Tomaz Bratanic

blogs. Jupyter notebooks that support my graph data science blog posts at https://bratanic-tomaz.medium.com/

langchain2neo4j. Integrating Neo4j database into langchain ecosystem

llm-movieagent. Semantic layer on top of a graph database to provide an LLM with a set of robust tools to interact with the database

diffbot-kg-chatbot. Knowledge graph construction and RAG demo using Diffbot and Neo4j

NeoGPT-Explorer. Knowledge-graph based chatbot using GPT3 and Neo4j

kg-rag. Supporting repository for the Essential GraphRAG book published by Manning

NeoGPT-Recommender. Context-aware knowledge-graph based chatbot using GPT4 and Neo4j

graphs-network-science. Accompanying repository for my book about Graph Data Science

trinity-ie. Information extraction pipeline containing coreference resolution, named entity linking, and relationship extraction

streamlit-neo4j-hackathon. Python

blog-datasets.

cypher-direction-competition. Repository that hold the information about the competition about validating and fixing relationship direction in Cypher statements based on the given schema

zeppelin-graph-algo. Repository of Notebooks taken from https://neo4j.com/graph-algorithms-book/

bitcoin-to-neo4jdash. Project that listens to bitcoin websocket API for new transactions and stores them to Neo4j to be analyzed

clinical-agent. This project is designed for a simple LLM agent with tools on a clinical knowledge graph in Neo4j.

neo4j-hp-viz. Demo App that uses GRANDstack to visualize Harry Potter network

neo4j-game-of-thrones. HTML

grand-sigmaJS. Network visualizations with SigmaJS and GrandStack (GraphQL + React + Apollo + Neo4j)

node2vec. Implementation of the node2vec algorithm.

SpaCIE. Python

llama_index. LlamaIndex (GPT Index) is a project that provides a central interface to connect your LLM's with external data.

hospitals-neo4j. HTML

neo4j-multimodal-rag.

mindgraph. proof of concept prototype for generating and querying against an ever-expanding knowledge graph with ai

graphrag. A modular graph-based Retrieval-Augmented Generation (RAG) system

auto_graph_llm. Experiment in developing generic toolset for Neo4j

langchain. ⚡ Building applications with LLMs through composability ⚡

llama-hub. A library of data loaders for LLMs made by the community -- to be used with LlamaIndex and/or LangChain

genai-stack. Langchain + Docker + Neo4j + Ollama

PyEmbeo. graph embeddings for neo4j in python

dspy. DSPy: The framework for programming—not prompting—foundation models

mem0. Memory for AI Agents; SOTA in AI Agent Memory, beating OpenAI Memory in accuracy by 26% - https://mem0.ai/research

entity-resolution. Entity resolution, also known as Data Matching or Record linkage is the task of finding a data set that refer to the same or similar real entity across different digital entities present on same or different data sets. Record linking is necessary when joining different entities which are similar and may or may not share some common identifiers. Ne