Work · AI / Automation · 2024
AI-powered reservation parsing for multilingual PDFs
An LLM-backed pipeline that extracts structured booking data from multilingual reservation PDFs (English + Arabic), with vendor-specific parsing rules and JSON Schema-validated outputs.
Result
95%+ extraction accuracy
on the production set.
- Client
- Direct Hotels
- Sector
- AI / Automation
- Year
- 2024
- Role
- Tech Lead
- Length
- 8 weeks
- Team
- 2 One lead, one backend.
Brief and outcome
What was needed.
Direct Hotels was burning hours every day on manual data entry — bookings come in as PDFs from a long tail of suppliers, in two languages, in formats that change without notice. We built a structured extraction pipeline that reads the PDFs once, validates the output, and posts straight into the reservation system.
What came of it.
Manual reservation entry dropped from a multi-hour daily task to a near-zero exception queue. Pipeline accuracy held above 95% on the production set, and the structured outputs flow directly into the booking CRM.
What was built
5 parts,
shipped.
A selection of projects shipped through Syntorium and our CTO's prior engagements.
Dual-model architecture
OpenAI GPT-4V for image-heavy PDFs, Anthropic Claude for text-dense ones. Both are abstracted behind a model-agnostic adapter so we can swap in new entrants without rewriting the pipeline.
Vendor-specific parsing strategies
Different suppliers have wildly different layouts; the pipeline picks a strategy per source with a fallback to the generic prompt.
Bilingual (English + Arabic) extraction
Including right-to-left layouts, mixed-direction lines, and Arabic-formatted dates.
JSON Schema validation + self-healing
Every model response is validated against a Zod-equivalent schema in PHP. Invalid responses re-prompt the model with the validator's complaint.
Cost ceiling per document
A hard cap on tokens per PDF, monitored in a dashboard. Saves the team from a runaway bill if a malformed PDF triggers a retry loop.
More work
Start
Send a brief.
We reply within one working day with a written estimate or a call.
No newsletters. Your details aren't shared.
Or say hello.
Sunday to Thursday, 09:00–18:00, GMT+4. Remote engineers cover the EU and the US asynchronously. We work in English, Arabic and Urdu.
