Skip to content
View AaricaMatrix's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report AaricaMatrix

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 is supported. This note will only be visible to you.
Report abuse

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

Report abuse
AaricaMatrix/README.md
Aarica Raj




About Me

coding gif

classAaricaRaj:
def__init__(self):
self.role="Data Science & AI"self.education="BCA; 2nd Year Undergraduate"self.location="Jamshedpur, India"self.contact="shrivastavarchana57@gmail.com"self.domain= ["Data Analytics", "NLP", "RAG Systems",
"Deep Learning", "MLOps", "Multimodal AI"]
self.stack= {
"languages" : ["Python", "SQL", "MySQL",
"JavaScript (basic)"],
"data_analytics" : ["Pandas", "NumPy", "Matplotlib",
"Seaborn", "Excel", "Power BI basics"],
"ai_ml" : ["LLMs", "RAG", "Transformers",
"Computer Vision", "Generative AI"],
"frameworks" : ["LangChain", "HuggingFace", "PyTorch",
"Scikit-learn", "Flask", "Gradio"],
"vector_search" : ["FAISS", "all-MiniLM-L6-v2",
"Semantic Embeddings"],
"cloud_apis" : ["Azure AI", "HuggingFace Spaces",
"Groq API", "Gemini API", "REST APIs"],
"mlops" : ["Docker", "Git", "GitHub",
"Jupyter", "Google Colab"],
}
defcurrent_focus(self):
return [
"Data analysis with Python, SQL and visualization tools",
"Prepping for Data Analyst roles; EDA, dashboards, storytelling",
"Production RAG pipelines; FAISS + LangChain + Groq",
"Fine-tuning DistilBERT and RoBERTa for NLP tasks",
"End-to-end MLOps: train, containerize, deploy, monitor",
]
defopen_to(self):
return [
"Data analytics projects and collaborations",
"AI/ML research and open-source contributions",
"Transformer fine-tuning and RAG systems",
"Student researcher and internship opportunities",
]


Technical Stack

Data Analytics & Visualization

AI / ML & Deep Learning

NLP, LLMs & Generative AI

Web, Deployment & MLOps

Cloud & APIs


Tech Stack Orbit

Tech Orbit


Featured Projects

AI-powered carbon footprint platform; Hackathon build

FastAPIScikit-learnGroq AIPythonAnomaly Detection

  • Predicts carbon footprint using ML models built with scikit-learn
  • Groq AI integration for real-time eco insights and an EcoBot coach
  • Anomaly detection to flag unusual emission patterns
  • Full FastAPI backend; built end-to-end for a hackathon

EcoTrack

Ask questions over any PDF using semantic search + LLM

LangChainFAISSHuggingFace EmbeddingsPythonGradio

  • Full RAG pipeline: PDF ingestion, FAISS vector store, semantic retrieval, LLM answer generation
  • Uses HuggingFace embeddings for document understanding
  • Clean Gradio UI; ask anything over your own documents
  • Deployed on HuggingFace Spaces

RAG Chatbot

Transformer fine-tuning for emotion and sentiment classification

DistilBERTDistilRoBERTaHuggingFacePython

  • Fine-tuned DistilRoBERTa for 7-class emotion classification; 91.3% accuracy on held-out test set
  • Fine-tuned DistilBERT separately for binary sentiment
  • Real-world use cases: product review analysis, social media monitoring
  • Deployed as a live HuggingFace Space

Sentiment

End-to-end ML with Docker and a 3D particle UI

PythonFlaskDockerRandom ForestREST API

  • Random Forest classifier wrapped in a Flask REST API and containerized with Docker
  • Covers the full ML lifecycle: data prep, training, API deployment, cloud delivery
  • Ships with a 3D particle effects UI; not your average Iris project!

MLOps

3D neural network you control with your hands; no install needed

Three.jsMediaPipe HandsWeb Audio APIWebGLHTML

  • Real-time 3D neural network visualization controlled entirely by hand gestures
  • Uses MediaPipe for hand tracking and Web Audio API for sound interaction
  • Runs 100% in the browser; no backend, no install
  • Also responds to claps and snaps via microphone input

Quantum AR

A browser game built with pure HTML, CSS and JS

JavaScriptCSSHTMLCreative Coding

  • A fully playable game inspired by the Suzume universe
  • Built with vanilla JS and CSS animations; no frameworks
  • Focuses on smooth interactions and creative browser-based experience

Suzume

Neon tube cursor animation using WebGL

Three.jsWebGLJavaScriptCanvas

  • A mesmerizing neon tube effect that follows your mouse in real time
  • Built with Three.js and WebGL for smooth GPU-accelerated rendering
  • Most starred repo; 2 stars and counting!

TubesCursor

Math-inspired generative art with Python's Turtle library

PythonTurtle GraphicsGenerative ArtMath

  • A collection of complex geometric patterns and animations
  • Covers physics simulations, math-art and procedural generation
  • Great starting point if you want to explore creative coding with Python

TurtleAnimations

Multimodal AI; Vision Transformer + BERT

BLIPVision TransformerBERTPyTorchHuggingFace

  • Salesforce BLIP implementation; 247M parameters combining a ViT encoder with BERT decoder
  • Supports both prompt-guided and unconditional captioning
  • Explores cross-modal attention between visual and text representations

BLIP



More on GitHub!


Visit Profile


Project Timeline

Project Timeline


RAG Pipeline Architecture

RAG Architecture


Impact & Numbers

Stats

MetricValueWhat it means
Live AI Systems4+Deployed on HuggingFace Spaces and PythonAnywhere
Best Model Accuracy91.3%DistilRoBERTa fine-tuned for 7-class emotion classification
Latency Reduction60xRAG pipeline dropped from 30s+ to ~0.5s with Groq
Model Scale247M paramsSalesforce BLIP multimodal implementation
CertificationAzure AIMicrosoft certified; 2025
Vector SearchFAISSSemantic retrieval on custom document corpora

Skill Proficiency

Skill Bars


Education & Certifications

DegreeInstitutionStatus
Bachelor of Computer Applications (BCA)Jamshedpur2nd Year (Ongoing)

CertificationIssuer
Azure AI FundamentalsMicrosoft

GitHub Analytics


Let's Build Together



Connect


🔗 Professional

LinkedInHuggingFace

💻 Development

GitHubLive Project

📧 Contact

Email


📧Email | 📍 Jamshedpur, India 🇮🇳


🔭 Currently building: Data analytics skills; SQL, EDA, dashboards, storytelling with data. Also building RAG systems and fine-tuning transformers on the side!

💡 Philosophy:Understand the data first; then let the model do the talking.

⭐ If my projects helped you, a star means a lot!


Snake


Pinned Loading

  1. mlops-pipelinemlops-pipelinePublic

    🌸 Iris Flower Species Predictor : End-to-end MLOps pipeline with Random Forest ML model, Flask REST API, and Docker containerization. Features a stunning 3D UI with particle effects. Deployable on …

    CSS 1