Execute read-only Cypher queries on Neo4j databases to retrieve data for GraphRAG applications, supporting semantic search and complex graph traversals.
Enables LLMs to run complex graph algorithms on Neo4j databases, answering graph-related questions by selecting and executing appropriate parameterised graph algorithms.
Enables LLMs to interact with Neo4j graph databases using natural language to execute Cypher queries and introspect database schemas. It supports both read and write operations for local, Docker, and cloud-based instances like Neo4j Aura.
Execute read-only Cypher queries on Neo4j to retrieve graph data for GraphRAG applications. Fetch nodes, relationships, and properties without altering the database.
Rebuild the code graph for an already-indexed source when graph-backed lookups return empty. Re-extracts entities and returns a job_id to poll for completion.
Rebuilds the Neo4j code graph for all indexed sources to repair empty-graph issues, enqueueing a graph job per source. Use when definitions or graph lookups return empty results.
Parse, chunk, embed, and store a code file in vectors and entities to enable GraphRAG search. Returns a job_id for tracking; set force=true to re-index unchanged files.
Find code by meaning, not just exact strings. Search across indexed repositories to understand flows, plan changes, and locate implementations by behavior.
Query the Reactome Neo4j graph database with read-only Cypher statements to analyze biological pathways, while safeguards prevent writes and cap result sizes.
Check Graphiti temporal knowledge-graph backend health: reports provider, Neo4j URI, group ID, and reachability. Fails closed with a recovery command when unavailable.