Skip to content
View feuerstrahll's full-sized avatar
6 followers · 4 following

Achievements

Achievement: YOLOAchievement: Pull Shark

Achievements

Achievement: YOLOAchievement: Pull Shark

Block or report feuerstrahll

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.

Content in all repositories owned by your account will be closed.
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
feuerstrahll/README.md

Hi, I'm Anastasiia 👋

🔭 My work explores how data and AI can help people better understand, navigate, and use complex information
🌱 Right now, I’m diving deeper into RAG, NLP, retrieval, and LLM-powered applications
🌍 I’m drawn to ideas where technology can make knowledge more accessible, useful, and meaningful for people

🛠️ Tech Stack

Core AI & Deep Learning

Python
Python 		PyTorch
PyTorch 		NumPy
NumPy 		scikit-learn
scikit-learn 		Hugging Face Transformers
Hugging Face
(Transformers)

NLP & LLM

Hugging Face
Hugging Face 		spaCy
spaCy 		LangChain
LangChain 		Qdrant
Qdrant 		Ollama
Ollama

Data, MLOps & Deployment

pandas
pandas 		PostgreSQL
PostgreSQL 		FastAPI
FastAPI 		Docker
Docker

Focus

Applied Machine Learning · Natural Language Processing · LLMs · RAG · OCR · Document AI · Computer Vision · PDF Processing · Information Extraction · Semantic Search

📌 Projects

🤖 AI Agent for Construction & Financial Document Verification — document processing, rule-based validation, LLM tool calling, secure enterprise workflows

🔎 RAG for Technical Documentation — structure-aware chunking, metadata enrichment, hybrid retrieval, retrieval evaluation

🎬 Movie Recommendation System — hybrid recommendation, embeddings, LightFM, FAISS, end-to-end ML pipeline

🗂️ OMNI Protocol Planner — healthcare-oriented backend and structured workflow automation

🧠 Mental Health App — ML-powered application with Python backend

Pinned Loading

  1. feuerstrahll feuerstrahll Public

  2. recommendation-system-movies recommendation-system-movies Public

    Movie recommender exploring content-based, collaborative (LightFM), and hybrid filtering on TMDB + MovieLens — with PostgreSQL/SQLite ETL and offline evaluation

    Python 1

  3. contextual-lexical-graph contextual-lexical-graph Public

    A Contextual Lexical Knowledge Graph and Adaptive Practice System. Models word-sense substitutability, grammar frames, and register shifts using WordNet + spaCy. Features a deterministic "Why Not?"…

    Python

  4. mental_health_app mental_health_app Public

    Mental Health Companion is a pilot mobile app that combines a chatbot and a mood diary to support users' emotional well-being.

    Dart

  5. OMNI-be-protocol-planner OMNI-be-protocol-planner Public

    An MVP assistant for planning bioequivalence (BE) studies

    Python