tree-graph-rag

Guide for designing and implementing a PostgreSQL database that fuses PageIndex-style document trees with LightRAG-style entity-relationship anchors. Use thi...

This skill appears coherent and implements the promised tree↔graph persistence and retrieval patterns. Before installing or running in production: 1) Review and control the db_pool credentials you supply (use a least-privilege DB role that can INSERT/SELECT on the pageindex_* tables but not superuser). 2) Review or provide a trusted llm_extract_func — the skill calls that function for each content row (do not pass an extract function that exfiltrates data). 3) For large datasets, implement batching/pagination and rate-limiting when calling the extractor and when writing to the DB. 4) Test on non-production data first and verify workspace filtering is enforced in your deployment. If you want, provide details of the DB driver and deployment topology and I can point out additional hardening steps.

Type: OpenClaw Skill Name: tree-graph-rag Version: 1.0.0 The skill provides a legitimate framework for implementing a hybrid Tree-Graph RAG system using PostgreSQL. It includes well-structured schema definitions (schema.sql), ingestion scripts (ingestion_core.py), and retrieval logic (retrieval_core.py) that correctly use parameterized queries and enforce multi-tenancy. No indicators of malicious intent, data exfiltration, or unauthorized execution were found.