8000 GitHub - dhruvsh1997/dhruvsh1997
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

dhruvsh1997/dhruvsh1997

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

25 Commits
Β 
Β 

Repository files navigation

Myself Dhruv Sharma, Welcome to my Profile πŸ‘‹

πŸš€ AI Engineer | Machine Learning | Generative AI | MLOps | Deep Learning | IoT | Agentic AI | LLM | CI/CD

πŸ“ AI Researcher & Developer specializing in cutting-edge AI-driven solutions, NLP, Computer Vision, and scalable MLOps pipelines.

Profile Views


πŸ“Š Dashboard Overview


πŸ”Ή About Me

  • πŸŽ“ AI & Machine Learning Specialist with expertise in Generative AI, Agentic AI, and MLOps
  • πŸ’» Skilled in Python, Django, Flask, Streamlit, LangChain, Hugging Face, YOLO, Stable Diffusion, BLIPs2, WhisperX, T5
  • πŸš€ Experience in Developing AI-Powered Chatbots, NLP Applications, and Advanced Computer Vision Systems
  • πŸ“ˆ Expertise in AI Model Deployment, Cloud-based ML Pipelines (AWS, GCP, Azure), MLflow, CI/CD, and Docker
  • πŸ›  Passionate about AI-powered automation, intelligent system design, and enterprise AI integration
  • πŸ“š Always learning & building scalable AI and backend solutions with real-world impact

πŸ† Key AI Projects & Contributions

1️⃣ Agentic AI-Based Self-RAG Chatbot with Role-Based Authentication

  • Developed an Advanced Self-Retrieval-Augmented Generation (Self-RAG) chatbot using LangChain, Langraph, MLflow, and Django.
  • Supports multi-modal query handling (text, images, tables, flowcharts) extracted from PDFs.
  • Integrated Web Scraping with Selenium to retrieve real-time referenced data from URLs.
  • Implemented Role-Based Access Control (RBAC) for user authentication and document access.

2️⃣ Computer Vision & Generative AI Models

  • Built Advanced Computer Vision projects including:
    • Text-to-Image Generation models with Stable Diffusion, Pix2Pix, and Transformer-based architectures
    • AI-driven Image Captioning system using BLIP2 and vision-language models
    • Real-time Object Detection and Semantic Segmentation using YOLO and OpenCV
  • Enabled context-aware image descriptions with advanced multi-modal learning techniques

3️⃣ Meeting Video Processing & AI-Based Report Generation

  • Created an AI-powered meeting analytics system using YOLO (face detection), WhisperX (transcription), T5 (summarization), and Llama 3.3 (context analysis).
  • Implemented Emotion and Sentiment Detection for assessing speaker tone.
  • Automated Report Generation and Delivery via Google Cloud API.
  • Built with Django, Django Celery for background processing, and Streamlit for interactive visualization

4️⃣ Web Scraping & Data Intelligence

  • Developed Comprehensive Web Scraping Frameworks using:
    • Selenium for dynamic web content extraction
    • BeautifulSoup for HTML parsing
    • Scrapy for large-scale web crawling
  • Created intelligent data collection pipelines with data cleaning and transformation techniques
  • Implemented ethical web scraping practices respecting robots.txt and site policies

5️⃣ Cybersecurity Insights

  • Basic Anomaly Detection Models for network security
  • Explored Machine Learning techniques in preliminary threat analysis
  • Demonstrated foundational understanding of security-driven AI approaches

πŸ›  Tech Stack & Tools

Category Technologies
Languages Python JavaScript
Web Frameworks Django Flask Streamlit
Computer Vision OpenCV YOLO
Databases PostgreSQL SQLite
AI & ML Hugging Face LangChain Stable Diffusion
Data Processing Pandas NumPy
MLOps & Deployment MLflow Docker AWS

πŸ“Š GitHub Contribution Activity

Dhruv's Activity Graph


πŸ“« Connect with Me


🎯 "Transforming Industries with Intelligent AI Solution" πŸš€

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published
0