Skip to content
View Vaish-d30's full-sized avatar

Block or report Vaish-d30

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Vaish-d30/README.md

Hi, I'm Vaishnavi πŸ‘‹

Final-year Artificial Intelligence & Data Science student passionate about building practical AI systems that combine machine learning, data analysis, and generative AI technologies.

I enjoy solving real-world problems using data-driven approaches and developing intelligent applications powered by modern ML and LLM frameworks.

Currently exploring areas such as Retrieval-Augmented Generation (RAG), machine learning systems, and AI-powered automation.


πŸ”§ Tech Stack

Programming

Python, SQL

Machine Learning

Supervised & Unsupervised Learning
Classification, Regression, Clustering
Anomaly Detection
Feature Engineering
Model Evaluation & Prediction

Data Analysis & Visualization

Pandas
NumPy
Matplotlib
Seaborn
Tableau

Generative AI

RAG Pipelines
Embeddings
Prompt Engineering
LLM Workflows (Gemini API)

Tools & Frameworks

Scikit-learn
LangChain
Streamlit
Gradio
Flask (basic)

Infrastructure & Systems

Docker
Apache Kafka
Zookeeper
AWS (EC2, S3 – basic)


πŸš€ Featured Projects

AI Anomaly Detection & Automated Response System

  • Built ensemble anomaly detection model using Random Forest, XGBoost, and Isolation Forest
  • Achieved ~96% accuracy with only 4 false positives
  • Performed preprocessing, feature engineering, scaling, and model comparison
  • Integrated ML pipeline with database-backed automated response system
  • Developed Streamlit interface for real-time anomaly monitoring

RAG-Based AI Document Assistant

  • Built a Retrieval-Augmented Generation (RAG) system using Python and Google Gemini to answer questions from PDF documents.
  • Implemented document ingestion, text chunking, embedding generation using SentenceTransformers, and semantic retrieval using ChromaDB.
  • Designed a retrieval pipeline that fetches relevant document chunks and generates grounded responses with source citations.
  • Evaluated retrieval quality using multiple test queries.

Document Data Extraction Tool

  • Developed Python pipeline to extract structured data from PDFs
  • Converted results into Excel/CSV automatically
  • Built lightweight Gradio interface for user interaction

Business Data Dashboard

  • Built interactive Tableau dashboard for KPI monitoring
  • Implemented SQL-based data extraction and transformation
  • Designed visual analytics for trend analysis and performance tracking

πŸ“š What I'm Currently Learning

  • Advanced Retrieval-Augmented Generation systems
  • Vector database optimization
  • ML system design & deployment
  • Scalable AI application architectures

🎯 Career Interests

I am currently looking for opportunities in:

  • Data Science
  • Machine Learning Engineering
  • AI Engineering
  • Generative AI / LLM Applications

πŸ“« Connect With Me

LinkedIn
https://linkedin.com/in/vaishnavi-sunil-desai

Email
vaishnavidesai3028@gmail.com

Pinned Loading

  1. AI-Based-Anomaly-Detection-Automated-Response-System-For-Cyber-Defense AI-Based-Anomaly-Detection-Automated-Response-System-For-Cyber-Defense Public

    AI-powered cyber defense system that detects anomalies using ensemble ML models and triggers automated response workflows, with real-time monitoring via a Streamlit dashboard.

    Python

  2. RAG-Based-AI-Document-Assistant- RAG-Based-AI-Document-Assistant- Public

    RAG-based AI document assistant for semantic search and question answering over PDFs. Uses SentenceTransformers for embeddings, ChromaDB for vector retrieval, and Google Gemini to generate grounded…

    Jupyter Notebook