretation logic that flags bullish/bearish pressure. Clean, data-dense dashboard for fast decision-making. Tech: Python, Pandas, REST APIs, data automation, real-time charting.

1

95

Cover image for Hit a classic Django trap

Hit a classic Django trap this week and figured it's worth sharing since so many people are running into it now. I was adding an LLM feature to a Django app. The AI call takes a few seconds, so naturally I made the view async so it doesn't block a worker while waiting. Wrote the async view, called the ORM like I always do, and boom: SynchronousOnlyOperation: You cannot call this from an async context. Turns out Django's ORM can't just be called normally inside async code. The classic sync API isn't safe in an event loop, so Django protects it and throws this error instead. The fix is simpler than most people think. Since Django 4.1 the ORM has async versions of everything, same names with an "a" prefix. So objects.get() becomes await objects.aget(), create() becomes acreate(), save() becomes asave(). For loops over querysets, async for works directly. And for old sync code or third party libraries you can't change, wrap them with sync_to_async(). Why this matters right now: everyone is bolting AI features onto Django apps, and LLM calls are exactly the slow I/O that async is made for. Which means a lot of devs who never touched async Django are suddenly hitting this error for the first time. One honest caveat: transactions still don't fully work in async mode, so if you need atomic blocks, keep that path sync and wrap it. Anyone else made the jump to async views yet, or still happily on WSGI?

0

84

Cover image for An AI-driven trading engine that

An AI-driven trading engine that analyzes 200-DMA breakouts and real-time market sentiment to generate long/short recommendations. It scans 1,500+ NSE stocks in under 2 seconds and uses generative AI to build option strategies, delivering event-driven trade signals end-to-end. I built the full Django backend, async APIs, and the signal-generation logic. Accomplishments and responsibilities: Built an AI-driven trading engine analyzing 200-DMA breakouts and market sentiment, generating long/short signals with ~70% directional accuracy — outperforming baseline strategies by 35%; Integrated generative-AI insights for automated option-strategy creation (spreads, straddles, condors), improving Sharpe ratio by 1.6× and cutting manual analysis time by 60%; Developed a Django backend with async APIs scanning 1,500+ NSE stocks in under 2 seconds, achieving 40% lower latency with event-driven alerts.

0

74

Cover image for An AI-powered news platform that

An AI-powered news platform that delivers concise, real-time AI-industry updates to 2,500+ active users. It scrapes and aggregates 500+ sources daily, removes duplicates, and uses generative-AI summarization to cut reading time significantly while surfacing the most relevant stories. I built the backend responsible for scraping, deduplication, and the LLM summarization pipeline.

0

76

AI & ML Solutions for Real-World Impact 🌐

AI & ML Solutions for Real-World Impact 🌐

Cover image for Comment Feel - YouTube Comments Sentiment Analyzer Tool

Comment Feel - YouTube Comments Sentiment Analyzer Tool

0

27

Cover image for 🤖 MediBot AI – AI-Powered Medical Chatbot

🤖 MediBot AI – AI-Powered Medical Chatbot

0

10

Cover image for Dish Decode- Flask Based API for Recipe Extraction from video

Dish Decode- Flask Based API for Recipe Extraction from video

0

4

Placeholder project card media

View more →

Gurugram, India

Power BI & ML Expert | Dashboards & Predictions

Power BI & ML Expert | Dashboards & Predictions

Cover image for Movie Recommendation System using Machine Learning

Movie Recommendation System using Machine Learning

0

3

Cover image for Power BI Dashboard for Binge and Bash

Power BI Dashboard for Binge and Bash

0

8

Cover image for PUBG Game Winner Prediction with Machine Learning

PUBG Game Winner Prediction with Machine Learning

0

4

Placeholder project card media

View more →

AI Automation Expert | Agents · Workflows · Chatbots

New to Contra

AI Automation Expert | Agents · Workflows · Chatbots

Cover image for Presented ML-based anomaly detection and

Presented ML-based anomaly detection and SLA prediction systems to senior stakeholders at DXC. Built using XGBoost and Random Forest — the SLA prediction model achieved 0.1% variance in forecast accuracy. Currently under patent review as a first-of-kind application of predictive ML in backup operations.

1

51

Cover image for Running a 100-day LinkedIn series

Running a 100-day LinkedIn series telling the complete story of AI — from Alan Turing in 1950 to modern agents and LLMs. One person, one paper, or one breakthrough per day. Written for business leaders and professionals who want the real story without the jargon. 11 days in and counting.

1

48

Cover image for Natural Language Workflow Editing Title:

Natural Language Workflow Editing Title: "Editing AI Workflows Using Chat" Description: "Demo of RAPR AI's chat-based workflow editor — modifying a live workflow and adding nodes through natural language. No manual config, just conversation.

1

63

Cover image for Built RAPR AI from scratch

Built RAPR AI from scratch as a personal project. It's a desktop application that lets you chain Claude, Gemini, and local models into automated workflows without any extra API costs. Includes a skill marketplace, Telegram integration, shared memory across models, and self-fixing agent loops. Open source and live at raprai.com (http://raprai.com).

1

52

AI Engineer building custom RAG chatbots & automation

New to Contra

AI Engineer building custom RAG chatbots & automation

Cover image for Designed and developed a custom

Designed and developed a custom AI analytics dashboard for Globe Spring to provide real-time business insights and performance tracking. The platform aggregates sales, customer, and operational data into a single interactive dashboard with AI-powered recommendations and automated reporting. This solution helps decision-makers monitor KPIs, identify trends, and make faster data-driven decisions.

0

40

Cover image for Designed and developed scalable AI-powered

Designed and developed scalable AI-powered APIs that connected Globe Spring's applications, databases, and internal systems. The integration enabled intelligent search, personalized recommendations, chatbot functionality, and automated workflows through secure REST APIs and LangChain orchestration.

0

45

Cover image for Developed an AI-powered workflow automation

Developed an AI-powered workflow automation system for Globe Spring using n8n, Zapier, and OpenAI to automate order processing, email notifications, and CRM updates.

0

50

Cover image for Personalized AI Chatbot for Globe

Personalized AI Chatbot for Globe Spring

1

65

Developer building AI-powered and scalable digital solutions

New to Contra

Developer building AI-powered and scalable digital solutions

Cover image for RAG-Based PDF Q&A AI System

RAG-Based PDF Q&A AI System

0

46

Cover image for Multi-Agent AI Research System

Multi-Agent AI Research System

0

40

Cover image for Voice-Based AI Learning Platform

Voice-Based AI Learning Platform

0

41

Cover image for AI-Powered Gadget Recommendation Agent

AI-Powered Gadget Recommendation Agent

0

51

Python | AI/ML | Data Analytics | Web Development

New to Contra

Python | AI/ML | Data Analytics | Web Development

Cover image for SkinScan AI

0

0

Cover image for Infectious Disease Analysis

Infectious Disease Analysis

0

0

Cover image for Student Performance Management

Student Performance Management

0

1

Cover image for Heart Disease Risk Predictor App Development

Heart Disease Risk Predictor App Development

0

0