Knowledge Graph RAG (ToPWR)
FastAPI + Neo4j + LangGraph workflow that turns natural language into Cypher.
A university data assistant designed to help students and staff navigate institutional information faster. The system combines a React chat UI, a FastAPI application layer, an MCP server, and a Neo4j knowledge graph so users can ask natural language questions and retrieve structured university data.
Converted user questions into Cypher-backed graph retrieval
Added query routing, relevance checks, and optional Langfuse observability
Worked within a broader ETL pipeline that turns documents into graph knowledge
Impact
Natural language questions mapped to graph-backed university data
Role
Software / AI Engineer
Timeline
2025
Key tags
Problem
University information is scattered across departments, pages, and systems, which makes discovery slow for students and staff.
Solution
Built a knowledge-graph retrieval workflow that checks query relevance, generates Cypher, executes graph retrieval, and returns answers through an application API.
Architecture
The system combines a React frontend, a FastAPI backend, a FastMCP server, and Neo4j. LangGraph orchestrates the retrieval workflow, while separate ingestion flows process documents and populate the knowledge graph.
Challenges
- Modeling university entities and relationships cleanly in a graph schema
- Handling ambiguous user intent without unsafe or misleading queries
- Keeping retrieval tied to structured university data while preserving conversational UX
Technology stack
Continue exploring
More case studies
Lucid - AI Notes Platform
Helps students turn scattered lecture screenshots and notes into searchable study material.
NeuroPark - 3D Vehicle Detection
Supports smart parking analysis by estimating vehicles and scene geometry from regular RGB images.
Medical Chatbot RAG
Provides educational health Q&A from retrieved source content instead of free-form LLM answers.