Skip to content

graph-loader.md

Latest commit

 

History

History
73 lines (51 loc) · 1.51 KB

graph-loader.md

File metadata and controls

73 lines (51 loc) · 1.51 KB
Raw
description Load and query exported Code-Graph-RAG knowledge graphs with the Python SDK.

Graph Loader

The load_graph function loads exported JSON graph data for programmatic analysis.

Export a Graph

First, export the knowledge graph to JSON:

cgr export -o my_graph.json

Or export during graph update:

cgr start --repo-path /path/to/repo --update-graph --clean -o my_graph.json

Load and Query

from cgr import load_graph

graph = load_graph("my_graph.json")

Summary Statistics

summary = graph.summary()
print(f"Total nodes: {summary['total_nodes']}")
print(f"Total relationships: {summary['total_relationships']}")

Find Nodes by Label

functions = graph.find_nodes_by_label("Function")
classes = graph.find_nodes_by_label("Class")
modules = graph.find_nodes_by_label("Module")

Analyse Relationships

for func in functions[:5]:
    relationships = graph.get_relationships_for_node(func.node_id)
    print(f"Function {func.properties['name']} has {len(relationships)} relationships")

Query Memgraph Directly

For live queries against a running Memgraph instance:

from cgr import MemgraphIngestor

with MemgraphIngestor(host="localhost", port=7687) as db:
    rows = db.fetch_all("MATCH (f:Function) RETURN f.name LIMIT 10")
    for row in rows:
        print(row)

Use Cases

  • Integration with other tools
  • Custom analysis scripts
  • Building documentation generators
  • Creating code metrics dashboards