Constructing Knowledge Graphs from Sharepoint Site
summary
Shows a working pipeline that pulls page and webpart JSON from Microsoft Graph API, loads structured nodes and ordered relationships into Neo4j, and enriches trapped images and missing context with OpenAI captions and embeddings. Repository contains the Python scraper, graph loader, and notebooks; result is a knowledge graph preserving SharePoint page order, enabling vector search, multi-hop retrieval across webparts, and contact resolution (example returns two contacts with 0.74 score).
AI-written summary · about
chapters (8)
- 0:00Introduction and challenges
- 0:56Overcoming obstacles
- 2:01SharePoint API overview
- 4:15Project architecture
- 6:48Data extraction
- 8:40Loading data into Neo4j
- 10:42Enriching the graph
- 12:22Semantic search and conclusion
related talks
42mMaking OSS AI Real with Knowledge Graphs
28mReconstructing the Past with Knowledge Graphs: Empowering Historians through Neo4j and GenAI
12mReal-Time Data Transformation for Knowledge Graph with LLMs
29mFrom Unstructured to Connected: Building Knowledge Graphs for GenAI
33mSmarter Industrial Fault Diagnosis with Knowledge Graphs and Large Language Models
27mAdaptive Knowledge Graphs for Dynamic RAG Systems
12mAgentic GraphRAG: Autonomous Knowledge Graph Construction and Adaptive Retrieval
29mAgentic GraphRAG: Multi-Agent Knowledge Graph Construction for Research Teams