Skip to content
View IvayloP0709's full-sized avatar

Block or report IvayloP0709

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

Pinned Loading

  1. langchain-pdf-rag langchain-pdf-rag Public

    Retrieval-Augmented Generation (RAG) system for PDF documents using LangChain. Enables intelligent question-answering over PDF content by combining document retrieval with large language models for…

    Python

  2. llm-router llm-router Public

    A cost-optimized LLM routing system that uses an XGBoost classifier to automatically route queries to the cheapest suitable model (gemini-flash, gpt-4o, or o3-mini) based on 37 NLP features — savin…

    Python

  3. review-rating-classifier review-rating-classifier Public

    MSc Data Science and Society thesis project investigating NLP techniques for automated review rating prediction. Developed at Tilburg University, exploring sentiment analysis and rating classifica…

    Python

  4. Cancer-Classification-CNN Cancer-Classification-CNN Public

    Deep learning approach to cancer image classification using three CNN architectures: two custom networks and one transfer learning implementation. Demonstrates multiclass classification for medica…

    Python 1

  5. Sentiment-Analysis-using-VADER-and-roBERTa Sentiment-Analysis-using-VADER-and-roBERTa Public

    Comparative study of sentiment analysis techniques using VADER (rule-based) and roBERTa (transformer-based) models. Demonstrates the performance differences between traditional and deep learning a…

    Jupyter Notebook

  6. dispute-automation dispute-automation Public

    CLI pipeline that automates Stripe chargeback responses: collects evidence from Stripe/PostHog/Resend/Gmail, drafts a rebuttal with Claude, and submits after human approval.

    Python