# Knowledge Graph Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/knowledge-graph
> Markdown URL: https://aitinkerers.org/technologies/knowledge-graph.md
> Technology record last updated: 2026-02-25T06:47:07Z
> Generated: 2026-09-21T15:48:35Z

A Knowledge Graph (KG) is a semantic network: it models real-world entities (nodes) and their relationships (edges) to provide context and structure for machine reasoning.

Knowledge Graphs structure data as interconnected entities (nodes) and explicit relationships (edges), shifting data organization from 'strings to things' (Neo4j). This graph-based model enables systems to understand context, not just keywords. Major applications include Google’s Knowledge Graph (over 500 million objects) for enhanced search results and enterprise use cases like AI-powered recommendation engines (Netflix) and financial crime prevention (KYC/AML). KGs integrate disparate datasets, providing a unified, explainable knowledge base critical for advanced AI and data analytics.

- Official technology site: https://www.ibm.com/topics/knowledge-graph
- Public AI Tinkerers demos and talks: 9
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Talking to a huge product catalog in plain English using LLMs](https://chicago.aitinkerers.org/talks/rsvp_uJ7UIZ0RHQY)

At Fetch, we have a product catalog consisting of millions of products, in extremely granular levels of detail (even more specific than UPCs are!). It can be difficult to easily get summary stats about those products because of the hierarchical structure of the product categories, so I built a knowledge graph on top of the catalog. The cherry on top is a LangChain-driven interface to ask questions like "how many brands do we have in the Red Wine category?" or "what offers are we running right now for snack products?"

- Event context: AI Tinkerers Chicago February Meetup — 2025-02-18 — Chicago
- Public talk page: https://chicago.aitinkerers.org/talks/rsvp_uJ7UIZ0RHQY

### [Vital AI Agent Ecosystem + Chat.ai](https://nyc.aitinkerers.org/talks/rsvp_EplSu1Cm9yk)

We're building an open standard for deploying A.I. Agents and for A.I. Agent collaboration. Vital AI Agent Ecosystem is an open-source reference implementation of these. We'll demo this platform for deploying an Agent and enabling different Agents to communicate and collaborate with each other and people.

- Event context: AI Tinkerers - New York City - December 2024 Meetup — 2024-12-12 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_EplSu1Cm9yk

### [CopilotBuilder - Democratizing Generative AI agent creation for every organization](https://columbus.aitinkerers.org/talks/rsvp_AwGKD4NWtwk)

We will demo our platform that we have been working on for over 9 months that allows individuals and organizations of any technical competency to create and deploy incredibly sophisticated AI-based agents (called "Copilots"). We will walk thru our application architecture and discuss the challenges that we have faced over the past year to create the functionality that the current platform has.

- Event context: AI Tinkerers - Columbus December Meetup — 2024-12-05 — Columbus
- Public talk page: https://columbus.aitinkerers.org/talks/rsvp_AwGKD4NWtwk

### [Building a Real-Time Knowledge Graph for an Autonomous AI Trader](https://montreal.aitinkerers.org/talks/rsvp_jXF52pJo9EI)

I'm excited to share my journey in building an autonomous AI trader powered by a real-time knowledge graph. Over the past three years, I’ve faced countless challenges, from database migrations to handling LLM hallucinations, endless parsing and validation. I'll walk you through the actual code I used and demonstrate the workings of my real-time knowledge graph. The highlight will be my custom LLM python package (93 stars) and the process of migrating databases multiple times to survive and achieve the best results. Join me as I share the technical nitty-gritty, the surprises along the way, and the valuable lessons learned. No slides, just a pure code walkthrough and a live example!

