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.

  • Laravel
  • OpenAI GPT-4V
  • Anthropic Claude
  • JSON Schema

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

The brief

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.

The outcome

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

Shipped

5 parts,
shipped.

From

A selection of projects shipped through Syntorium and our CTO's prior engagements.

  1. 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.

  2. Vendor-specific parsing strategies

    Different suppliers have wildly different layouts; the pipeline picks a strategy per source with a fallback to the generic prompt.

  3. Bilingual (English + Arabic) extraction

    Including right-to-left layouts, mixed-direction lines, and Arabic-formatted dates.

  4. 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.

  5. 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.

Open the brief form

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.