From unstructured PDF to clean database.
aikaruvi bridges the gap between static documents and database-driven design. Here's exactly how our backend processes your complex engineering specifications — step by step.
Secure PDF Upload
Upload your engineering drawing specs, instrument schedules, datasheets, or pipe line lists via the drag-and-drop dashboard. Any PDF format is accepted — scanned or native.
Your document is stored in an isolated, encrypted Google Cloud Storage folder. Access is restricted using secure IAM rules and custom authorisation tokens — your files are never accessible between accounts.
Drag & drop or click to upload any engineering PDF
Intelligent AI Extraction
Our FastAPI backend reads the PDF content and filters noise. It then communicates with OpenAI's structured extraction model using high-accuracy JSON schemas designed for engineering data.
We bypass standard OCR limitations by using vision models that understand structured table rows, tag names, equipment codes, and engineering properties — even on multi-column layouts and scanned pages.
Structured DB Output
The system returns validated, structured data fields. Review results in the dashboard, copy JSON, or export to CSV/Excel for direct import into your engineering tools.
Phase 2 Integration (coming soon): JSON outputs feed directly into our AutoCAD Plant3D DLL, syncing spec tables to dynamic P&ID blocks and 3D piping specs — without any manual mapping.
Data is validated against your engineering schema before export
Every standard engineering document format.
aikaruvi is pre-configured for the document types that dominate plant and process engineering projects.
Instrument Datasheets
ISA S20-format and vendor-specific datasheets. Extracts tag, service, range, material, process conditions, and engineering notes.
Valve & Fitting Schedules
Multi-row tabular schedules with tag, size, rating, material, end connection, and actuator type — all structured and numbered.
Line Lists
Process line identification with fluid service, design pressure/temperature, insulation, and piping class across complex multi-sheet formats.
Equipment Lists
Equipment tags, descriptions, capacities, operating weights, and design codes from project MR and spec packages.
I/O Lists
Marshalling and DCS I/O lists with signal type, range, cabinet ID, loop number, and associated instrument tags.
Custom Formats
Got a non-standard document format? Contact us and we'll configure a custom extraction schema for your specific templates.
Built on infrastructure you can trust.
Enterprise-grade components handling your most sensitive engineering documents.