Neo4j knowledge graph returns no landmark nodes even after ETL successfully runs

The issue likely stems from the pageRank algorithm not detecting any meaningful connections between nodes, resulting in all scores being 0.0, which prevents any node from being marked as a landmark. Ensure your graph has edges connecting nodes (e.g., Problem → RootCause → Solution) to enable scoring. Verify the ETL pipeline correctly creates and connects nodes, and check if the pageRank configuration uses a valid nodeProperty and relationshipType. Example: gds.pageRank.stream('graph', { nodeProperty: 'score', relationshipType: 'RELATED_TO' }).

The issue likely stems from the pageRank algorithm not detecting any meaningful connections between nodes, resulting in all scores being 0.0, which prevents any node from being marked as a landmark. Ensure your graph has edges that connect nodes meaningfully (e.g., Problem → RootCause → Solution). Verify the edge direction and existence using MATCH (n)-[r]->(m) RETURN COUNT(r).

MATCH (n)-[r]->(m) RETURN COUNT(r)

If no edges are found, the pageRank algorithm cannot compute scores. Check your ETL pipeline for edge creation logic.

Same root cause as the duplicate question — PageRank scores of 0.0 mean the GDS projection has no edges to propagate through. But here's the specific Neo4j AuraDB gotcha:

AuraDB GDS availability

Not all AuraDB tiers include GDS (Graph Data Science). Free and Professional tiers have limited or no GDS plugin access. If CALL gds.graph.project(...) succeeds but returns zero relationship count, or if PageRank silently returns all zeros, check:

CALL gds.version() YIELD version

If this errors, GDS isn't available on your tier.

The ETL ordering problem

Most likely cause: your ETL creates nodes in one transaction and edges in a subsequent step, but the edge creation silently matches zero nodes because of property mismatches:

// This MERGE creates new disconnected nodes if questionId doesn't match exactly
MERGE (p:Problem {questionId: $qid})
MERGE (s:Solution {questionId: $qid})
MERGE (p)-[:FIXED_BY]->(s)

Debug with:

// Count edges by type
MATCH ()-[r]->() RETURN type(r), count(r)

// Find orphan nodes (no edges at all)
MATCH (n) WHERE NOT (n)--() RETURN labels(n), count(n)

If most nodes are orphans, the edge creation step is failing silently.

Landmark promotion without Pattern nodes

If your pipeline promotes isLandmark only on Pattern nodes, and the LLM extraction produces zero Patterns (common — see the related batch extraction question), then landmarks will always be empty regardless of PageRank scores.

Quick fix: promote landmarks from the top N PageRank nodes across ALL types, not just Patterns:

MATCH (n) WHERE n.pageRank > 0
WITH n ORDER BY n.pageRank DESC LIMIT 10
SET n.isLandmark = true

This is a cascade failure with three links:

1. ETL model omits Pattern nodes If your extraction prompt includes a rule like "omit nodes you're not confident about" or treats Pattern as optional, weaker models (e.g. Claude Haiku) will skip them almost entirely, especially when the extraction is batched and the model is optimizing for token efficiency. Problem, RootCause, and Solution nodes feel concrete — Pattern is abstract and gets skipped.

2. No Pattern nodes = no INSTANCE_OF edges The Problem INSTANCE_OF Pattern edges are what the pageRank pipeline scores against. The GDS pageRank query counts inbound INSTANCE_OF edges to score Pattern nodes. If no Pattern nodes exist, no scores get written — all nodes stay at pageRank 0.0.

3. pageRank 0 = no landmarks The isLandmark promotion step takes the top N% of nodes by pageRank. If everything is 0, nothing gets promoted. graph_initialize returns an empty landmark set.

Fix: Make Pattern nodes required in your extraction prompt, not optional. Include a concrete worked example showing the full Problem → RootCause → Solution → Pattern chain with an explicit INSTANCE_OF edge. Change the rule from "omit if uncertain" to "always abstract the problem to its general pattern — ask yourself 'what class of problem is this?'".

Also switch to a stronger model (Sonnet vs Haiku) for extraction — the quality difference on structured output is significant.

After fixing the prompt and re-running ETL, the GDS pipeline will score Pattern nodes by INSTANCE_OF edge count and the top percentile will be promoted to isLandmark=true.