Skip to content
View tahirkorma's full-sized avatar
1 follower · 0 following

Block or report tahirkorma

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
tahirkorma/README.md

👋 Hi there, I'm Tahir Korma!

Welcome to my GitHub profile! I'm a Data Science enthusiast passionate about turning data into meaningful insights. I enjoy solving real-world problems using core techniques in Statistics and Machine Learning, advanced methods in Natural Language Processing, Deep Learning, and Generative AI, and modern AI Frameworks such as LangChain, LangGraph, and Agentic AI. I focus on building intelligent systems that can reason, plan, and interact autonomously.

🧠 What I Know

  • Languages: Python, SQL, R
  • ML & DS Tools: Scikit-learn, Pandas, NumPy, Matplotlib, Seaborn, NLTK, Statsmodels
  • ML Techniques: Regression, Classification, Clustering, Causal Inference, NLP
  • Deep Learning & Generative AI: PyTorch, Keras, LLMs, RAG systems
  • AI Frameworks: LangChain, LangGraph, Agentic AI
  • Web & Deployment: Streamlit, Flask, Pickle, Git/GitHub
  • Other Tools: Jupyter, VS Code, Google Colab, Excel, Tableau

🛠️ Projects I'm Proud Of

🎥 YouTube RAG Q&A with Google Gemini

Interactive app that answers questions about YouTube videos using their transcripts, powered by a RAG pipeline with FAISS embeddings and Google Gemini LLM.

🔍 Skilled Manager Intervention Analysis

Causal inference using OLS regression to estimate impact of skilled management interventions.

📩 Spam Detector

Email spam classifier using Multinomial Naive Bayes, deployed with Streamlit.

🎬 Movie Recommender

Content-based movie recommendation engine using NLTK lemmatization and cosine similarity.

🌍 Atmospheric Gas Clustering

Unsupervised learning on Mauna Loa gas data using PCA and K-Means clustering.

📈 What I'm Learning Now

  • Deep Learning with PyTorch
  • Time Series Forecasting
  • Docker for ML model deployment

Thanks for stopping by! 🚀

Pinned Loading

  1. langgraph-chatbot langgraph-chatbot Public

    A LangGraph-powered chatbot with threading, streaming, and SQLite vector DB for semantic search. Includes tools for web search, calculator, and stock prices, with a Streamlit UI for better UX. Inte…

    Python

  2. rag-youtube-assistant rag-youtube-assistant Public

    Interactive YouTube Q&A app using Retrieval-Augmented Generation (RAG) and Google Gemini LLM. Ask questions about video transcripts and get accurate answers powered by AI in a simple Streamlit inte…

    Jupyter Notebook

  3. langchain-models langchain-models Public

    A modular LangChain-based repository integrating Chat Models, traditional LLMs, and Embedding Models from OpenAI, Anthropic, Google, Hugging Face, and Local Inference. Built with the latest LangCha…

    Python 1

  4. movies_recommender movies_recommender Public

    Content-based movie recommender with NLTK and cosine similarity via Streamlit

    Jupyter Notebook

  5. skilled-manager-intervention-analysis skilled-manager-intervention-analysis Public

    Causal Inference project analyzing the impact of skilled manager interventions using OLS regression

    R

  6. spam-detector spam-detector Public

    Spam detection using Multinomial Naive Bayes, deployed via Streamlit with pickle model

    Jupyter Notebook