- Event context: AI Tinkerers Montreal - December 2024 Meetup at IVADO Labs — 2024-12-03 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_jXF52pJo9EI

### [Graph RAG: Combining the power of vectors and graphs for better retrieval](https://toronto.aitinkerers.org/talks/rsvp_34ZT1TVKokY)

In this demo, I'll showcase how to bring together the power of graph and vector search to provide LLMs with better context when generating responses for RAG. Because constructing a knowledge graph is typically the biggest bottleneck towards using them in real applications, I'll also quickly showcase some new frameworks and tools to prompt LLMs to extract structured data from unstructured text, and how to easily store them as an on-disk graph that can be improved over time.

- Event context: AI Tinkerers Toronto - Spooky Botober Meetup at Mozilla HQ — 2024-10-30 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_34ZT1TVKokY

### [Enhancing AI with RAG - Techniques to improve accuracy](https://bogota.aitinkerers.org/talks/rsvp_QjI40TNRTXw)

This talk explores how to optimize AI companions for project management using RAG. Standard RAG models struggle with context, leading to incomplete or inaccurate data retrieval, which is important when managing resources and making decisions. We’ll explore GraphRAG and context-aware RAG, which use knowledge graphs and enhanced contextual embeddings to improve the precision and relevance of information retrieval.

- Event context: AI Tinkerers Octubre en Colombia 4.0 — 2024-10-30 — Bogotá
- Public talk page: https://bogota.aitinkerers.org/talks/rsvp_QjI40TNRTXw

### [Accelerating Research Discovery: Integrating HippoRAG and Bodhi for Intelligent Paper Recommendation and Comprehension](https://ann-arbor.aitinkerers.org/talks/rsvp_cBRaUxqzNBs)

In the rapidly expanding universe of scientific literature, novice researchers often face the daunting task of identifying and understanding the most relevant papers in their field. This presentation introduces an integrated approach that leverages HippoRAG—a neurobiologically inspired retrieval framework—and Bodhi, a novel system designed to empower researchers by providing curated reading paths through complex research areas. Our project harnesses HippoRAG to enable multi-hop reasoning and capture synonymy relations between paper topics that traditional citation datasets often overlook. By ingesting research papers into a knowledge graph and applying algorithms inspired by the hippocampal indexing theory of human memory, HippoRAG facilitates deeper and more efficient knowledge integration. This allows users to receive highly relevant paper recommendations directly from open-ended research questions. For example, a query like "I want to create hardware-accelerated algorithms for machine learning inference" yields a tailored list of essential papers to read. Building upon this foundation, Bodhi guides users through the most pivotal papers in a specific area, organized in order of complexity. The process involves: 1. Embedding Research Papers: We embed metadata from research papers and perform clustering to identify different research areas. 2. Filtering Important Papers: Within each cluster, we filter for the top n most important papers, assigning an importance score that reflects a paper's necessity for understanding the cluster's research. 3. Creating Directed Graphs: We construct directed graphs for each sparsified cluster, ensuring edges flow from simpler papers to more complex ones. 4. Finding Minimum Spanning Arborescence (MSA): Using the Chu-Liu/Edmonds/Bock Algorithm, we derive the MSA for each directed graph. The resulting arborescence serves as a curated reading path for researchers. By integrating HippoRAG's advanced retrieval capabilities with Bodhi's structured learning paths, our project offers a powerful tool that accelerates learning and comprehension, enabling researchers to navigate vast scientific domains efficiently and effectively.

- Event context: AI Tinkerers: Ann Arbor - September 18 — 2024-09-18 — Ann Arbor
- Public talk page: https://ann-arbor.aitinkerers.org/talks/rsvp_cBRaUxqzNBs

### [Tractorbeam](https://chicago.aitinkerers.org/talks/rsvp__bgLVv8Dl5A)

We are building a text to knowledge graph retrieval tool! This will be the first time we show it to the public.

