Back to projects▸**ETL:** Multi-source document ingestion (PDFs, structured data) with automated preprocessing ▸**Knowledge Graph:** Neo4j stores entities + relationships; Cypher queries surface connections invisible in flat text ▸**GraphRAG:** Custom graph traversal chains augment LLM context with relational data from the knowledge graph ▸**Summarization:** Multi-document LLM summarization with source attribution
Production NDA — described architecturally
GraphRAG Due Diligence Tool
Knowledge-graph-powered due diligence document analysis
Knowledge-graph-powered analysis platform for due diligence workflows. Automated multi-source ETL and multi-document summarization via LLM pipelines. Meaningfully reduced manual research and analyst time.
Tech stack
Neo4jPythonFastAPIDocker
Problem
Analysts spending days manually cross-referencing documents across multiple sources to identify key entities, relationships, and risks.
Architecture
Outcome
Meaningfully reduced analyst research cycle time. Surfaced entity relationships that manual review consistently missed.