Ocular Workflow Engine
Multi-step document processing workflows
11
Total Workflows
47
Total Executions
3
Active Now
94%
Success Rate
Legal Contract Analysis
Comprehensive analysis of legal contracts including: - Parties involved and their obligations - Key dates (effective date, termination date) - Financial terms and payment schedules - Termination clauses and conditions - Liability and indemnification clauses - Confidentiality and non-disclosure terms - Risk assessment and red flags
DeepInfra OLMoCR2 OCR
Resumable PDF-to-text OCR through DeepInfra's OpenAI-compatible endpoint.
Floor Plan OCR ยท Superfici
Carica una planimetria catastale o un'immagine, conferma la scala con una misura nota o con il rapporto stampato, traccia i perimetri degli ambienti e ottieni la superficie stimata stanza per stanza con un PDF brandizzabile. L'OCR suggerisce scale e quote leggibili; la misura finale usa sempre la calibrazione e i poligoni confermati dall'utente.
Images from Document
Extract embedded photos from scanned documents. For .docx files, extracts embedded images directly via python-docx. For .doc/.docm files, first converts the document to PDF via LibreOffice in headless mode. Converts each PDF page to a raster image, detects photo regions via contour analysis, OCRs the caption area below each photo, and saves cropped images as JPEGs with EXIF metadata containing the caption. Typical input: scanned property documentation with inline photographs (e.g. "Documentazione Fotografica" from Italian real-estate dossiers).
Invoice Data Extraction
Extract structured data from invoices including: - Invoice number, date, due date - Vendor and customer information - Line items with descriptions, quantities, prices - Subtotals, taxes, totals - Payment terms and methods
Medical Records Extraction
Extract structured data from medical records while ensuring HIPAA compliance: - Patient demographics - Medical history - Current medications - Allergies and adverse reactions - Lab results and vital signs - Diagnoses (ICD-10 codes) - Treatment plans - Provider notes NOTE: This workflow should only be used in HIPAA-compliant environments.
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
Receipt and Expense Scanning
Extract data from receipts for expense tracking and accounting: - Merchant name and location - Transaction date and time - Line items with descriptions and prices - Subtotal, tax, tip, total - Payment method - Category classification (meals, travel, office supplies, etc.)
Resume/CV Parsing
Extract structured data from resumes and CVs for ATS (Applicant Tracking Systems): - Personal information - Work experience with dates and responsibilities - Education history with degrees and institutions - Skills (technical, soft skills, languages) - Certifications and licenses - Projects and publications - Achievement highlights
Smart OCR
Resumable OCR uses the v3 text-quality correction pipeline before consumer-supplied structured JSON extraction.
YouTube Caption
Unified YouTube caption extraction and processing workflow. Consolidates youtube_caption_extraction_v1 and youtube_caption_processing_v1 into a single template using the youtube_pipeline processor's built-in modes. Modes (controlled by processor_config.mode): - caption_only: Extract captions (replaces youtube_caption_extraction_v1) - caption_with_text_processing: Extract + text normalization - caption_with_structure: Extract + processing + LLM structure extraction - full_pipeline: Complete processing (replaces youtube_caption_processing_v1) v2 improvements: - Integrated paragraphize support (previously CLI-only) - Single-step architecture aligned with engine capabilities - Timestamp-aware paragraph breaking - All processing modes in one template