📄 Real Estates Dossier
Italian real estate auction PDF extraction workflow. Pages are rendered to PNG, OCR'd individually with Cirrascale's olmOCR-2-7B-1025 model, and joined into raw and corrected text outputs. Structured extraction is opt-in. When enabled, document classification feeds a TypeSafe Jev decision pass first; a user-defined policy can then skip or trigger the Gemma full JSON extraction pass. v3 improvements over v2: - Cirrascale OCR with per-page processing and response capture - Text corrections and intermediate artifacts - Structured logging with proper exception hierarchy Features: - Battle-tested OCR pipeline with text corrections - Parallel page processing - Comprehensive caching and workspace management
Template Information
- Workflow ID
real_estates_extraction_v3- Version
- 3.1.0
- Status
- Active
- Author
- AECS4U Ocular Team
- Created
- 2026-02-26T00:00:00Z
- Steps
- 3
- Tags
- extraction property italian real-estate auction ocr v3 production jev conditional-extraction
Input Schema
file_path- str
enable_corrections- bool
mojibake_fix- bool
digit_fix_mode- str
force- bool
enable_structure_extraction- bool
classification_confidence_threshold- float
gemma_model- str
jev_model- str
jev_questions_json- str
gemma_policy_json- str
jev_failure_policy- str
Instance Presets
0No instances defined for this template
Workflow Flowchart
Workflow Steps
- Step ID
ocr_extraction- Processor Type
- python
- Timeout
- 900s
- Max Retries
- 2
- Retry on Failure
- Yes
- Cache Results
- Yes
Input Mapping
| Target Parameter | Source Value |
|---|---|
file_path |
file_path |
enable_corrections |
enable_corrections |
- Step ID
document_classification- Processor Type
- python
- Timeout
- 300s
- Max Retries
- 2
- Retry on Failure
- Yes
- Cache Results
- Yes
- Step ID
ensemble_extraction- Processor Type
- python
- Timeout
- 900s
- Max Retries
- 2
- Retry on Failure
- Yes
- Cache Results
- Yes