LLM-driven automated knowledge graph construction from text using DSPy and Neo4j.

LLM Analytics

Finds Instagram location IDs near a specified latitude and longitude.

Open Source Intelligence gathering tool aimed at reducing the time spent harvesting information from open sources.

RAG with knowledge graphs implemented from scratch

Kolmogorov Arnold Networks

the AI-native open-source embedding database

Conference talk: from zero to your first LLM application

Near Duplicate Video Detection (Perceptual Video Hashing) - Get a 64-bit comparable hash-value for any video.

This projects contains different conformal methods and approaches. Includes code generated for a experimental evaluation of a multidimensional, low-sample size biomedical dataset of oncological sub…

Demo data repository (crime statistics)

Windows inside a Docker container.

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.

[ACM Computing Surveys'23] Implementations or refactor of some temporal link prediction/dynamic link prediction methods and summary of related open resources for survey paper "Temporal Link Predict…

A Library for Dynamic Graph Learning (NeurIPS 2023)

Langchain + Docker + Neo4j + Ollama

👑 Multivariate exploratory data analysis in Python — PCA, CA, MCA, MFA, FAMD, GPA

🔎 Most Advanced Open Source Intelligence (OSINT) Framework for scanning IP Address, Emails, Websites, Organizations.

You can get here the greatest collection of my personal book summaries

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

Dark Web OSINT Tool

Run your GitHub Actions locally 🚀

Generating and Imputing Tabular Data via Diffusion and Flow XGBoost Models

Tookie is a advanced OSINT information gathering tool that finds social media accounts based on inputs.

Fast, accurate and scalable probabilistic data linkage with support for multiple SQL backends

Hummingbird compiles trained ML models into tensor computation for faster inference.

Generate Diverse Counterfactual Explanations for any machine learning model.