Alexey Grigorev

data-science-interviews. Data science interview questions and answers

mlbookcamp-code. The code from the Machine Learning Bookcamp book

llm-rag-workshop. Chat with your own data - LLM+RAG workshop

workshops. One repository for some of the workshops I'm giving

build-your-own-search-engine. Code for the "Build Your Own Search Engine" workshop

datascience-recruitment-challenges. Home assignments for data science positions

outbrain-click-prediction-kaggle. Solution to the Outbrain Click Prediction competition

libftrl-python. FTRL-Proximal with python bindings

libffm-python. A Python wrapper for LibFFM

clothing-dataset. Closing dataset, all classes

vimeo-download. Python

fitness-assistant. This is your friendly fitness assistant, which is a RAG applications built as a part of LLM Zoomcamp

minsearch. Minimalistic text and vector search engines that use Scikit-Learn and Pandas

avito-duplicates-kaggle. Solution for Avito Duplicate Ads Detection competition

clothing-dataset-small. Clothing dataset, 10 classes

unpossibly-instagram-challenge. Predicting the number of likes an instagram post will receive in 24 hours - winning solution

alexeygrigorev.

rag-agents-workshop. From RAG to Agents: Building Smart AI Assistants

lightweight-mlops-zoomcamp. A stripped-down version MLOps Zoomcamp (1.5 hours workshop)

toyaikit. Minimalistic implementation for LLM-based chat assistants with Tool Use (function calling) and MCP

nips-ad-placement-challenge. The winning solution to the Ad Placement Challenge (NIPS'17 Causal Inference and Machine Learning Workshop)

leetcode-solutions. My solutions to some of leetcode challenges

data-engineering-rag. Data Engineering Zoomcamp course repository RAG

cikm-cup-2016-cross-device. Solution for the Cross-Device linking challenge from CIKM CUP 2016

serverless-deep-learning. Example from my "Serverless Deep Learning" talk

aws-lambda-docker. Using AWS Lambda with Docker to deploy a deep learning model

classifying-crisis-reports-dsc. The top 10 solution to the "Growing Instability: Classifying Crisis Reports" challenge

tensorflow-protobuf. Protobuf files from TensorFlow without TensorFlow

kubeflow-deep-learning. Deploying a Keras model with KServe (formerly KFServing) and EKS

mlbookcamp-page. The webpage for ML Bookcamp

mastering-java-data-science. The code for the book "Mastering Java for Data Science"

wsdmcup17-vandalism-detection. The 2nd place solution for WSDM Cup 2017: Vandalism Detection

hands-on-mlops-workshop. MLOps Hands-on Guide: From Training to Deployment and Monitoring: A day long workshop about MLOps

keras-image-helper. A lightweight library for pre-processing images for pre-trained keras models

tflite-aws-lambda. Compiled TF-Lite for AWS Lambda

deep-learning-keras-aws-lambda. Jupyter Notebook

warc-extractor. Extract text information from warc files

student-acceptance-project. Building a model for predicting whether a student will be admitted to college. Done as a part of Project of the Week at DataTalks.Club

datasets. different datasets for private and public use

kids-horror-stories-ru. Страшилки для детей на русском

java-vk-oauth20. OAuth 2.0 interface for interacting with VK

clickbait-challenge. The 3rd place solution to the clickbait challenge

ml-engineering-contsructor-workshop. The two days ML engineering workshop for constructor

product-recommendation. Experimenting with recommender system techniques as a part of the project-of-the-week at DataTalks.Club

projects. Various projects

toloka-data-collection. Jupyter Notebook

kubernetes-deep-learning. Deployng a Keras model with TF-Serving and EKS

alexeygrigorev.github.io. My website

aihero. HTML

large-datasets. A bunch of large datasets that I don't want to put in the other dataset repo

competitions. Finished but not cleaned stuff - for my future reference

mlops-zoomcamp-2025. Jupyter Notebook

lld-lead-scoring. LLM-Driven Development for Machine Learning - lead scoring project

avito-page-view-prediction-boosters. Solution for Avito Page View prediction competition (Avito BI contest task 3 on boosters)