📄 Document Extraction Demo
OCR with Tesseract — pick a sample document to see the extracted text and fields
This demo shows the
OCR step from our blog post
AI-Powered Document Extraction with Tesseract and Ollama.
The LLM-based field extraction (Ollama) is not included here — it's too heavy for a shared demo server.
Instead, we use lightweight heuristics to pull out common fields like invoice numbers, dates, and totals.
Loading samples...
OCR Output
Extracted Fields
Select a sample document above to begin.