Visualize extraction workflow stages and service health
Ingestion
Phase 0: Metadata, TOC, page images
Extraction
Phase 1: Core PDF extraction
Markdown
Phase 2: Layout-aware markdown
Enhancement
Phase 3: Table OCR
Chunking
Phase 3.5: Semantic chunking
NER
Named entity recognition
Events
Leadership event extraction
Classification
Document classification
Embeddings
Semantic embeddings
Resolution
Cross-document entity linking
Finalize
Complete pipeline
Redis
Event streams & checkpointing (port 6379)
PostgreSQL
Jobs, documents, page results (port 5432)
Neo4j
Knowledge graph database (port 7687)
Neo4j GraphQL
GraphQL subgraph service (port 8018)
Apollo Gateway
GraphQL federation (port 4000)
Jobs API
FastAPI backend (port 8000)
Loading...
Press enter or space to select a node. You can then use the arrow keys to move the node around. Press delete to remove it and escape to cancel.
Press enter or space to select an edge. You can then press delete to remove it or escape to cancel.