Every Game Is Connected — I Built the Graph That Proves It

Description and use

The system uncovers hidden connections between video games using FalkorDB and AI narration, offering transparent, verifiable explanations.

Problem

Recommendation engines can tell you what games are similar but not why two games are connected across studios, decades, and genres.

Outcome

The system delivers quick (≈2 s) path discovery between arbitrary games, revealing five types of connections and providing verifiable AI narration. It demonstrates how to build a transparent, AI‑augmented graph reasoner for game data.

Workflow

• 1. User selects 2–4 games in the UI.
• 2. The app queries FalkorDB for paths between the selected games.
• 3. The reasoner suppresses hub nodes and overly common genres to avoid meaningless connections.
• 4. The shortestPath Cypher query retrieves nodes along the path.
• 5. IBM watsonx (Granite) generates a narrative from the path data, citing path IDs.
• 6. The UI highlights the path when a claim or node is clicked.
• 7. Users can explore random game sets via a slot‑machine feature.

Evidence

pick any 2–4 games, and it traverses a FalkorDB graph of 50,217 games, 84,296 nodes, and 1,023,292 relationships to find the hidden paths between them

Source

The narration is IBM watsonx (Granite), and it has exactly one job: explain paths the graph already found

Source

FalkorDB runs in Docker on a single IBM VPC virtual server (bx2-4x16, us-south). The app is a single-file Python 3.12 program using only the standard library

Source