PDF to structured data

Run document.parse (LlamaParse) on a vendor invoice PDF, then extract_structured to typed JSON. End-to-end in two calls.

Cost~$0.05 per PDF

Operations

document.parsetext_generation.extract_structured

Prerequisites

document.parse enabled (LlamaParse-backed).

Walkthrough

1. Parse

Returns markdown that preserves tables and layout - much friendlier to LLMs than raw PDF text.

bash# LlamaParse converts PDF to structured markdown.
curl -X POST https://www.upivia.com/v1/service-requests \
  -H "Authorization: Bearer $AGENT_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "service":"document",
    "operation":"parse",
    "payload":{"url":"https://uploads.example.com/inv-001.pdf","mode":"markdown"}
  }'

2. Extract

Feed the markdown into text_generation.extract_structured with your invoice schema (see the 'Structured extraction' tutorial).

Next steps

Audit every call at /audit-logs, watch spend at /usage, and tune budgets per service on the agent's page.

Create an account →