- Event context: AI Tinkerers Chicago July Meetup — 2024-07-23 — Chicago
- Public talk page: https://chicago.aitinkerers.org/talks/rsvp__bgLVv8Dl5A

### [From text to graph and back again, with entity extraction and GraphRAG Q&A.](https://berlin.aitinkerers.org/talks/rsvp_wnnCu9MBJ1g)

Usually you only see text + embeddings with LLMs but many advanced RAG patterns need more structure. In a knowledge graph you can represent that structure and use it to provide better context for Q&A. But how to get there from text documents? You can use the language skills of LLMs to extract entities and relationships from texts and store them in the graph connected to the original documents and chunks. The application and code I'll show will demonstrate how to get from text to graph to GraphRAG and I will highlight the good and the difficult aspects of this approach.

- Event context: Ollama & Friends coming to AI Tinkerers Berlin — 2024-07-18 — Berlin
- Public talk page: https://berlin.aitinkerers.org/talks/rsvp_wnnCu9MBJ1g

## Related Technologies

- [RAG](https://aitinkerers.org/technologies/rag) ([Markdown](https://aitinkerers.org/technologies/rag.md)) — 147 public demos
- [GraphRAG](https://aitinkerers.org/technologies/graphrag) ([Markdown](https://aitinkerers.org/technologies/graphrag.md)) — 13 public demos
- [LangChain](https://aitinkerers.org/technologies/langchain) ([Markdown](https://aitinkerers.org/technologies/langchain.md)) — 445 public demos
- [Agentic AI](https://aitinkerers.org/technologies/agentic-ai) ([Markdown](https://aitinkerers.org/technologies/agentic-ai.md)) — 6 public demos
- [AI agents](https://aitinkerers.org/technologies/ai-agents) ([Markdown](https://aitinkerers.org/technologies/ai-agents.md)) — 35 public demos
- [alBERT](https://aitinkerers.org/technologies/albert) ([Markdown](https://aitinkerers.org/technologies/albert.md)) — 4 public demos
- [BERT](https://aitinkerers.org/technologies/bert) ([Markdown](https://aitinkerers.org/technologies/bert.md)) — 179 public demos
- [Bodhi](https://aitinkerers.org/technologies/bodhi) ([Markdown](https://aitinkerers.org/technologies/bodhi.md)) — 1 public demo
- [Boost Graph Library](https://aitinkerers.org/technologies/boost-graph-library) ([Markdown](https://aitinkerers.org/technologies/boost-graph-library.md)) — 1 public demo
- [Chu-Liu/Edmonds algorithm](https://aitinkerers.org/technologies/chu-liu-edmonds-algorithm) ([Markdown](https://aitinkerers.org/technologies/chu-liu-edmonds-algorithm.md)) — 1 public demo
- [Copilot Evaluations](https://aitinkerers.org/technologies/copilot-evaluations) ([Markdown](https://aitinkerers.org/technologies/copilot-evaluations.md)) — 1 public demo
- [Database Migration](https://aitinkerers.org/technologies/database-migration) ([Markdown](https://aitinkerers.org/technologies/database-migration.md)) — 1 public demo
- [ELMo](https://aitinkerers.org/technologies/elmo) ([Markdown](https://aitinkerers.org/technologies/elmo.md)) — 1 public demo
- [Embeddings](https://aitinkerers.org/technologies/embeddings) ([Markdown](https://aitinkerers.org/technologies/embeddings.md)) — 22 public demos
- [GPT-2](https://aitinkerers.org/technologies/gpt-2) ([Markdown](https://aitinkerers.org/technologies/gpt-2.md)) — 4 public demos
- [GPT-3](https://aitinkerers.org/technologies/gpt-3) ([Markdown](https://aitinkerers.org/technologies/gpt-3.md)) — 191 public demos
- [Graph database](https://aitinkerers.org/technologies/graph-database) ([Markdown](https://aitinkerers.org/technologies/graph-database.md)) — 2 public demos
- [GraphRAG Q&A](https://aitinkerers.org/technologies/graphrag-q-a) ([Markdown](https://aitinkerers.org/technologies/graphrag-q-a.md)) — 1 public demo